Figure 1.
Overall flowchart of feature fusion-based preprocessing.
Citation: Nily Dan. Lipid-Nucleic Acid Supramolecular Complexes: Lipoplex Structure and the Kinetics of Formation[J]. AIMS Biophysics, 2015, 2(2): 163-183. doi: 10.3934/biophy.2015.2.163
| [1] | Guozhen Dong . A pixel-wise framework based on convolutional neural network for surface defect detection. Mathematical Biosciences and Engineering, 2022, 19(9): 8786-8803. doi: 10.3934/mbe.2022408 |
| [2] | Xuguo Yan, Liang Gao . A feature extraction and classification algorithm based on improved sparse auto-encoder for round steel surface defects. Mathematical Biosciences and Engineering, 2020, 17(5): 5369-5394. doi: 10.3934/mbe.2020290 |
| [3] | Xiaochen Liu, Weidong He, Yinghui Zhang, Shixuan Yao, Ze Cui . Effect of dual-convolutional neural network model fusion for Aluminum profile surface defects classification and recognition. Mathematical Biosciences and Engineering, 2022, 19(1): 997-1025. doi: 10.3934/mbe.2022046 |
| [4] | Hongxia Ni, Minzhen Wang, Liying Zhao . An improved Faster R-CNN for defect recognition of key components of transmission line. Mathematical Biosciences and Engineering, 2021, 18(4): 4679-4695. doi: 10.3934/mbe.2021237 |
| [5] | Lili Wang, Chunhe Song, Guangxi Wan, Shijie Cui . A surface defect detection method for steel pipe based on improved YOLO. Mathematical Biosciences and Engineering, 2024, 21(2): 3016-3036. doi: 10.3934/mbe.2024134 |
| [6] | Zhigao Zeng, Cheng Huang, Wenqiu Zhu, Zhiqiang Wen, Xinpan Yuan . Flower image classification based on an improved lightweight neural network with multi-scale feature fusion and attention mechanism. Mathematical Biosciences and Engineering, 2023, 20(8): 13900-13920. doi: 10.3934/mbe.2023619 |
| [7] | Yongmei Ren, Xiaohu Wang, Jie Yang . Maritime ship recognition based on convolutional neural network and linear weighted decision fusion for multimodal images. Mathematical Biosciences and Engineering, 2023, 20(10): 18545-18565. doi: 10.3934/mbe.2023823 |
| [8] | Yinghong Xie, Biao Yin, Xiaowei Han, Yan Hao . Improved YOLOv7-based steel surface defect detection algorithm. Mathematical Biosciences and Engineering, 2024, 21(1): 346-368. doi: 10.3934/mbe.2024016 |
| [9] | Jiaming Ding, Peigang Jiao, Kangning Li, Weibo Du . Road surface crack detection based on improved YOLOv5s. Mathematical Biosciences and Engineering, 2024, 21(3): 4269-4285. doi: 10.3934/mbe.2024188 |
| [10] | Naigong Yu, Hongzheng Li, Qiao Xu . A full-flow inspection method based on machine vision to detect wafer surface defects. Mathematical Biosciences and Engineering, 2023, 20(7): 11821-11846. doi: 10.3934/mbe.2023526 |
Surface defects are an important factor affecting the quality of steel plates and strips. More than 60% of the quality objection incidents by users of steel plate and strip products are prompted by surface defects, thus causing enormous economic losses to the steel companies [1]. With the technological advancement of optical instruments, image processing-based steel plate surface defect recognition has become a research focus of scholars worldwide [2,3,4]. High-quality images of steel plates can be captured by coordinating the camera, light source, and laser line. Additionally, the surface defects of the steel plate can be detected and classified by a custom algorithm. The automatic surface defect detection system can perform online detection of surface defects and provide timely feedback. Detection and timely feedback are key to improving the surface quality of steel plates and strips. With the improvement of the production line speed and the increasingly stringent requirements that users impose regarding product quality, it is urgent to improve the accuracy, speed, and efficiency of defect detection and recognition algorithms in surface detection systems.
The machine vision detection algorithm consists of two steps: Feature extraction and classification. Multiple sets of features from different aspects, such as gray level, shape, and texture, can be extracted from the defect image and are conducive to the correct classification of defects. However, too many features affect the complexity and performance of the classifier. To achieve the best possible classification result without losing features, feature selection methods are generally used to process the features. Commonly used feature extraction algorithms include the gray-level cooccurrence matrix (GLCM) [5] and scale-invariant feature transformation (SIFT) [6]. With these methods, a high-dimensional space is mapped to a low-dimensional space to generate a linear combination of the original features and to reduce the feature dimension. Defect classification falls under the scope of pattern recognition. Commonly used classification algorithms include support vector machines [7], naïve Bayes [8], K-nearest neighbors [9], and random forests (RFs) [10]. Relevant classification algorithms have received increasing attention and have achieved good results in practice. However, the abovementioned traditional detection methods have poor generalization ability and rely on the personal experience of researchers to design the feature engineering. Hence, it is very difficult to apply these methods in large-scale industrial production.
In recent years, deep convolutional neural networks (CNNs) [11,12,13] have sparked a resurgence of visual research because of the benefit of self-learning image features. Inspired by the biological natural visual perception mechanism, CNNs can substantially reduce the number of training parameters by using the weight sharing mechanism mainly through supervised learning and backpropagation training. However, in practical applications, because specific parameters, such as weight bias in training, cannot be set, deep CNNs have certain shortcomings. Therefore, only the hyperparameters during learning can be adjusted to control the fitting. Then, the weight bias parameters needed for recognition are generated. This black-box algorithm has been criticized by researchers. Especially in steel plate surface defect recognition, due to the low contrast of image data, CNNs learn image features through randomly generated convolution kernels. By using such convolution kernels with uncertain parameters, important features may be unminable. The unminability of important features easily leads to misjudgment and affects the further improvement of the recognition rate.
To detect cracks in nuclear power plant components, Chen [14] and Jahanshahi et al. proposed a deep learning framework based on a CNN and naï ve Bayes data fusion scheme to analyze single video frames for crack detection. The authors presented a new data fusion scheme to agammaegate the information extracted from each video frame to enhance the overall performance and robustness of the system. A method to extract the potential features of steel plate defects by fusing multiple convolutional network feature layers was proposed by He [15]. However, this method relies on the network to perform the fusion, and there is a certain randomness in the learning process; additionally, this method needs a huge amount of data. Wang et al. [16] proposed an improved RF algorithm with optimal multi-feature-set fusion for distributed defect recognition. This algorithm fuses the histogram of oriented gradients (HOG) feature set and GLCM feature set by using the multi-feature-set fusion factor to change the number of decision trees corresponding to each feature set in the RF algorithm. In this paper, a feature fusion preprocessing method is designed. This method can achieve a high recognition rate for six categories of defects by using a small amount of data, help the CNN to mine the deeper features of steel plate defect images, and give full play to the learning advantage of neural networks.
