A Novel Method for Scene Classification Feeding Mid-Level Image Patch to Convolutional Neural Networks

Abstract

Scene classification is an important task for computer vision, and Convolutional Neural Networks, a model of deep learning, is widely used for object classification. However, they rely on pooling and large fully connected layers to combine information from spatially disparate regions; these operations can throw away useful fine-grained information, and in natural scenes, there are many useless information which will increase computation cost. In this paper, mid-level discriminative patches are utilized to pre-process the full images. The proposed method which combines mid-level discriminative patches for preprocessing with CNN for feature extraction improved the efficiency of computation and are more suitable for classifying scenes. Firstly, full images are divided into discriminative parts. Then utilize these patches to go through CNN for feature extraction. Finally, a support vector machine will be used to classify the scenes. Experimental evaluations using MIT 67 indoor dataset performs well and proved that proposed method can be applied to scene classification.