Relevance Feedback-based Image Retrieval using Particle Swarm Optimization

Image retrieval is a basic task in many content-based image systems. Achieving a high precision, while maintaining the computation time, is very important in relevance feedback-based image retrieval systems. This paper establishes an analogy between this and the task of image classification. Therefore, in the image retrieval problem, we will obtain an optimized decision surface that separates the dataset images into two categories of relevant/irrelevant images corresponding to the query image. This problem is viewed and solved as an optimization problem using the particle optimization algorithm. Although the particle swarm optimization (PSO) algorithm is widely used in the field of image retrieval, no one uses it for a direct feature weighting. The information extracted from the user feedbacks will guide particles in order to find the optimal weights of various features of images (color-, shape- or texture-based features). Fusion of these very non-homogenous features require a feature weighting algorithm that will take place by the help of the PSO algorithm. Accordingly, an innovative fitness function is proposed to evaluate each particle’s position. The experimental results on the Wang dataset and Corel-10k indicate that the average precision of the proposed method is higher than the other semi-automatic and automatic approaches. Moreover, the proposed method suggests a reduction in the computational complexity in comparison with the other PSO-based image retrieval methods.