Abstract
Nowadays, bioimages such as microscopic images and in situ hybridization images increase exponentially. The rapid growth of such images calls for efficient and effective methods for mining significant patterns in them. As a biological process usually consists of several temporal stages, one important task in bioimage analysis is to classify images into different stages. In this paper, a multi-layer model collaboration approach is proposed to capitalize the class correlations in order to enhance the multi-class classification accuracy. First, several middle-level classes, which are relatively easy to annotate are created. A set of subspace-based classifiers are trained. Next, the classification scores output from these models are integrated with the target class classification scores. The score integration problem was formulated as a convex optimization problem, which is solved by the gradient descent approach. Experiments on four biological image data sets demonstrate that the proposed framework outperforms other current state-of-the-art algorithms, which indicates the proposed framework is promising.
