A Classification-Driven Partially Occluded Object Segmentation (CPOOS) Method with Application to Chromosome Analysis

Hugo Guterman (Inventor), Boaz Lerner (Inventor)

Research output: Patent

Abstract

Classification of segment images created by connecting points of high concavity along curvatures is used to resolve partial occlusion in images. Modelling of shape or curvature is not necessary nor is the traditional excessive use of heuristics. Applied to human cell images, 82.6% of the analysed clusters of chromosomes are correctly separated, rising to 90.5% following rejection of 8.7% of the images. Index Terms- Chromosome analysis, image classification, image segmentation, neural networks, partial occlusion 1. Introduction To generate a description of an image it is necessary to segment the image into regions of interest or objects, each having a high level of uniformity in some parameter such as brightness, color or texture. However, objects in images in real-world applications do very often partially occlude each other, hence their segmentation is not trivial and requires the application of a dedicated procedure. A failure to recognise partially occluded objects or partially occ.
Original languageEnglish
StatePublished - 2013

Fingerprint

Dive into the research topics of 'A Classification-Driven Partially Occluded Object Segmentation (CPOOS) Method with Application to Chromosome Analysis'. Together they form a unique fingerprint.

Cite this