Image Classification Using Object Attention Model

Dr.S. Vanitha Sivagami and N. Muthupriya

Classification of the objects is an easy task for humans, yet it’s tiring to the machine. The image classification includes image pre-processing, object detection, object segmentation, feature extraction and object classification. In our task, Object Recognition is done by selective search which is a hierarchical grouping algorithm used for locating objects in the scenes. Here locations are generated at all scales by continuing the grouping process until the whole image becomes a single region. Positive and Negative samples are generated by comparing object hypothesis with the groundtruth images. HOG feature extraction is more dominant in object recognition. Hence, Support Vector Machine uses this HOG features for classification. Deep neural network is also used for image classification.

Volume 11 | 04-Special Issue

Pages: 1109-1118