This paper proposes a Hilbert stereo reconstruction algorithm based on depth feature and stereo matching to solve the problem of occlusive region matching errors, namely, the Hilbert stereo network. The traditional stereo network pays more attention to disparity itself, leading to the inaccuracy of disparity estimation. Our design network studies the effective disparity matching and refinement through reconstruction representation of Hilbert’s disparity coefficient. Since the Hilbert coefficient is not affected by the occlusion and texture in the image, stereo disparity matching can conducted effectively. Our network includes three sub-modules, namely, depth feature representation, Hilbert cost volume fusion, and Hilbert refinement reconstruction. Separately, texture features of different depth levels of the image were extracted through Hilbert filtering operation. Next, stereoscopic disparity fusion was performed, and then Hilbert designed to refine the difference regression stereo matching solution was used. Based on the end-to-end design, the structure is refined by combining the depth feature extraction module and Hilbert coefficient disparity. Finally, the Hilbert stereo matching algorithm achieves excellent performance on standard big data set and is compared with other advanced stereo networks. Experiments show that our network has high accuracy and high performance.
Different areas of eyes reflect different states of internal organs of human body. That can assist to detect the disease internal organs, facilitate the prevention and cure by analyzing the image of human eyes. In this paper, we propose a new algorithm, Deep Composite Predict Network (DCP-Net), combined deep learning technique with traditional Chinese medicine theory, which can segment interesting areas of the human eyes, detect the disease eyes texture and then predict internal lesion organ. Aimed at helping doctors to diagnose quickly. The proposed algorithm consists three sub-modules, i.e., multiple segmentation sub-module, fast detection sub-module and predict eye disease module. The multiple segmentation module is solved by the improved retraining U-network, which can obtain an accurate eye to segment interesting areas. The fast detection module is based on enhanced Yolo framework. The predication disease method combined Chinese traditional theory with computer vision technology. Finally, our network can accurately detect the disease of human eyes and predict lesions of internal organs, which can help doctors quickly diagnose lesion organs by human eyes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.