Early detection of glaucoma is important for slowing disease progression and preventing total vision loss. The diagnosis of glaucoma is closely related to the shape of the optic disc and cup (cup-disc) and whether there is a defect in the retinal nerve fiber layer (RNFL). In previous studies, it was common to predict glaucoma by analyzing changes in cup-to-disc ratio, or to directly classify fundus images for glaucoma using a deep learning classification model. This paper proposes a method for diagnosing glaucoma by combining the cup-disc shape information and retinal nerve fiber layer defect (RNFLD) information. We use a fully convolutional neural network that based on a multi-scale attention mechanism (AM-CNN) to identify cup-disc morphology and RNFLD regions, further use previous methods and image processing methods to extract features in these two spaces. Finally, we use the SVM method in machine learning to classify the sample for glaucoma based on the features fusion of the two spaces. Specifically, we first establish a small database with both the cup-disc annotation, retinal nerve fiber layer defect annotation and glaucoma diagnosis results, which includes 735 fundus images labeled with either positive glaucoma (356) or negative glaucoma (379). Then, a semantic segmentation model based on attention is designed. By adding attention to the context information of the model, a more accurate segmentation image is obtained, not only has a good effect on the segmentation of the cup-disc, but also has a significant effect on the recognition of RNFLDs. Finally, the four-dimensional features were extracted from the cup-disc segmentation map by the previous method, and the four-dimensional features such as distance and area were extracted from the retinal nerve fiber layer segmentation map. Combine the two kinds of features using SVM algorithm to establish a classification model for glaucoma classification. The experiment results show that adding the attention module to the decoder can improve the effect of segmentation tasks for more complex problems and the classification model fusion cup-disc shape and RNFLD information significantly advances glaucoma detection.
3D reconstruction of objects has been an important topic in the field of computer vision. Limited by the optical measurement methods such as structured light, time of flight and binocular imaging, the data measured at multiple viewpoints have to be registered in order to obtain the complete information of the object. Iterative Closest Points (ICP) algorithm is classical in points registration field. However, Euclidean distance is only used in ICP algorithm to calculate the corresponding point pair, which has instability. And it is not necessary to perform a recent search for all points in target point cloud and source point cloud. Therefore, we propose an improved ICP registration method based on curvature feature extraction. First, the statistical outlier removal and voxel grid filter are applied for denoising and streamlining of large-scale scattered point cloud. Then, the corresponding points are extracted according to the curvature feature. In every corresponding points searching, they are matched by the relationship between surface local feature and point distance, which can not only reflect to basic geometrical feature, but also give ICP algorithm good iterative initial value. Next, we use ICP method to build a least squares problem, and singular value decomposition for covariance matrix to obtain the coordinate transformation matrix. In the iteration, the kd-tree is used to accelerate the pair search, and the iteration is repeated until the limit of the distance error function is satisfied finally. We configure PCL on Visual Studio for testing. The experimental results show that the proposed algorithm is more effective than traditional ICP in terms of run time and accuracy.
Binocular stereo vision is becoming a research hotspot in the area of image processing. Based on traditional adaptive-weight stereo matching algorithm, we improve the cost volume by averaging the AD (Absolute Difference) of RGB color channels and adding x-derivative of the grayscale image to get the cost volume. Then we use guided filter in the cost aggregation step and weighted median filter for post-processing to address the edge problem. In order to get the location in real space, we combine the deep information with the camera calibration to project each pixel in 2D image to 3D coordinate matrix. We add the concept of projection to region-growing algorithm for surface reconstruction, its specific operation is to project all the points to a 2D plane through the normals of clouds and return the results back to 3D space according to these connection relationship among the points in 2D plane. During the triangulation in 2D plane, we use Delaunay algorithm because it has optimal quality of mesh. We configure OpenCV and pcl on Visual Studio for testing, and the experimental results show that the proposed algorithm have higher computational accuracy of disparity and can realize the details of the real mesh model.
New virtual view is synthesized through depth image based rendering(DIBR) using a single color image and its associated depth map in 3D view generation. Holes are unavoidably generated in the 2D to 3D conversion process. We propose a hole-filling method based on depth map to address the problem. Firstly, we improve the process of DIBR by proposing a one-to-four (OTF) algorithm. The “z-buffer” algorithm is used to solve overlap problem. Then, based on the classical patch-based algorithm of Criminisi et al., we propose a hole-filling algorithm using the information of depth map to handle the image after DIBR. In order to improve the accuracy of the virtual image, inpainting starts from the background side. In the calculation of the priority, in addition to the confidence term and the data term, we add the depth term. In the search for the most similar patch in the source region, we define the depth similarity to improve the accuracy of searching. Experimental results show that the proposed method can effectively improve the quality of the 3D virtual view subjectively and objectively.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.