Since the matrices and defects of steel plates are mostly gray and black, the overall contrast between the defects and their defects is extremely low. Even if an advanced color camera is used to collect images in a red-green-blue format, the color features of steel plate defects are not obvious. Therefore, the images acquired by industrial cameras are mostly single-channel grayscale images. In this study, specific contour and texture detection operators are combined to process the original grayscale image acquired by an industrial camera to extract the image features, fuse the image features with the original image based on the channel model, and finally convert the image to a single channel based on a certain weight ratio. By using the above processing, not only can the feature dimension of the image be increased and the image be more easily activated by the network to extract features, but the same pixel level as that of the original grayscale image can also be guaranteed, without wasting extra computational cost. Additionally, artificial guidance helps the CNN learn image features purposefully and avoid the drawbacks of black-box algorithms, thereby improving the recognition accuracy of low-contrast images.
The main contributions of this study are as follows:
(1) This study promotes the purposeful learning of a CNN, improves the classification capability of the network, and proposes a multichannel fusion strategy based on the combination of feature operators. This strategy not only increases the feature dimension but also retains the feature information of the original image.
(2) This study proposes converting multiple channels into a single channel for network training according to a certain weight ratio to reduce computational cost. Such a conversion not only ensures the classification accuracy but also does not affect the computational speed.
(3) This study obtains the optimal weight ratio of fusion and conversion by using the traversal method, which involves comparing the impacts of different fusion and conversion schemes on the classification results.
When a CNN extracts images, the shallow convolution kernel is mainly used to extract the edge features, and the deep convolution kernel is mainly used to extract the high-level abstract features, such as texture. Then, these features are integrated through the full connection layer to make the classification. A convolution kernel with a specific template can extract the directional features of the image by using, e.g., the Sobel [17], Laplace [18], Prewitt [19], and Roberts operators [20]; the texture features of image data can be encoded by contrast and integration of pixels, such as with the local binary pattern (LBP) [21]. In this paper, a feature extraction operator is used to extract the edge and texture information of an image to make it is easier for the shallow convolution kernel to learn edge features and for the deep convolution kernel to learn texture features. Additionally, the influence of different fusion schemes on the steel plate surface defect recognition rate is investigated.
Currently, five feature extraction operators are commonly used: Sobel, Laplace, Prewitt, Robert, and LBP. In this paper, we choose each pair of these operators to process the original grayscale image, and the resulting feature matrix is fused with the original grayscale matrix. The original grayscale matrix is placed in the middle channel, and the image processed by the feature operators is randomly placed on the remaining two channels. Fifteen combination schemes of the same feature operator and different feature operators form a three-channel color-effect image. The three-channel data after fusion results in the data calculation burden for two additional channels in the model. In contrast, the model of the original grayscale image requires only the data calculation for a single channel. To mitigate the increase in computational load after multichannel fusion, we use a traversal method to explore the optimal weight ratio and convert the three-channel image data into single-channel image data according to a certain weight ratio. The flowchart is shown in Figure 1.
In this study, the same CNN framework and hyperparameters are used for the training. The sensitivity of the feature fusion preprocessing model at the defect area is verified using a heat map and a feature activation map of the visual learning area. The accuracy (acc)-loss curve is used to observe the convergence of the model before and after feature preprocessing. The confusion matrix is used to assess the accuracy of network recognition before and after feature fusion preprocessing. The goal of the experiment is to find the optimal fusion scheme and conversion weight.
The NEU steel surface defect database created by Song et al. [22] of Northeastern University, China, was selected for use in this study. There are six categories of defects, namely, crazing, inclusion, patches, pitted, rolled-in, and scratches. There are 300 sample data points for each defect category, thus, resulting in a total of 1800 data points. The image resolution is 200 × 200 pixels. Figure 2 shows the defect samples.
Defect recognition based on the NEU steel plate surface defect database [23] faces three difficulties: (1) Defects of different classes have similar features; (2) illumination and material changes can affect the gray value of the acquired defect image; and (3) there are effects of various noises. To prevent overfitting, data augmentation is used in this study to expand the existing database capacity to 5000 samples, to increase the data volume of the experiment set, and to improve the generalization ability of the model. The experimental set in this paper is divided into three categories: Training set, validation set and test set, which are distributed according to the ratio of 7:2:1. So there are 3500 samples in training set, 1000 samples in validation set and 500 samples in test set. In order to ensure the consistency of the samples, the number of samples for each category in each sample set is roughly the same.
To fairly compare the data results before and after feature fusion processing, the exact same hyperparameters are used as follows: Adam, which is used as the optimizer; ReLU, which is used as the activation function; random initialization of weights; and use of the learning rate decay strategy with an initial learning rate of 0.00001, an epoch of 100, and a batch size of 32.
All experiments were run on a graphics workstation with two 10-core Intel Xeon E5-260 Wv4 central processing units (CPUs), an NVIDIA Titan 1080Ti graphics processing unit (GPU), and 128 GB memory. Windows 10-based Python was the development environment, and Keras was used as the learning framework.
Five classical models, Lenet-5 [24], Alexnet [25], VGG16 [26], InceptionV3 [27], and Resnet50 [28], are selected as the main framework of the CNN. Taking the original image data as samples, the recognition accuracies of these classical network models are compared using identical hyperparameters. The results of this comparison are shown in Figure 3. VGG16 has the highest recognition rate, up to 95.55%. Therefore, this model is the most suitable for learning the features of the NEU data. Therefore, VGG16 is chosen as the main framework.
To study the influence of the fusion of the same operators and the original image on the model, the image processed by each operator is selected and combined with the original grayscale image. The original grayscale data are placed in the middle channel, and the grayscale matrix is placed in the other two channels. The result is five different fusion schemes, as shown in Figure 4. Five sets of experiments (Nos. 1 to 5) are carried out for each fusion scheme by using the above hyperparameters for training. Hence, there are a total of 25 sets of experiments. The results are shown in Table 1. The fusion scheme of Sobel:image:Sobel has the highest average accuracy, reaching 96.22%.
| Conversion weights | Accuracy | Average Accuracy | ||||
| No. 1 | No. 2 | No. 3 | No. 4 | No. 5 | ||
| Sobel:img:Sobel | 97.24 | 96.54 | 94.27 | 93.28 | 96.77 | 96.22 |
| Roberts:img:Roberts | 95.34 | 95.49 | 94.65 | 96.97 | 95.30 | 95.55 |
| Prewitt:img:Prewitt | 95.25 | 93.94 | 95.21 | 94.24 | 94.71 | 94.67 |
| Laplace:img:Laplace | 88.13 | 87.12 | 86.44 | 87.63 | 87.08 | 87.28 |
| LBP:img:LBP | 92.11 | 92.48 | 92.26 | 93.32 | 94.43 | 92.92 |
DownLoad:
CSV
To study the influence of the feature operator combination scheme on the recognition accuracy of the model, the image processed by each pair of operators is selected and combined with the original grayscale image, and the original grayscale data are placed in the middle channel, while the grayscale matrix processed by the two operators is randomly placed in the other two channels. Ten combination schemes are based on channel fusion, as shown in Figure 5. The fused data are all in color, and the inclusion areas of the images with edge operator fusion tend to be darker. The inclusion area of the image data processed by the LBP operator and the texture of the steel plate background are more prominent. Using the aforementioned model and hyperparameters, five sets of experiments (Nos. 1 to 5) were carried out for each fusion scheme; thus, a total of 50 experiments were carried out. The accuracy of the fusion results obtained using different operators is shown in Table 2.
