• Dr. R. MATHESWARI

Object detection and tracking of moving objects play a vital role in digital image processing. Objects needs to be recognized at all the stages considering different factors like size, shape, color, dynamic background, cluttered environment, occlusion, optical flow and with fast moving objects. Humans with very little effort identifies number of objects in images even when they change their nature. Image objects changes in their viewpoints like different sizes / scale, when they are translated or rotated etc. Humans recognize objects even when they are partially obstructed from the view. Employing computers for these kind of tasks are more challenging. Therefore the proposed system combines appearance-based 3D object recognition systems with an algorithm for occluded parts identification. The method performs recognition of random objects in the presence of clutter and occlusion. Bounding box with patch-based framework for object detection is presented in this paper.

Recognition based on appearance, Bounding box, Patch creation, Occlusion detection

"Occluded Parts Identification for Human Recognition System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 4, page no.882-888, April-2020, Available :http://www.jetir.org/papers/JETIR2004120.pdf

"Occluded Parts Identification for Human Recognition System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 4, page no. pp882-888, April-2020, Available at : http://www.jetir.org/papers/JETIR2004120.pdf