Feature selection based-on genetic algorithm for image annotation

Machine learning techniques for feature selection, which include the optimization of feature descriptor weights and the selection of optimal feature descriptor subset, are desirable to enhance the performance of image annotation systems. In our system, the multimedia content description interface (MPEG-7) image feature descriptors consisting of color descriptors, texture descriptors and shape descriptors are employed to represent low-level image features. We use a real coded chromosome genetic algorithm and k-nearest neighbor (k-NN) classification accuracy as fitness function to optimize the weights of MPEG-7 image feature descriptors. A binary one and k-NN classification accuracy combining with the size of feature descriptor subset as fitness function are used to select optimal MPEG-7 feature descriptor subset. Furthermore, a bi-coded chromosome genetic algorithm is used for the simultaneity of weight optimization and descriptor subset selection, whose fitness function is the same as that of the binary one. The experimental results over 2000 classified Corel images show that with the real coded genetic algorithm, the binary coded one and the bi-coded one, the accuracies of image annotation system are improved by 7%, 9% and 13.6%, respectively, comparing to the method without machine learning. Furthermore, 2 of 25 MPEG-7 feature descriptors are selected with the binary coded genetic algorithm and four with the bi-coded one, which may improve the efficiency of system significantly.