| Fusion scheme | Accuracy | Average Accuracy | ||||
| No. 1 | No. 2 | No. 3 | No. 4 | No. 5 | ||
| Sobel:img:Roberts | 98.88 | 97.36 | 98.05 | 99.09 | 97.97 | 98.27 |
| Sobel:img:Laplace | 97.51 | 98.14 | 98.98 | 98.91 | 99.45 | 98.61 |
| Sobel:img:Prewitt | 98.51 | 97.04 | 98.17 | 99.01 | 97.27 | 98.00 |
| Sobel:img:LBP | 76.11 | 76.25 | 75.22 | 74.89 | 75.58 | 75.61 |
| Roberts:img:Laplace | 98.02 | 96.94 | 96.01 | 98.57 | 99.61 | 97.83 |
| Roberts:img:Prewitt | 95.17 | 96.37 | 95.25 | 96.44 | 97.32 | 96.11 |
| Roberts:img:LBP | 81.21 | 81.37 | 83.27 | 81.65 | 80.25 | 81.55 |
| Laplace:img:Prewitt | 97.41 | 97.11 | 97.02 | 96.51 | 95.55 | 96.72 |
| Laplace:img:LBP | 70.52 | 67.61 | 65.84 | 64.32 | 67.26 | 67.11 |
| Prewitt:img:LBP | 19.84 | 14.28 | 15.77 | 16.19 | 17.22 | 16.66 |
DownLoad:
CSV
Table 2 shows that among the five sets of experiments, the fusion result of Sobel:image:Laplace has the highest average accuracy, reaching 98.61%. The fused images with the LBP operator generally have poor performance. In this case, the CNN performs poorly because although the CNN is more sensitive to the visual feature information of the image, the CNN is not good at analyzing the intrinsic meaning of the abstract texture features encoded by LBP.
Processing the three-channel data after fusion will double the computational cost, while the original grayscale image model only needs to process the single-channel data. In this study, to avoid this drawback after multichannel fusion, the three-channel data are converted into a single-channel grayscale image according to a certain weight ratio, as shown in Eq (1):
| $ {\rm{Final}}\;\;{\rm{image = \mathsf{ α} (1st}}\;\;{\rm{channel) + \mathsf{ β} (2nd}}\;\;{\rm{channel) + \mathsf{ γ} (3rd}}\;\;{\rm{channel)}} $ | (1) |
where α, β, and γ are the weight ratio coefficients of different channels, and they sum up to 1. The traversal method is used with a step size of 0.1. And there is a total of 36 combinations. Based on the original model, the average accuracy is tested, as shown in Figure 6.
The results show that when the weight coefficients of α, β, and γ are 0.2, 0.6, and 0.2, respectively, the computational cost is the same as with the original data. However, the accuracy is 1.16% higher than when using the three-channel fusion. Figure 7 compares the single-channel image converted using a weight ratio of 0.2:0.6:0.2 with the original image. The figure shows that the defect feature edge of the feature fusion image of the Sobel:image:Sobel algorithm is more obvious. The weight of 0.6 assigned to the original grayscale image can properly retain the information of the original image. The ability to retain this information helps the convolution kernel to learn weights, and the weight of 0.2 assigned to the edge extraction operator can well highlight the defect features on the steel plate image. Consequently, these defect features are conducive to CNN capturing. The same calculation parameters as those of the original data can be retained, while the recognition rate can reach as high as 99.77%.
The feature activation map of the first layer of VGG16 before and after the feature fusion processing is visualized, and the learning results are analyzed. One such image is randomly selected for processing (Figure 8). The yellow area indicates that the defect feature is activated and contains the black inclusion defects; hence, it can be determined that this feature produces the correct phase response. Figure 8 also shows that, in the activation map without feature fusion, 23 feature maps in the defect area generate correct activation. In contrast, in the results after feature fusion, 31 feature maps in the defect area generate correct activation. These data indicate that because the edge extraction operator captures the target defect area in advance and fuses it with the original image, the edge extraction operator can enhance the edge pixel feature of the defect area of the image and ensure that the original data are not lost. Consequently, it is easier for the convolution kernel to capture the defect.
In this study, the gradient-weighted class activation mapping (Grad-CAM) algorithm [29] is used to further validate the target area where the model finally learns. This algorithm can display the area where the model learns in the form of a heat-affected zone to facilitate the observation of whether the final model successfully learns the features of the correct area. Given an input image, the algorithm can obtain the output feature map of a convolution layer through the trained model, which can obtain the parameters of the convolution kernel corresponding to each pair of feature maps without modifying the original model structure. The category relative to each channel of this feature map is used as a weight to generate a spatial map of the activation intensity of the input image to the category. So the heat-affected zone can be generated. In this paper, this method is used to visualize the model before and after feature fusion. Figure 9 shows the learning result of the inclusion defect. The figure shows that the defect area of the steel plate image data subjected to feature fusion process is red; i.e., the area is a “high-temperature” zone. This zone can be accurately located in the image, while the defect area of the original image data not processed by the feature operator is not very well covered. The results show that the data processed by the feature operator have an increased pixel level in the defect area; therefore, the area is more likely to be captured by the CNN. The heat map analysis further verifies that feature fusion preprocessing significantly improves the recognition ability of the CNN model.
The acc and loss curves of the model learning before and after feature fusion are plotted in Figure 10. This figure shows that the acc curve after feature operator processing has a narrow range of fluctuation and overall larger fluctuation; in contrast, the acc curve without feature operator processing has a relatively wide range of fluctuation and overall smaller fluctuation. The loss curve after feature operator processing has a narrow range of fluctuation and overall smaller fluctuation; in contrast, the loss curve without feature operator processing has a wide range of fluctuation and overall larger fluctuation. It can be concluded that the model after feature fusion has a higher fitting ability and better convergence than the model without feature fusion.
The confusion matrix is used in this study to further compare the classification results of the model before and after feature fusion. Each row of the matrix represents the results of a predicted category. The optimal results before and after feature fusion are represented by the confusion matrix, as shown in Figure 11. The figure shows that the recognition accuracy for the crazing category with a steel plate background is 100% with or without feature fusion; the recognition accuracy for the inclusion category is 99.33% with feature fusion and 97.58% without feature fusion; the recognition accuracy for the patches category feature is 100% with feature fusion and 98.48% without feature fusion; the recognition accuracy for the pitted category is 100% with feature fusion and 78.48% without feature fusion; the recognition accuracy for the rolled-in category is 100% with feature fusion and 95.76% without feature fusion; and the recognition accuracy for the scratches category is 99.33% with feature fusion and 95.15% without feature fusion. The above results show that the recognition accuracy of the model is higher in each category after preprocessing with feature fusion than without feature fusion. These results indicate the feasibility of preprocessing with feature fusion in improving the recognition accuracy.
