A Hybrid Genetic Programming Approach to Feature Detection and Image Classification

Image classification is a crucial task in Computer Vision. Feature detection represents a key component of the image classification process, which aims at detecting a set of important features that have the potential to facilitate the classification task. In this paper, we propose a Genetic Programming (GP) approach to image feature detection. The proposed method uses the Speeded Up Robust Features (SURF) method to extract features from regions automatically selected by GP, and adopts a wrapper approach combined with a voting scheme to perform image classification. The proposed approach is evaluated using three datasets of increasing difficulty, and is compared to five popularly used machine learning methods: Support Vector Machines, Random Forest, Naive Bayes, Decision Trees, and Adaptive Boosting. The experimental results show the proposed approach has achieved comparable or better performance than the five existing methods on all three datasets, and reveal its capability to automatically detect good regions from a large image from which good features are automatically constructed.