Object segmentation for image indexing in large database

Abstract

It is a challenging task to devise an effective model for object segmentation considering numerous classes because different classes might have different features and different backgrounds. We propose a unique segmentation and classification model to detect and classify objects. We propose a extended version of the U-Net model for object segmentation whereas, for the classification task, we propose an effective fusion scheme by exploiting two popular CNN models including ResNet50 and MobileNet. We conduct experiments on the Caltech101 benchmark dataset which contains 8677 images grouped into 101 classes. Besides, to examine the performance of our proposed segmentation method on object detection, we devise a polygonal ground-truth dataset based on the Caltech101 benchmark dataset. The unique feature of polygon shape ground truth is that it creates a mask of the target image in which the probability of noise is very low where there is noise in the bounding box ground truth. Extensive experiments on the Caltech101 benchmark dataset demonstrate the efficacy of our proposed approaches compared to the other existing models with a segmentation accuracy of 95.94% and classification accuracy of 99.90%. We also achieve an average IoU score of 0.98 which validates the effective object recognition performance of our model.