This study proposes an image preprocessing method based on feature operator fusion that is mainly used for defect recognition on low-contrast steel plate surface grayscale images. Through many combination tests, the original grayscale images have been processed using the Sobel and Laplace operators, then superimposed with the original grayscale image at a weight ratio of 0.2:0.6:0.2 as the input to a CNN. The experimental results show that this fusion scheme effectively improves the recognition rate of the test set. Without changing the experimental network framework, the accuracy rate can reach 99.77%, which is 4.22% higher than the accuracy rate of the CNN trained directly on the original images without fusion.
In this study, the influence of several commonly used operators on the accuracy of the model have been investigated, and a solution scheme from the perspective of optimizing the data sources has been offered to resolve the bottleneck problem of CNN learning. The results show that this feature operator-based channel fusion strategy is highly effective at improving the pixel features of defects and making it easier for the network to capture the features of defects, thereby successfully enhancing classification accuracy.
The authors acknowledge the support from the National Key R & D Program of China (Grant No. 2018YFB1701601).
The authors declared that they have no conflicts of interest to this work.
| [1] |
Friedmann T, Roblin R (1972) Gene therapy for human genetic disease? Science (New York, NY) 175: 949-955. doi: 10.1126/science.175.4025.949
|
| [2] | Forsythe JA, Jiang BH, Iyer NV, et al. (1996) Activation of vascular endothelial growth factor gene transcription by hypoxia-inducible factor 1. Mol Cell Biol 16: 4604-4613. |
| [3] |
Whitehead KA, Langer R, Anderson DG (2009) Knocking down barriers: advances in siRNA delivery. Nat Rev Drug Discov 8: 129-138. doi: 10.1038/nrd2742
|
| [4] |
Caplen NJ, Alton E, Middleton PG, et al. (1995) Liposome-mediated CFTR gene-transfer to the nasal epithelium of patients with cystic fibrosis. Nat Med 1: 39-46. doi: 10.1038/nm0195-39
|
| [5] | Fujiwara T, Grimm EA, Mukhopadhyay T, et al. (1994) Induction of chemosensitivity in human lung cancer cells in-vivo by adenovirus-mediated transfer of the wild type P53 gene. Cancer Res 54: 2287-2291. |
| [6] |
Merdan T, Kopecek J, Kissel T (2002) Prospects for cationic polymers in gene and oligonucleotide therapy against cancer. Adv Drug Delivery Rev 54: 715-758. doi: 10.1016/S0169-409X(02)00046-7
|
| [7] |
Abou-El-Enein M, Bauer G, Reinke P, et al. (2014) A roadmap toward clinical translation of genetically-modified stem cells for treatment of HIV. Trends Mol Med 20: 632-642. doi: 10.1016/j.molmed.2014.08.004
|
| [8] |
Carnio S, Novello S, Bironzo P, et al. (2014) Moving from histological subtyping to molecular characterization: new treatment opportunities in advanced non-small-cell lung cancer. Expert Review Anticancer Therapy 14: 1495-1513. doi: 10.1586/14737140.2014.949245
|
| [9] |
Pensado A, Seijo B, Sanchez A (2014) Current strategies for DNA therapy based on lipid nanocarriers. Expert Opinion Drug Delivery 11: 1721-1731. doi: 10.1517/17425247.2014.935337
|
| [10] |
Qasim W, Thrasher AJ (2014) Progress and prospects for engineered T cell therapies. Brit J Haematol 166: 818-829. doi: 10.1111/bjh.12981
|
| [11] |
Sahay G, Querbes W, Alabi C, et al. (2013) Efficiency of siRNA delivery by lipid nanoparticles is limited by endocytic recycling. Nat Biotechnol 31: 653-U119. doi: 10.1038/nbt.2614
|
| [12] |
Schroeder A, Levins CG, Cortez C, et al. (2010) Lipid-based nanotherapeutics for siRNA delivery. J Intern Med 267: 9-21. doi: 10.1111/j.1365-2796.2009.02189.x
|
| [13] |
Xue W, Dahlman JE, Tammela T, et al. (2014) Small RNA combination therapy for lung cancer. P Natl Acad Sci U S A 111: E3553-E3561. doi: 10.1073/pnas.1412686111
|
| [14] |
Dahlman JE, Barnes C, Khan OF, et al. (2014) In vivo endothelial siRNA delivery using polymeric nanoparticles with low molecular weight. Nat Nanotechnol 9: 648-655. doi: 10.1038/nnano.2014.84
|
| [15] | Ramamoorth M, Narvekar A (2015) Non viral vectors in gene therapy- an overview. J Clinical Diagnostic Res JCDR 9: GE01-06. |
| [16] |
Yang J, Liu H, Zhang X (2014) Design, preparation and application of nucleic acid delivery carriers. Biotechnology Advances 32: 804-817. doi: 10.1016/j.biotechadv.2013.11.004
|
| [17] |
Choi YS, Lee MY, David AE, et al. (2014) Nanoparticles for gene delivery: therapeutic and toxic effects. Molecular Cellular Toxicology 10: 1-8. doi: 10.1007/s13273-014-0001-3
|
| [18] |
Dan N, Danino D (2014) Structure and kinetics of lipid-nucleic acid complexes. Adv Colloid Interface 205: 230-239. doi: 10.1016/j.cis.2014.01.013
|
| [19] |
Li S, Huang L (2000) Nonviral gene therapy: promises and challenges. Gene Ther 7: 31-34. doi: 10.1038/sj.gt.3301110
|
| [20] |
Mintzer MA, Simanek EE (2009) Nonviral vectors for gene delivery. Chem Rev 109: 259-302. doi: 10.1021/cr800409e
|
| [21] | Schaffer DV, Fidelman NA, Dan N, et al. (2000) Vector unpacking as a potential barrier for receptor-mediated polyplex gene delivery. Biotechnol Bioeng 67: 598-606. |
| [22] |
Radler JO, Koltover I, Salditt T, et al. (1997) Structure of DNA-cationic liposome complexes: DNA intercalation in multilamellar membranes in distinct interhelical packing regimes. Science 275: 810-814. doi: 10.1126/science.275.5301.810
|
