SIFT and tensor based object classification in images using Deep Neural Networks
N Najva, Edet Bijoy K. · 2016
Object classification is an important task within the field of computer vision. It is the process of labeling objects into predefined and semantically meaningful categories using trained datasets. A classification is made using a segment of image which is actually a single pixel or a group of pixels which is called a classification unit. Many researchers are working in this area to improve the accuracy of object classification focusing on different features and classifiers. As SIFT feature dominates in current object classification problem, we incorporate Tensor features with SIFT to improve the accuracy of the problem. Moreover we use Deep Neural Network for classification which is a type of artificial intelligence that could solve complex perceptual problems as fast as human brain. Simulation results obtained illustrate that the proposed classifier model produces more accurate results than the existing methods which combines both SIFT and tensor features for feature extraction and DNN for classification.