In lung CT images, the edge of a tumor is frequently fuzzy because of the complex relationship between tumors and tissues, especially in cases that the tumor adheres to the chest and lung in the pathology area. This m...In lung CT images, the edge of a tumor is frequently fuzzy because of the complex relationship between tumors and tissues, especially in cases that the tumor adheres to the chest and lung in the pathology area. This makes the tumor segmentation more difficult. In order to segment tumors in lung CT images accurately, a method based on support vector machine(SVM) and improved level set model is proposed. Firstly, the image is divided into several block units; then the texture, gray and shape features of each block are extracted to construct eigenvector and then the SVM classifier is trained to detect suspicious lung lesion areas; finally, the suspicious edge is extracted as the initial contour after optimizing lesion areas, and the complete tumor segmentation can be obtained by level set model modified with morphological gradient. Experimental results show that this method can efficiently and fast segment the tumors from complex lung CT images with higher accuracy.展开更多
Because texture images cannot be directly processed by the gray level information of individual pixel,we propose a new texture descriptor which reflects the intensity distribution of the patch centered at each pixel.T...Because texture images cannot be directly processed by the gray level information of individual pixel,we propose a new texture descriptor which reflects the intensity distribution of the patch centered at each pixel.Then the general multiphase image segmentation model of Potts model is extended for texture segmentation by adding the region information of the texture descriptor.A fast numerical scheme based on the split Bregman method is designed to speed up the computational process.The algorithm is efficient,and both the texture descriptor and the characteristic functions can be implemented easily.Experiments using synthetic texture images,real natural scene images and synthetic aperture radar images are presented to give qualitative comparisons between our method and other state-of-the-art techniques.The results show that our method can accurately segment object regions and is competitive compared with other methods especially in segmenting natural images.展开更多
As a current popular method,intelligent detection of cracks is of great significance to road safety,so deep learning has gradually attracted attention in the field of crack image detection.The nonlinear structure,low ...As a current popular method,intelligent detection of cracks is of great significance to road safety,so deep learning has gradually attracted attention in the field of crack image detection.The nonlinear structure,low contrast and discontinuity of cracks bring great challenges to existing crack detection methods based on deep learning.Therefore,an end-to-end deep convolutional neural network(AttentionCrack)is proposed for automatic crack detection to overcome the inaccuracy of boundary location between crack and non-crack pixels.The AttentionCrack network is built on U-Net based encoder-decoder architecture,and an attention mechanism is incorporated into the multi-scale convolutional feature to enhance the recognition of crack region.Additionally,a dilated convolution module is introduced in the encoder-decoder architecture to reduce the loss of crack detail due to the pooling operation in the encoder network.Furthermore,since up-sampling will lead to the loss of crack boundary information in the decoder network,a depthwise separable residual module is proposed to capture the boundary information of pavement crack.The AttentionCrack net on public pavement crack image datasets named CrackSegNet and Crack500 is trained and tested,the results demonstrate that the AttentionCrack achieves F1 score over 0.70 on the CrackSegNet and 0.71 on the Crack500 in average and outperforms the current state-of-the-art methods.展开更多
In this paper, firstly, target candidate regions are extracted by combining maximum symmetric surround saliency detection algorithm with a cellular automata dynamic evolution model. Secondly, an eigenvector independen...In this paper, firstly, target candidate regions are extracted by combining maximum symmetric surround saliency detection algorithm with a cellular automata dynamic evolution model. Secondly, an eigenvector independent of the ship target size is constructed by combining the shape feature with ship histogram of oriented gradient(S-HOG) feature, and the target can be recognized by Ada Boost classifier. As demonstrated in our experiments, the proposed method with the detection accuracy of over 96% outperforms the state-of-the-art method. efficiency switch and modulation.展开更多
The point spread function（PSF） is investigated in order to study the centroids algorithm in a reverse Hartmann test（RHT） system. Instead of the diffractive Airy disk in previous researches, the intensity of PSF be...The point spread function（PSF） is investigated in order to study the centroids algorithm in a reverse Hartmann test（RHT） system. Instead of the diffractive Airy disk in previous researches, the intensity of PSF behaves as a circle of confusion（CoC） and is evaluated in terms of the Lommel function in this paper. The fitting of a single spot with the Gaussian profile to identify its centroid forms the basis of the proposed centroid algorithm. In the implementation process, gray compensation is performed to obtain an intensity distribution in the form of a two-dimensional（2D） Gauss function while the center of the peak is derived as a centroid value. The segmental fringe is also fitted row by row with the one-dimensional（1D） Gauss function and reconstituted by averaged parameter values. The condition used for the proposed method is determined by the strength of linear dependence evaluated by Pearson＇s correlation coefficient between profiles of Airy disk and CoC. The accuracies of CoC fitting and centroid computation are theoretically and experimentally demonstrated by simulation and RHTs. The simulation results show that when the correlation coefficient value is more than 0.9999, the proposed centroid algorithm reduces the root-mean-square error（RMSE） by nearly one order of magnitude, thus achieving an accuracy of - 0.01 pixel or better performance in experiment. In addition, the 2D and 1D Gaussian fittings for the segmental fringe achieve almost the same centroid results, which further confirm the feasibility and advantage of the theory and method.展开更多
基金supported by the National Natural Science Foundation of China(No.61261029)Jinchuan Company Research Foundation(No.JCYY2013009)
文摘In lung CT images, the edge of a tumor is frequently fuzzy because of the complex relationship between tumors and tissues, especially in cases that the tumor adheres to the chest and lung in the pathology area. This makes the tumor segmentation more difficult. In order to segment tumors in lung CT images accurately, a method based on support vector machine(SVM) and improved level set model is proposed. Firstly, the image is divided into several block units; then the texture, gray and shape features of each block are extracted to construct eigenvector and then the SVM classifier is trained to detect suspicious lung lesion areas; finally, the suspicious edge is extracted as the initial contour after optimizing lesion areas, and the complete tumor segmentation can be obtained by level set model modified with morphological gradient. Experimental results show that this method can efficiently and fast segment the tumors from complex lung CT images with higher accuracy.