| [23] | Koltover I, Salditt T, Radler JO, et al. (1998) An inverted hexagonal phase of cationic liposome-DNA complexes related to DNA release and delivery. Science 281: 78-81. |
| [24] |
Simberg D, Danino D, Talmon Y, et al. (2001) Phase behavior, DNA ordering, and size instability of cationic lipoplexes—Relevance to optimal transfection activity. J Biol Chem 276: 47453-47459. doi: 10.1074/jbc.M105588200
|
| [25] |
Evans HM, Ahmad A, Ewert K, et al. (2003) Structural polymorphism of DNA-dendrimer complexes. Phys Rev Lett 91: 075501. doi: 10.1103/PhysRevLett.91.075501
|
| [26] |
Merkel OM, Mintzer MA, Sitterberg J, et al. (2009) Triazine dendrimers as nonviral gene delivery systems: effects of molecular structure on biological activity. Bioconjug Chem 20: 1799-1806. doi: 10.1021/bc900243r
|
| [27] |
Juliano R, Alam MR, Dixit V, et al. (2008) Mechanisms and strategies for effective delivery of antisense and siRNA oligonucleotides. Nucleic Acids Res 36: 4158-4171. doi: 10.1093/nar/gkn342
|
| [28] |
de Fougerolles A, Vornlocher HP, Maraganore J, et al. (2007) Interfering with disease: a progress report on siRNA-based therapeutics. Nat Rev Drug Discov 6: 443-453. doi: 10.1038/nrd2310
|
| [29] |
Akinc A, Goldberg M, Qin J, et al. (2009) Development of lipidoid-siRNA formulations for systemic delivery to the liver. Mol Ther 17: 872-879. doi: 10.1038/mt.2009.36
|
| [30] |
Desigaux L, Sainlos M, Lambert O, et al. (2007) Self-assembled lamellar complexes of siRNA with lipidic aminoglycoside derivatives promote efficient siRNA delivery and interference. Proc Natl Acad Sci U S A 104: 16534-16539. doi: 10.1073/pnas.0707431104
|
| [31] |
Tros de Ilarduya C, Sun Y, Duzgunes N (2010) Gene delivery by lipoplexes and polyplexes. Eur J Pharm Sci 40: 159-170. doi: 10.1016/j.ejps.2010.03.019
|
| [32] |
Ma BC, Zhang SB, Jiang HM, et al. (2007) Lipoplex morphologies and their influences on transfection efficiency in gene delivery. J Controlled Release 123: 184-194. doi: 10.1016/j.jconrel.2007.08.022
|
| [33] |
Kapoor M, Burgess DJ, Patil SD (2012) Physicochemical characterization techniques for lipid based delivery systems for siRNA. Int J Pharm 427: 35-57. doi: 10.1016/j.ijpharm.2011.09.032
|
| [34] |
Wasungu L, Hoekstra D (2006) Cationic lipids, lipoplexes and intracellular delivery of genes. J Control Release 116: 255-264. doi: 10.1016/j.jconrel.2006.06.024
|
| [35] |
Safinya CR, Ewert KK, Leal C (2011) Cationic liposome-nucleic acid complexes: liquid crystal phases with applications in gene therapy. Liq Cryst 38: 1715-1723. doi: 10.1080/02678292.2011.624364
|
| [36] |
May S, Ben-Shaul A (1997) DNA-lipid complexes: stability of honeycomb-like and spaghetti-like structures. Biophys J 73: 2427-2440. doi: 10.1016/S0006-3495(97)78271-7
|
| [37] |
Harries D, May S, Gelbart WM, et al. (1998) Structure, stability, and thermodynamics of lamellar DNA-lipid complexes. Biophys J 75: 159-173. doi: 10.1016/S0006-3495(98)77503-4
|
| [38] | Bruinsma R (1998) Electrostatics of DNA cationic lipid complexes: isoelectric instability. Eur Phys J B 4: 75-88. |
| [39] |
Dan N (1996) Formation of ordered domains in membrane-bound DNA. Biophys J 71: 1267-1272. doi: 10.1016/S0006-3495(96)79326-8
|
| [40] |
Dan NL (1997) Multilamellar structures of DNA complexes with cationic liposomes. Biophys J 73: 1842-1846. doi: 10.1016/S0006-3495(97)78214-6
|
| [41] |
Dan N (1998) The structure of DNA complexes with cationic liposomes—cylindrical or flat bilayers? BBA-Biomembranes 1369: 34-38. doi: 10.1016/S0005-2736(97)00171-5
|
| [42] |
Simberg D, Danino D, Talmon Y, et al. (2001) Phase behavior, DNA ordering, and size instability of cationic lipoplexes—Relevance to optimal transfection activity. J Biol Chem 276: 47453-47459. doi: 10.1074/jbc.M105588200
|
| [43] | Simberg D, Danino D, Talmon Y, et al. (2003) Phase behavior, DNA ordering and size instability of cationic lipoplexes: Relevance to optimal transfection activity. J Liposome Res 13: 86-87. |
| [44] |
Kastner E, Kaur R, Lowry D, et al. (2014) High-throughput manufacturing of size-tuned liposomes by a new microfluidics method using enhanced statistical tools for characterization. Int J Pharm 477: 361-368. doi: 10.1016/j.ijpharm.2014.10.030
|
| [45] |
Balbino TA, Azzoni AR, de la Torre LG (2013) Microfluidic devices for continuous production of pDNA/cationic liposome complexes for gene delivery and vaccine therapy. Colloid Surface B 111: 203-210. doi: 10.1016/j.colsurfb.2013.04.003
|
| [46] |
Chen D, Love KT, Chen Y, et al. (2012) Rapid Discovery of Potent siRNA-Containing Lipid Nanoparticles Enabled by Controlled Microfluidic Formulation. J Am Chem Soc 134: 6948-6951. doi: 10.1021/ja301621z
|
| [47] |
Kennedy MT, Pozharski EV, Rakhmanova VA, et al. (2000) Factors governing the assembly of cationic phospholipid-DNA complexes. Biophys J 78: 1620-1633. doi: 10.1016/S0006-3495(00)76714-2
|
| [48] |
Pozharski EV, MacDonald RC (2007) Single lipoplex study of cationic lipoid-DNA, self-assembled complexes. Mol Pharm 4: 962-974. doi: 10.1021/mp700080m
|
| [49] |
Barreleiro PCA, Lindman B (2003) The kinetics of DNA-cationic vesicle complex formation. JPhys Chem B 107: 6208-6213. doi: 10.1021/jp0277107
|
| [50] |
Junquera E, Aicart E (2014) Cationic Lipids as Transfecting Agents of DNA in Gene Therapy. Current Topics Medicinal Chem 14: 649-663. doi: 10.2174/1568026614666140118203128
|
| [51] |
Ma B, Zhang S, Jiang H, et al. (2007) Lipoplex morphologies and their influences on transfection efficiency in gene delivery. J Control Release 123: 184-194. doi: 10.1016/j.jconrel.2007.08.022
