Real-Time Recognition of Cattle Using Fisher Locality Preserving Projection Method

Abstract

With the arrival of adequate computer vision techniques, animal biometrics-based recognition systems have accomplished attention for the identification and monitoring of jeopardized species and individual animal. In this chapter, a novel fisher locality preserving projection-based cattle recognition framework is proposed for extraction and representation of cattle identification in real time. The biometric muzzle point image of cattle is captured using the surveillance camera and transferred them to the server of cattle recognition framework by using wireless network technology. The motivation of proposed method is to maximize the inter-class (between-class) scatter feature matrix of the muzzle point image and efficiently minimize the intra-class (within-class) scatter matrix of muzzle point images. This strategy of proposed method improves the accuracy of cattle identification. The efficacy of proposed recognition approach for cattle is estimated under different identification settings. The proposed method yields 96.87% recognition rate for identifying individual cattle. Further, the method assessed the 10.25 recognition time (seconds) for enrollment and recognition of biometrics muzzle point feature for cattle on the different image database.