Object identification for computer vision using image segmentation
📜 Abstract
Object detection for computer vision is one of the key factors for scene understanding. It is still a challenge today to accurately determine an object from a background where similar shaped objects are present in a large number. In this paper we proposed a method for object detection from such chaotic background by using image segmentation and graph partitioning. We build a “feature set” from the original object and then we train the system using the “feature set” and graph partitioning on the chaotic image. Testing is done on computer manipulated images and real world images. In both the cases our system identified the search object among other similar objects successfully.
✨ Summary
The paper presents an early segmentation-based object-identification method that combines feature-set construction with graph partitioning to locate a target object among visually similar objects. Subsequent publications cite it as related work in applications and reviews involving image segmentation, object recognition, indoor positioning, and near-infrared pharmaceutical identification. For example, later studies reference the paper when discussing computer-vision-based indoor positioning and image-segmentation methods, while other works list it among prior object-detection or segmentation approaches. (sciencedirect.com)
The available evidence indicates bibliographic and methodological influence within later academic literature, but no specific industrial deployment or product implementation directly attributable to this paper was identified in the search. The paper is listed as a 2010 IEEE conference contribution by Debalina Barik and Manik Mondal, published in the proceedings of the 2nd International Conference on Education Technology and Computer, pages V2-170–V2-172. (researchgate.net)