|
| [52] | Xiong F, Mi Z, Gu N (2011) Cationic liposomes as gene delivery system: transfection efficiency and new application. Pharmazie 66: 158-164. |
| [53] |
Zhdanov RI, Podobed OV, Vlassov VV (2002) Cationic lipid-DNA complexes-lipoplexes-for gene transfer and therapy. Bioelectrochemistry 58: 53-64. doi: 10.1016/S1567-5394(02)00132-9
|
| [54] |
Cullis PR, de Kruijff B (1979) Lipid polymorphism and the functional roles of lipids in biological membranes. Biochim Biophys Acta 559: 399-420. doi: 10.1016/0304-4157(79)90012-1
|
| [55] |
Epand RM (1998) Lipid polymorphism and protein-lipid interactions. Biochim Biophys Acta 1376: 353-368. doi: 10.1016/S0304-4157(98)00015-X
|
| [56] |
Seddon JM (1990) STRUCTURE OF THE INVERTED HEXAGONAL (HII) PHASE, AND NON-LAMELLAR PHASE-TRANSITIONS OF LIPIDS. Biochim Biophys Acta 1031: 1-69. doi: 10.1016/0304-4157(90)90002-T
|
| [57] |
Netz RR, Andelman D (2003) Neutral and charged polymers at interfaces. Phys Rep 380: 1-95. doi: 10.1016/S0370-1573(03)00118-2
|
| [58] | Nelson P (2013) Biological Physics: Freeman. |
| [59] |
Gregory J, Barany S (2011) Adsorption and flocculation by polymers and polymer mixtures. Adv Colloid Interface 169: 1-12. doi: 10.1016/j.cis.2011.06.004
|
| [60] | G. Fleer, M.A. Cohen Stuart, J.M.H.M. Scheutjens, et al. (1993) Polymers at Interfaces Springer;. |
| [61] |
Sukhishvili SA, Granick S (1998) Polyelectrolyte adsorption onto an initially-bare solid surface of opposite electrical charge. J Chem Phys 109: 6861-6868. doi: 10.1063/1.477253
|
| [62] |
Pozharski E, MacDonald RC (2002) Thermodynamics of cationic lipid-DNA complex formation as studied by isothermal titration calorimetry. Biophys J 83: 556-565. doi: 10.1016/S0006-3495(02)75191-6
|
| [63] |
Pozharski E, MacDonald RC (2003) Lipoplex thermodynamics: Determination of DNA-cationic lipoid interaction energies. Biophys J 85: 3969-3978. doi: 10.1016/S0006-3495(03)74811-5
|
| [64] |
Koltover I, Salditt T, Safinya CR (1999) Phase diagram, stability, and overcharging of lamellar cationic lipid-DNA self-assembled complexes. Biophys J 77: 915-924. doi: 10.1016/S0006-3495(99)76942-0
|
| [65] |
Ahsan A, Rudnick J, Bruinsma R (1998) Elasticity theory of the B-DNA to S-DNA transition. Biophys J 74: 132-137. doi: 10.1016/S0006-3495(98)77774-4
|
| [66] |
Hirsch-Lerner D, Barenholz Y (1999) Hydration of lipoplexes commonly used in gene delivery: follow-up by laurdan fluorescence changes and quantification by differential scanning calorimetry. Biochimica Et Biophysica Acta-Biomembranes 1461: 47-57. doi: 10.1016/S0005-2736(99)00145-5
|
| [67] |
Tilcock CP, Bally MB, Farren SB, et al. (1982) Influence of cholesterol on the structural preferences of dioleoylphosphatidylethanolamine-dioleoylphosphatidylcholine systems: a phosphorus-31 and deuterium nuclear magnetic resonance study. Biochemistry 21: 4596-4601. doi: 10.1021/bi00262a013
|
| [68] |
Danino D, Kesselman E, Saper G, et al. (2009) Osmotically induced reversible transitions in lipid-DNA mesophases. Biophys J 96: L43-45. doi: 10.1016/j.bpj.2008.12.3887
|
| [69] |
Scarzello M, Chupin V, Wagenaar A, et al. (2005) Polymorphism of pyridinium amphiphiles for gene delivery: influence of ionic strength, helper lipid content, and plasmid DNA complexation. Biophys J 88: 2104-2113. doi: 10.1529/biophysj.104.053983
|
| [70] |
Ewert KK, Evans HM, Zidovska A, et al. (2006) A columnar phase of dendritic lipid-based cationic liposome-DNA complexes for gene delivery: hexagonally ordered cylindrical micelles embedded in a DNA honeycomb lattice. J Am Chem Soc 128: 3998-4006. doi: 10.1021/ja055907h
|
| [71] |
Zidovska A, Evans HM, Ewert KK, et al. (2009) Liquid crystalline phases of dendritic lipid-DNA self-assemblies: lamellar, hexagonal, and DNA bundles. J Phys Chem B 113: 3694-3703. doi: 10.1021/jp806863z
|
| [72] | Wasungu L, Stuart MC, Scarzello M, et al. (2006) Lipoplexes formed from sugar-based gemini surfactants undergo a lamellar-to-micellar phase transition at acidic pH. Evidence for a non-inverted membrane-destabilizing hexagonal phase of lipoplexes. Biochim Biophys Acta 1758: 1677-1684. |
| [73] |
Bilalov A, Olsson U, Lindman B (2009) A cubic DNA-lipid complex. Soft Matter 5: 3827-3830. doi: 10.1039/b908939j
|
| [74] | Larsson K (1983) Two cubic phases in monoolein-water system. Nature. |
| [75] |
Leal C, Ewert KK, Bouxsein NF, et al. (2013) Stacking of Short DNA Induces the Gyroid Cubic-to-Inverted Hexagonal Phase Transition in Lipid-DNA Complexes. Soft Matter 9: 795-804. doi: 10.1039/C2SM27018H
|
| [76] |
Farago O, Ewert K, Ahmad A, et al. (2008) Transitions between distinct compaction regimes in complexes of multivalent cationic lipids and DNA. Biophys J 95: 836-846. doi: 10.1529/biophysj.107.124669
|
| [77] |
Fire A, Xu S, Montgomery MK, et al. (1998) Potent and specific genetic interference by double-stranded RNA in Caenorhabditis elegans. Nature 391: 806-811. doi: 10.1038/35888
|
| [78] |
Davidson BL, Paulson HL (2004) Molecular medicine for the brain: silencing of disease genes with RNA interference. Lancet Neurol 3: 145-149. doi: 10.1016/S1474-4422(04)00678-7
|
| [79] | Ponnappa BC (2009) siRNA for inflammatory diseases. Curr Opin Investig Drugs 10: 418-424. |
| [80] |
Whitehead KA, Langer R, Anderson DG (2009) Knocking down barriers: advances in siRNA delivery. Nat Rev Drug Discov 8: 129-138. doi: 10.1038/nrd2742
|
| [81] |
Takeshita F, Ochiya T (2006) Therapeutic potential of RNA interference against cancer. Cancer Sci 97: 689-696. doi: 10.1111/j.1349-7006.2006.00234.x
