Animal Biometrics

This chapter presents a brief introduction of the animal biometrics followed by the major characteristics, advantages, potential applications, and interdisciplinary relevance of animal biometrics recognition system in the field of ecology. Further, the chapter includes the general framework of animal biometrics recognition systems along with major components for detection and identification of species or individual animal along with some state-of-the-art animal biometrics recognition systems. Furthermore, the chapter introduces the population distribution of different species, technological challenges and recommendations for animal biometrics. Finally the community, communication, data and tool sharing are also included to provide the better collaboration to encourage the multidisciplinary researches in the field of animal biometrics.

This chapter is dedicated to the comprehensive survey on the current state-of-the-art in the field of animal biometrics. In addition to this, we have provided a brief introduction to the discipline of animal biometrics followed by the classification and identification techniques of species or individual animal using the discriminatory set of their biometric features in brief. Further, the potential challenges of existing methods and research communities, tools, and data sharing are also discussed.

In this chapter, a cattle recognition system is proposed. The proposed cattle recognition system uses the face image for identification of cattle using computer vision approaches. The major research contributions of this research are in three folds: (1) the preparations of a facial image database of cattle, (2) extraction of discriminatory set of features from the cattle’s face image database and implementation of computer vision-based face recognition representation algorithms for recognizing individual cattle, and (3) finally, the experimental results and discussion of face recognition algorithms. Thus, this chapter presents a comprehensive review of the performances of various computer vision and pattern recognition approaches for the application of cattle face recognition.

Animal biometrics-based recognition systems are gradually gaining more proliferation due to their diversity of application and uses. The recognition system is applied for representation, recognition of generic visual features and classification of different species based on their phenotype appearances, the morphological image pattern, and biometric characteristics. The muzzle point image pattern is a primary animal biometric characteristic for the recognition of individual cattle. It is similar to the identification of minutiae points in human fingerprints. This chapter presents an automatic recognition algorithm of muzzle point image pattern of cattle for the identification of individual cattle, verification of false insurance claims, registration, and traceability process. The proposed recognition algorithm uses the texture feature descriptors, such as speeded up robust feature and local binary pattern for the extraction of features from the muzzle point images at different smoothed levels of Gaussian pyramid. The feature descriptors acquired at each Gaussian smoothed level are combined using fusion weighted sum rule method. With a muzzle point image pattern database of 500 cattle, the proposed algorithm yields the desired level of identification accuracy. Moreover, the comparative analysis of experimental results for proposed work and appearance-based face recognition algorithms has been done at each level. The proposed work, therefore, can be a potential approach for the recognition of individual cattle using muzzle point image pattern.

This chapter presents a novel cattle recognition system using hybrid texture feature of muzzle point pattern for identification and classification of cattle breeds. The major contributions of this research are (1) preparation of muzzle point image database, (2) extraction of hybrid texture features of muzzle point images of cattle dataset, (3) classification of cattle using classification models such as K-nearest neighbor (K-NN), Fuzzy-K-NN, Decision Tree (DT), Gaussian Mixture Model (GMM), Probabilistic Neural Network (PNN), Multilayer Perceptron(MLP), and Naive Bays. In addition, the proposed approach is validated by achieving the state-of-the-art accuracy on muzzle point image database of cattle with standard identification settings.

Recently, deep learning approaches have achieved more attention for recognition of species or individual animal using visual features. In this chapter, the deep learning-based recognition system is proposed for identification of different cattle based on their primary muzzle point (nose pattern) image pattern characteristics to solve major problem of missed or swapped animal and false insurance claims. The major contributions of the research work are as follows: (1) preparation of muzzle point image database, which are not publically available; (2) extraction of the salient set of texture features and representation of muzzle point image of cattle using the deep learning-based convolution neural network and deep belief neural network proposed approaches. The stacked denoising auto-encoder technique is applied to encode the extracted feature of muzzle point images; and (3) experimental results and analysis of proposed approach. Extensive experimental results illustrate that the proposed deep learning approach outperforms state-of-the-art methods for recognition of cattle on muzzle point image database. The efficacy of the proposed deep learning approach is computed under different identification settings. With multiple test galleries, rank-1 identification accuracy of 98.99% is achieved.

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.

This chapter provides an extensive view about the state-of-the-art animal biometric recognition systems for different applications and environments. The chapter also introduced animal biometrics databases of different species or individual animal in tabular format. In addition, visual animal biometrics followed by the issues and challenges is presented in brief. Finally, some opinions as to the future directions are presented in the summary of the chapter.