Search

Interactive image segmentation uses a priori information to guide the acquisition of the people ' s interesting parts of an image, but existing algorithms cannot balance efficiency and accuracy. To solve this problem, this paper proposed a fast interactive segmentation algorithm based on superpixel and random walk (random walk on superpixel, SPRW) . Firstly, it presegmented the image into superpixel regions with local similarity and used pixel colour averages to represent the superpixel regions. Secondly, it built the F-B graph structure based on manually labelled a priori information and extended the range of the random walk, obtained the hard segmentation results using the random walk solution. Finally, this paper proposed the improved matting algorithm (fast robust matting, FRB ) for the unsmooth boundaries of segmentation results and performed the secondary process to obtain soft segmentation results. Experiments on the BSDSOO and MSRC datasets confirm that the proposed hard method is superior to other algorithms in terms of time and average intersection ratio, while experiments on the Alpha Matting dataset demonstrate that the proposed soft algorithm improves efficiency and accuracy. In addition, the experiment of replacing the background of a life photograph demonstrates the application value of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The traditional algorithms have the low performance when applied to remote sensing images segmentation. Thus, this paper proposed a segmentation algorithm based on adaptive feature-reduction. Firstly, this algorithm divided the source image into super-pixels as the basic operation object. Then, it extracted the color, texture, edge and spatial features of images and used weighted pixel values to calculate the features of super-pixels. Furthermore, it added the fuzzy separation measure into the FRFCM model to construct own segmentation model. This model can automatically select useful features. Finally, this paper got the final segmentation result based on optimizing the segmentation model. Experiments on remote sensing images prove that this proposed algorithm has superior performance in terms of segmentation accuracy, running time and eliminate noise effects. [ABSTRACT FROM AUTHOR]

The interactive image segmentation algorithm based on pixel-level is sensitive to initial seed position and noise . However, the image segmentation method only oriented super-pixels is unable to retain image details so that under-segmentation could produce. Aiming at above problems, this paper proposed the segmentation model based on superpixel/pixel constraint and sparse representation. The method firstly defined two mutual constraint cost functions utilized the Gaussian model for super-pixels and pixels respectively. Meanwhile, it introduced constraint condition oriented on sparse decomposition to optimize the proposed model to avoid over-segmentation. Finally, this paper utilized joint optimization method to obtain the solution of the proposed model and estimated the object and background labels to realize object extraction. Experiment results demonstrate that the proposed method can obtain better segmentation results compared with the state-of-the-art methods and is more robust to noise. [ABSTRACT FROM AUTHOR]

To enhance the performance of image classification and improve the accuracy and efficiency of copy detection, this paper proposed an image hash algorithm based on QBFM moments and three-dimensional structure. Firstly, it used normalization to process the color image, and obtained the Gaussian fusion image and Laplace fusion image through multi-scale fusion, then extracted the QBFM features of two fusion images. At the same time, it directly extracted gradient information of the Gaus-sian fusion image in the RGB color space and constructed a three-dimensional model, used the concave convex point information of peak and valley curve of gradient from different perspectives to obtain the three-dimensional local structure features. Then, it disposed the three-dimensional model of gradient image by equidistant segmentation, Counted the number of pixels and variance of each section as the three-dimensional global structure features. Finally, it combined the QBFM features and three-dimensional features of the image and scrambled to form the final hash sequence. Experimental results show that the algorithm has a better balance between robustness and discrimination. Compared with the existing hash algorithms, it has good image classification performance. In the copy detection experiment, the algorithm has the best recall and precision. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the existing image segmentation algorithm is complex and the segmentation precision is not high enough, this paper proposed a medical image clustering segmentation algorithm based on geometric distance optimization centroid and rough fuzzy C-means ( RFCM). First it set up the set of pixels represented by the soft set and calculated the distance between each pixel and the centroid. Then it grouped the pixels into clusters based on the minimum distance between the pixel and the centroid. In order to apply the soft set to the coarse fuzzy C-means, it defined a fuzzy soft set. It further converted the input image into a binary image, and selected an appropriate centroid by calculating the geometric distance of the connected region. Finally, using these new centroids to calculate the membership value of the updated pixel, it completed the fuzzy clustering. The performance of the proposed hybrid algorithm was evaluated on three medical databases, such as Allen Brain Atlas. The obtained Jaccard coefficient and segmentation accuracy (SA) were better than several comparison algorithms. Experiments show that the proposed clustering segmentation algorithm has good performance. [ABSTRACT FROM AUTHOR]

Aiming at the problem of low segmentation accuracy in semantic segmentation of foggy images, this paper proposed a semantic segmentation method of foggy images that based on atrous space pyramid pooling, Xception module and residual network. On the one hand, this algorithm used the atrous space pyramid pooling and residual network to extract the multi-scale context features of the input image by the parallel convolution of multiple sampling rates and the convolution kernel size of 1 x 1. On the other hand, it used the decoder structure to classify the extracted features with Xception module after pretraining, and the prediction results of each pixel enhanced the refinement of the segmentation boundary and got the segmentation result with fine boundary. Experimental results show that the average intersection and union ratio of the proposed algorithm on foggy cityscapes dataset are 73. 03 %,73. 81 % and 74. 50%, and the segmentation performance is good. [ABSTRACT FROM AUTHOR]