|
| [82] |
Leal C, Bouxsein NF, Ewert KK, et al. (2010) Highly efficient gene silencing activity of siRNA embedded in a nanostructured gyroid cubic lipid matrix. J Am Chem Soc 132: 16841-16847. doi: 10.1021/ja1059763
|
| [83] |
Leal C, Ewert KK, Shirazi RS, et al. (2011) Nanogyroids incorporating multivalent lipids: enhanced membrane charge density and pore forming ability for gene silencing. Langmuir 27: 7691-7697. doi: 10.1021/la200679x
|
| [84] |
Aytar BS, Muller JP, Kondo Y, et al. (2013) Redox-based control of the transformation and activation of siRNA complexes in extracellular environments using ferrocenyl lipids. J Am Chem Soc 135: 9111-9120. doi: 10.1021/ja403546b
|
| [85] |
Schroeder A, Levins CG, Cortez C, et al. (2010) Lipid-based nanotherapeutics for siRNA delivery. J Intern Med 267: 9-21. doi: 10.1111/j.1365-2796.2009.02189.x
|
| [86] |
Kim DH, Rossi JJ (2007) Strategies for silencing human disease using RNA interference. Nat Revs Genet 8: 173-184. doi: 10.1038/nrg2006
|
| [87] |
De Paula D, Bentley MV, Mahato RI (2007) Hydrophobization and bioconjugation for enhanced siRNA delivery and targeting. RNA 13: 431-456. doi: 10.1261/rna.459807
|
| [88] | A.S. Edelstein, Cammarata RC (1996) Nanomaterials: Synthesis, Properties and Applications: Inst. of Physics Publishing. |
| [89] |
Filippova NL (1998) Adsorption and desorption kinetics of polyelectrolytes on planar surfaces. Langmuir 14: 1162-1176. doi: 10.1021/la970544n
|
| [90] |
Iruthayaraj J, Poptoshev E, Vareikis AV, et al. (2005) Adsorption of low charge density polyelectrolyte containing poly(ethylene oxide) side chains on silica: Effects of ionic strength and pH. Macromolecules 38: 6152-6160. doi: 10.1021/ma050851x
|
| [91] |
Sedeva IG, Fornasiero D, Ralston J, et al. (2009) The Influence of Surface Hydrophobicity on Polyacrylamide Adsorption. Langmuir 25: 4514-4521. doi: 10.1021/la803838k
|
| [92] |
McFarlane A, Yeap KY, Bremmell K, et al. (2008) The influence of flocculant adsorption kinetics on the dewaterability of kaolinite and smectite clay mineral dispersions. Colloid Surface A 317: 39-48. doi: 10.1016/j.colsurfa.2007.09.045
|
| [93] |
Enarsson L-E, Wagberg L (2008) Adsorption kinetics of cationic polyelectrolytes studied with stagnation point adsorption reflectometry and quartz crystal microgravimetry. Langmuir 24: 7329-7337. doi: 10.1021/la800198e
|
| [94] |
van Heiningen JA, Hill RJ (2011) Polymer adsorption onto a micro-sphere from optical tweezers electrophoresis. Lab Chip 11: 152-162. doi: 10.1039/C005217P
|
| [95] |
Dickinson E, Eriksson L (1991) Particle flocculation by adsorbing polymers. Adv Colloid Interfac 34: 1-29. doi: 10.1016/0001-8686(91)80045-L
|
| [96] |
Barany S, Szepesszentgyorgyi A (2004) Flocculation of cellular suspensions by polyelectrolytes. Adv Colloid Interfac 111: 117-129. doi: 10.1016/j.cis.2004.07.003
|
| [97] |
Popa I, Gillies G, Papastavrou G, et al. (2009) Attractive Electrostatic Forces between Identical Colloidal Particles Induced by Adsorbed Polyelectrolytes. J Phys Chem B 113: 8458-8461. doi: 10.1021/jp904041k
|
| [98] |
Popa I, Gillies G, Papastavrou G, et al. (2010) Attractive and Repulsive Electrostatic Forces between Positively Charged Latex Particles in the Presence of Anionic Linear Polyelectrolytes. J Phys Chem B 114: 3170-3177. doi: 10.1021/jp911482a
|
| [99] |
Lin MY, Lindsay HM, Weitz DA, et al. (1989) Universality in colloid aggregation. Nature 339: 360-362. doi: 10.1038/339360a0
|
| [100] | S. Edelstein, Cammarata RC (1996) Nanomaterials: Synthesis, Properties and Applications: Inst. of Physics Publishing, London, UK. |
| [101] |
Lai E, van Zanten JH (2002) Real time monitoring of lipoplex molar mass, size and density. J Control Release 82: 149-158. doi: 10.1016/S0168-3659(02)00104-9
|
| [102] |
Lai E, van Zanten JH (2001) Monitoring DNA/poly-L-lysine polyplex formation with time-resolved multiangle laser light scattering. Biophys J 80: 864-873. doi: 10.1016/S0006-3495(01)76065-1
|
| [103] |
Gershon H, Ghirlando R, Guttman SB, et al. (1993) Mode of formation and structural features of DNA-cationic liposome complexes used for transfection. Biochemistry 32: 7143-7151. doi: 10.1021/bi00079a011
|
| [104] |
Zhang Y, Garzon-Rodriguez W, Manning MC, et al. (2003) The use of fluorescence resonance energy transfer to monitor dynamic changes of lipid-DNA interactions during lipoplex formation. Biochim Biophys Acta 1614: 182-192. doi: 10.1016/S0005-2736(03)00177-9
|
| [105] |
Braun CS, Fisher MT, Tomalia DA, et al. (2005) A stopped-flow kinetic study of the assembly of nonviral gene delivery complexes. Biophys J 88: 4146-4158. doi: 10.1529/biophysj.104.055202
|
| [106] |
Barreleiro PC, May RP, Lindman B (2003) Mechanism of formation of DNA-cationic vesicle complexes. Faraday Discuss 122: 191-201; discussion 269-182. doi: 10.1039/b200796g
|
| [107] |
Leal C, Sandstrom D, Nevsten P, et al. (2008) Local and translational dynamics in DNA-lipid assemblies monitored by solid-state and diffusion NMR. BBA-Biomembranes 1778: 214-228. doi: 10.1016/j.bbamem.2007.09.035
|
| [108] |
Zuidam NJ, Barenholz Y (1997) Electrostatic parameters of cationic liposomes commonly used for gene delivery as determined by 4-heptadecyl-7-hydroxycoumarin. Biochim Biophys Acta 1329: 211-222. doi: 10.1016/S0005-2736(97)00110-7
|
| [109] |
Zuidam NJ, Barenholz Y (1998) Electrostatic and structural properties of complexes involving plasmid DNA and cationic lipids commonly used for gene delivery. Biochim Biophys Acta 1368: 115-128. doi: 10.1016/S0005-2736(97)00187-9
