Range segmentation

About: Range segmentation is a research topic. Over the lifetime, 3493 publications have been published within this topic receiving 70351 citations.

Segmentation of range and reflectance images with an expert system

Abstract: We propose a new image segmentation technique based on a combination of both global and local segmentation methods applied to range images and those applied to reflectance images. A high level image processing based on on expert system CLIPS combines all the information produced by the different segmentation methods and gives a good parameterization of all object surfaces included in the images. We show the contribution of such a system with respect to image segmentation.

Segmentation of breast images to find the lesions using the decreased neighborhood graph algorithm

Abstract: Classification of soft tissues is often joined with uncertainty and ultimate areas border might be hardly measured in segmentation. Basic techniques of edge detection can be used to determine the boundary edge, but because of noise and gray levels steep changes in medical images, it is difficult to achieve the edge of a lesion in image with reasonable and precise segmentation. In this paper a graph based algorithm is presented to extract alike region in image, this approach helps finding similar lesions and accurate segmentation.

Weighted principal component analysis based edge linking

Abstract: As a complicated and troublesome research area, the edge detection is a fundamental step in terms of some image processing tasks including segmentation, compression and registration. In this study, we present a new approach for edge linking by applying the concept of the PCA on different types of images to determine the attractive edge segments. To determine the direction by using the angle information, the PCA decomposition is carried out on the block around the processed point. Specifically, the horizontal and vertical directions are taken into account by considering the angle between the eigenvectors corresponding to the largest and smallest eigenvalues. After making some experiments on noisy and noise free images, we have observed that the proposed method is robust to noise, preserves the structure of image and extracts well-localized and straight lines.

Spatial-region classification by Min-Connected algorithm for unsupervised segmentation

Abstract: This work lies within the scope of color image segmentation by spatial-region classification. The spatial distribution of objects in each region of image is difficult to be identified when the region are non-connected clusters. A standard of color identification by conventional methods of segmentation remains weak for capturing the spatial dispersion of the various objects of the same color region. We propose to apply a spatial classification to characterize geographical connected sets that represent the same regions. The originality of this paper lies in our new min-connected algorithm which is derived from a spatial-color compactness model. Our work is a hybrid segmentation that takes into account the distribution of colors in the color space and the spatial location of colors in the image plane. Experimental tests on synthetic and real images show that our technique leads to promising results for segmentation.

Image generating device for stereoscopic vision, stereoscopic vision video display device, and image generating method for stereoscopic vision

Abstract: PROBLEM TO BE SOLVED: To further improve the reproducibility of the brightness of an entire original image with respect to the brightness of an entire stereoscopic vision videoSOLUTION: A value is set for each synthetic image sub-pixel included in a lenticular lens L1 by obtaining the sum of three fourths of the luminance of a sub-pixel in an original image pixel corresponding to a synthetic image pixel P0 and one fourth of the luminance of a sub-pixel in the original image pixel corresponding to a synthetic image pixel P1 A value is set for each synthetic image sub-pixel included in a lenticular lens L2 by obtaining the sum of two fourths of the luminance of sub-pixels in the original image pixels corresponding to the synthetic image pixels P1 and P2 A value is set for each synthetic image sub-pixel included in a lenticular lens L3 by obtaining the sum of one fourth of the luminance of the sub-pixel in the original image pixel corresponding to the synthetic image pixel P2 and three fourths of the sub-pixel in the original image pixel corresponding to a synthetic image pixel P3