Group Sparse Representation Approach for Recognition of Cattle on Muzzle Point Images

The usage of computer vision adds a new paradigm in the field of animal biometric, and has recently received more attention due to the growing importance of identification and tracking of animal species or individual animals. Biometric characteristics help to develop a better representation and a better identification of different animal species and individual animals. In this work, we propose an effective approach for automatic cattle recognition based on the multiple features of muzzle points and the cattle face images. The proposed method deals the cattle recognition problem as a classification problem among the multiple linear regression models and provides a new theory for the recognition of individual cattle. The group sparse signal representation based classification offers the key to addressing this problem using L2-minimization. In this paper, a comparative study among the well-established handcrafted texture feature extraction techniques and the appearance-based feature extraction techniques is also presented. A detailed set of experimental results on muzzle point image database is also carried to prove the theory. Our method has achieved 93.87% identification accuracy which demonstrates the superiority of the proposed method than the other existing machine learning based recognition algorithms.