|
| [110] |
Szilagyi I, Trefalt G, Tiraferri A, et al. (2014) Polyelectrolyte adsorption, interparticle forces, and colloidal aggregation. Soft Matter 10: 2479-2502. doi: 10.1039/c3sm52132j
|
| [111] |
Maier B, Radler JO (1999) Conformation and self-diffusion of single DNA molecules confined to two dimensions. Phys Rev Lett 82: 1911-1914. doi: 10.1103/PhysRevLett.82.1911
|
| [112] |
Epand RF, Sarig H, Ohana D, et al. (2011) Physical properties affecting cochleate formation and morphology using antimicrobial oligo-acyl-lysyl peptide mimetics and mixtures mimicking the composition of bacterial membranes in the absence of divalent cations. J Phys Chem B 115: 2287-2293. doi: 10.1021/jp111242q
|
| [113] |
Epand RF, Mor A, Epand RM (2011) Lipid complexes with cationic peptides and OAKs; their role in antimicrobial action and in the delivery of antimicrobial agents. Cell Mol Life Sci 68: 2177-2188. doi: 10.1007/s00018-011-0711-9
|
| [114] |
Sarig H, Ohana D, Epand RF, et al. (2011) Functional studies of cochleate assemblies of an oligo-acyl-lysyl with lipid mixtures for combating bacterial multidrug resistance. FASEB J 25: 3336-3343. doi: 10.1096/fj.11-183764
|
| [115] |
Chen DL, Love KT, Chen Y, et al. (2012) Rapid Discovery of Potent siRNA-Containing Lipid Nanoparticles Enabled by Controlled Microfluidic Formulation. J Am Chem Soc 134: 6948-6951. doi: 10.1021/ja301621z
|
| [116] |
Leung AKK, Hafez IM, Baoukina S, et al. (2012) Lipid Nanoparticles Containing siRNA Synthesized by Microfluidic Mixing Exhibit an Electron-Dense Nanostructured Core (vol 116, pg 18440, 2012). J Phys Chem C 116: 22104-22104. doi: 10.1021/jp3088786
|
| 1. | Wen Zhang, Min Wu, Sheng Du, Luefeng Chen, Plate shape recognition based on Gaussian function and particle swarm optimization for roller quenching process, 2022, 119, 09591524, 115, 10.1016/j.jprocont.2022.10.001 | |
| 2. | Feng Miao Tu, Ming Hui Wei, Jun Liu, Lu Lu Liao, An adaptive weighting multimodal fusion classification system for steel plate surface defect, 2023, 45, 10641246, 3501, 10.3233/JIFS-230170 | |
| 3. | Rachid Zaghdoudi, Abdelmalek Bouguettaya, Adel Boudiaf, Steel surface defect recognition using classifier combination, 2024, 132, 0268-3768, 3489, 10.1007/s00170-024-13407-z | |
| 4. | Hongkai Zhang, Suqiang Li, Qiqi Miao, Ruidi Fang, Song Xue, Qianchuan Hu, Jie Hu, Sixian Chan, Surface defect detection of hot rolled steel based on multi-scale feature fusion and attention mechanism residual block, 2024, 14, 2045-2322, 10.1038/s41598-024-57990-3 | |
| 5. | Fengmin Shen, Qian Zhou, Zhijia Bai, Hui Zhang, 2024, Crane Rail Bolt Image Defect Recognition Based on Feature Fusion, 979-8-3503-7364-6, 24, 10.1109/ICSECE61636.2024.10729317 |
Nily Dan. Lipid-Nucleic Acid Supramolecular Complexes: Lipoplex Structure and the Kinetics of Formation[J]. AIMS Biophysics, 2015, 2(2): 163-183. doi: 10.3934/biophy.2015.2.163
| Conversion weights | Accuracy | Average Accuracy | ||||
| No. 1 | No. 2 | No. 3 | No. 4 | No. 5 | ||
| Sobel:img:Sobel | 97.24 | 96.54 | 94.27 | 93.28 | 96.77 | 96.22 |
| Roberts:img:Roberts | 95.34 | 95.49 | 94.65 | 96.97 | 95.30 | 95.55 |
| Prewitt:img:Prewitt | 95.25 | 93.94 | 95.21 | 94.24 | 94.71 | 94.67 |
| Laplace:img:Laplace | 88.13 | 87.12 | 86.44 | 87.63 | 87.08 | 87.28 |
| LBP:img:LBP | 92.11 | 92.48 | 92.26 | 93.32 | 94.43 | 92.92 |
DownLoad:
CSV
| Fusion scheme | Accuracy | Average Accuracy | ||||
| No. 1 | No. 2 | No. 3 | No. 4 | No. 5 | ||
| Sobel:img:Roberts | 98.88 | 97.36 | 98.05 | 99.09 | 97.97 | 98.27 |
| Sobel:img:Laplace | 97.51 | 98.14 | 98.98 | 98.91 | 99.45 | 98.61 |
| Sobel:img:Prewitt | 98.51 | 97.04 | 98.17 | 99.01 | 97.27 | 98.00 |
| Sobel:img:LBP | 76.11 | 76.25 | 75.22 | 74.89 | 75.58 | 75.61 |
| Roberts:img:Laplace | 98.02 | 96.94 | 96.01 | 98.57 | 99.61 | 97.83 |
| Roberts:img:Prewitt | 95.17 | 96.37 | 95.25 | 96.44 | 97.32 | 96.11 |
| Roberts:img:LBP | 81.21 | 81.37 | 83.27 | 81.65 | 80.25 | 81.55 |
| Laplace:img:Prewitt | 97.41 | 97.11 | 97.02 | 96.51 | 95.55 | 96.72 |
| Laplace:img:LBP | 70.52 | 67.61 | 65.84 | 64.32 | 67.26 | 67.11 |
| Prewitt:img:LBP | 19.84 | 14.28 | 15.77 | 16.19 | 17.22 | 16.66 |
DownLoad:
CSV
| Conversion weights | Accuracy | Average Accuracy | ||||
| No. 1 | No. 2 | No. 3 | No. 4 | No. 5 | ||
| Sobel:img:Sobel | 97.24 | 96.54 | 94.27 | 93.28 | 96.77 | 96.22 |
| Roberts:img:Roberts | 95.34 | 95.49 | 94.65 | 96.97 | 95.30 | 95.55 |
| Prewitt:img:Prewitt | 95.25 | 93.94 | 95.21 | 94.24 | 94.71 | 94.67 |
| Laplace:img:Laplace | 88.13 | 87.12 | 86.44 | 87.63 | 87.08 | 87.28 |
| LBP:img:LBP | 92.11 | 92.48 | 92.26 | 93.32 | 94.43 | 92.92 |
| Fusion scheme | Accuracy | Average Accuracy | ||||
| No. 1 | No. 2 | No. 3 | No. 4 | No. 5 | ||
| Sobel:img:Roberts | 98.88 | 97.36 | 98.05 | 99.09 | 97.97 | 98.27 |
| Sobel:img:Laplace | 97.51 | 98.14 | 98.98 | 98.91 | 99.45 | 98.61 |
| Sobel:img:Prewitt | 98.51 | 97.04 | 98.17 | 99.01 | 97.27 | 98.00 |
| Sobel:img:LBP | 76.11 | 76.25 | 75.22 | 74.89 | 75.58 | 75.61 |
| Roberts:img:Laplace | 98.02 | 96.94 | 96.01 | 98.57 | 99.61 | 97.83 |
| Roberts:img:Prewitt | 95.17 | 96.37 | 95.25 | 96.44 | 97.32 | 96.11 |
| Roberts:img:LBP | 81.21 | 81.37 | 83.27 | 81.65 | 80.25 | 81.55 |
| Laplace:img:Prewitt | 97.41 | 97.11 | 97.02 | 96.51 | 95.55 | 96.72 |
| Laplace:img:LBP | 70.52 | 67.61 | 65.84 | 64.32 | 67.26 | 67.11 |
| Prewitt:img:LBP | 19.84 | 14.28 | 15.77 | 16.19 | 17.22 | 16.66 |
