Object Localization Using Putative Point Matching In Cluttered Scene
Prof.N.C.Patil Sneha Patil · Journal of Emerging Technologies and Innovative Research · 2015
in practice, the scene is often contaminated by clutters, making the point set matching problem more complicated. In this paper, we focus on how to locate a deformable shape in cluttered scenes under the no rigid point set matching framework. The shape May undergo arbitrary translational and rotational changes, and It may be no rigidly deformed and corrupted by clutters. To address the problem of rotation invariant no rigid point set matching, they proposed two methods for shape representation. The shape context (SC) feature descriptor was used and we constructed graphs on point sets where edges are used to determine the orientations of SCs. This enables the proposed methods rotation invariant. The goal of this project is to automatically detect and recognize some objects in an image by using a multi-agents architecture. A knowledge database is thus necessary and should contain an invariant description of known objects for the desired application. An agent processes an area of the image, its goal is to detect an object and check if this object belongs to the knowledge database. Here in this paper presents an algorithm for detecting a specific object based on finding point correspondences between the reference and the target image. It can detect objects despite a scale change or in-plane rotation. It is also robust to small amount of out-ofplane rotation.