基金supported by the National Natural Science Foundation of China(No.61170106)
文摘Because texture images cannot be directly processed by the gray level information of individual pixel,we propose a new texture descriptor which reflects the intensity distribution of the patch centered at each pixel.Then the general multiphase image segmentation model of Potts model is extended for texture segmentation by adding the region information of the texture descriptor.A fast numerical scheme based on the split Bregman method is designed to speed up the computational process.The algorithm is efficient,and both the texture descriptor and the characteristic functions can be implemented easily.Experiments using synthetic texture images,real natural scene images and synthetic aperture radar images are presented to give qualitative comparisons between our method and other state-of-the-art techniques.The results show that our method can accurately segment object regions and is competitive compared with other methods especially in segmenting natural images.
基金supported by the National Natural Science Foundation of China under Grant No.62001004the Key Provincial Natural Science Research Projects of Colleges and Universities in Anhui Province under Grant No.KJ2019A0768+2 种基金the Key Research and Development Program of Anhui Province under Grant No.202104A07020017the Research Project Reserve of Anhui Jianzhu University under Grant No.2020XMK04the Natural Science Foundation of the Anhui Higher Education Institutions of China,No.KJ2019A0789.
文摘As a current popular method,intelligent detection of cracks is of great significance to road safety,so deep learning has gradually attracted attention in the field of crack image detection.The nonlinear structure,low contrast and discontinuity of cracks bring great challenges to existing crack detection methods based on deep learning.Therefore,an end-to-end deep convolutional neural network(AttentionCrack)is proposed for automatic crack detection to overcome the inaccuracy of boundary location between crack and non-crack pixels.The AttentionCrack network is built on U-Net based encoder-decoder architecture,and an attention mechanism is incorporated into the multi-scale convolutional feature to enhance the recognition of crack region.Additionally,a dilated convolution module is introduced in the encoder-decoder architecture to reduce the loss of crack detail due to the pooling operation in the encoder network.Furthermore,since up-sampling will lead to the loss of crack boundary information in the decoder network,a depthwise separable residual module is proposed to capture the boundary information of pavement crack.The AttentionCrack net on public pavement crack image datasets named CrackSegNet and Crack500 is trained and tested,the results demonstrate that the AttentionCrack achieves F1 score over 0.70 on the CrackSegNet and 0.71 on the Crack500 in average and outperforms the current state-of-the-art methods.
基金supported by the National Natural Science Foundation of China(No.61401425)
文摘In this paper, firstly, target candidate regions are extracted by combining maximum symmetric surround saliency detection algorithm with a cellular automata dynamic evolution model. Secondly, an eigenvector independent of the ship target size is constructed by combining the shape feature with ship histogram of oriented gradient(S-HOG) feature, and the target can be recognized by Ada Boost classifier. As demonstrated in our experiments, the proposed method with the detection accuracy of over 96% outperforms the state-of-the-art method. efficiency switch and modulation.
基金Project supported by the National Natural Science Foundation of China(Grant No.61475018)
文摘The point spread function（PSF） is investigated in order to study the centroids algorithm in a reverse Hartmann test（RHT） system. Instead of the diffractive Airy disk in previous researches, the intensity of PSF behaves as a circle of confusion（CoC） and is evaluated in terms of the Lommel function in this paper. The fitting of a single spot with the Gaussian profile to identify its centroid forms the basis of the proposed centroid algorithm. In the implementation process, gray compensation is performed to obtain an intensity distribution in the form of a two-dimensional（2D） Gauss function while the center of the peak is derived as a centroid value. The segmental fringe is also fitted row by row with the one-dimensional（1D） Gauss function and reconstituted by averaged parameter values. The condition used for the proposed method is determined by the strength of linear dependence evaluated by Pearson＇s correlation coefficient between profiles of Airy disk and CoC. The accuracies of CoC fitting and centroid computation are theoretically and experimentally demonstrated by simulation and RHTs. The simulation results show that when the correlation coefficient value is more than 0.9999, the proposed centroid algorithm reduces the root-mean-square error（RMSE） by nearly one order of magnitude, thus achieving an accuracy of - 0.01 pixel or better performance in experiment. In addition, the 2D and 1D Gaussian fittings for the segmental fringe achieve almost the same centroid results, which further confirm the feasibility and advantage of the theory and method.
