Robust object recognition via weakly supervised metric and template learning

In this paper, we present a new framework for object recognition via weakly supervised metric and template learning, wherein the optimal metric and templates are jointly learned. Its advantages include high computational speed, and robustness against image noise and unbalanced training data. Specifically, considering the noise in the training data, our framework is formulated as a weakly supervised learning model in which images with higher reliability will contribute more to the training result. A latent structural SVM based Weakly Supervised Metric and Template Learning (WSMTL) method is designed to jointly learn the metric, the templates, and a weight vector. The weight vector is used to represent each image׳s reliability. With the learned metric and object templates, each testing sample is recognized via 1-NN searching within templates. Owing to the 1-NN searching scheme in the recognition phase, WSMTL is of great computational efficiency. We used CMU PIE database with synthesized noise to evaluate the robustness of WSMTL. Experimental results show that WSMTL is robust against noise and unbalanced training data. Moreover, we compared it with some state-of-the-art recognition methods on the public traffic sign dataset BTSC and human face database, i.e., Extended Yale-B. The comparison results demonstrate that our method outperforms the others in object recognition tasks.