Online Dictionary Learning using Biogeography-based Optimization for Sparse Representation

Computational visual attention modeling is a topic of increasing importance in machine understanding of images. The model with the `-0 norm as constraint is an NP hard problem. How to find the global optimal solution is a difficult point of this area. For Biogeography-based optimization (BBO) is good at solving NP hard problem, a dictionary learning method based on it is pro-posed in this paper. Biogeography-based optimization (BBO) al-gorithm is a new category of optimization technique based on bio-geography concept. This population-based algorithm uses the idea of the migration strategy of animals or other species for solv-ing optimization problems. The samples are first classified ran-domly for generate original population and residual of approxi-mate the sample class with a rank-1 matrix as habitat suitabil-ity index (HSI) is calculated. Then, select better individuals using league matches. After that new individuals are generated from mi-gration operators and mutation and the residual of the representa-tion is used as data samples for training the dictionary for the next layer. The experimental results show the algorithm are effective