Image Classification Using Deep Learning and Fuzzy Systems

Abstract

Classification of images is a significant step in pattern recognition and digital image processing. It is applied in various domains for authentication, identification, defense, medical diagnosis and so on. Feature extraction is an important step in image processing which decides the quality of the model to be built for image classification. With the abundant increase in data now-a-days, the traditional feature extraction algorithms are finding difficulty in coping up with extracting quality features in finite time. Also the learning models developed from the extracted features are not so easily interpretable by the humans. So, considering the above mentioned arguments, a novel image classification framework has been proposed. The framework employs a pre-trained convolution neural network for feature extraction. Brain Storm Optimization algorithm is designed to learn the classification rules from the extracted features. Fuzzy rules based classifier is used for classification. The proposed framework is applied on Caltech 101 dataset and evaluated using accuracy of the classifier as the performance metric. The results demonstrate that the proposed framework outperforms the traditional feature extraction based classification techniques by achieving better accuracy of classification.