Visual animal biometrics is an emerging research discipline in computer vision, pattern recognition and cognitive science. It is a promising research field that encourages new development of quantified algorithms and methodologies for representing, detection of visible features, phenotypic appearances of species, individuals and recognition of morphological and animal biometric characteristics. Furthermore, it also assists the study of animal trajectory and behaviours analysis of species. Currently, real-world applications of visual animal biometric systems are gaining more proliferation due to a variety of applications and use, enhancement of quantity and quality of the collection of extensive ecological data and processing. However, to advance visual animal biometrics will require integration of methodologies among the scientific disciplines involved. Such valuable efforts will be worthwhile due to the enormous perspective of this approach rests with the formal abstraction of phenomics, to build well-developed interfaces between different organisational levels of life. This study provides a comprehensive survey of visual animal biometric systems and recognition approaches for various species and individual animal based on their morphological image pattern and biometric characteristics. This comprehensive review paper encourages the multidisciplinary researchers, scientists, biologists and different research communities to design the better platforms for the development of efficient algorithms and learning models to solve the massive data processing, classification and identification of different species related problems.

In this study, a new geometric feature representation for a single finger geometry recognition based on infrared image is presented. The geometric representation is expressed based on the fingertip angles (FTA) measured from the right and the left finger edges. The extracted FTA feature is transformed into the frequency domain to form Fourier descriptor (FD) vector using discrete Fourier transform. The domain transformation is intended to make feature representation robust to the shifting, rotation and scaling variations. FD vectors from both right and the left contours are fused together to form a single row vector and principal component analysis is adopted to enhance the orthogonality between the FD components. The authors’ experimental results demonstrate the feasibility and the effectiveness of the proposed method.

Dictionary learning (DL) technique has received a great interest recently, due to its significant role in feature extraction. Although many DL-based methods have been presented, some of them still suffer from the lack of discriminative features, especially for the local manifold features. To mitigate this problem, the authors propose a novel DL method named low-rank representation based on twin tensor kernel (LRR-TTK) DL for face recognition in this study. Specifically, the training samples are projected to a high-dimensional space with TTK. Then, they extract the local manifold features and spatial features (representation coefficients) hidden in the facial images by TT locality preserving projection. In addition, powered by LRR reconstruction and DL theory, much more discriminative features are obtained, which can improve the recognition rate greatly. Comprehensive experimental results at AR, extended Yale-B and FERET face databases demonstrate the superiority of their proposed method.

This study presents a protection method for fingerprint templates by using fused structures at the feature level. The authors compute two transformed features from minutiae points: namely, local structure and distant structure. These structures are represented as bit-strings. A fusion on bit-strings is done at the feature level to produce a cancelable template. An equal error rate (EER) of 2.19, 1.6 and 6.14% on Fingerprint Verification Competition (FVC) 2002 Database (DB)1 through DB3 databases and an EER of 11.89, 12.71, 17.6% on FVC 2004 DB1 through DB3 proves the tenability of the proposed method.

Fingerprint recognition is widely used for verification and identification in many commercial, governmental and forensic applications. The orientation field (OF) plays an important role at various processing stages in fingerprint recognition systems. OFs are used for image enhancement, fingerprint alignment, for fingerprint liveness detection, fingerprint alteration detection and fingerprint matching. In this study, a novel approach is presented to globally model an OF combined with locally adaptive methods. The authors show that this model adapts perfectly to the ‘true OF’ in the limit. This perfect OF is described by a small number of parameters with straightforward geometric interpretation. Applications are manifold: Quick expert marking of very poor quality (for instance latent) OFs, high-fidelity low parameter OF compression and a direct road to ground truth OFs markings for large databases, say. In this contribution, they describe an algorithm to perfectly estimate OF parameters automatically or semi-automatically, depending on image quality, and they establish the main underlying claim of high-fidelity low parameter OF compression.

An off-line text-independent writer verification system that leverages the similarities with the field of speaker recognition by employing analogous techniques for modelling and comparing the features extracted from the input text images is presented. The main contribution of this work is the use of the i -vector paradigm in a writer verification setting. The proposed system is evaluated with images of lines of text from the IAM Handwriting Database, and compared with more traditional approaches. The authors also analyse several algorithms for the detection and extraction of points of interest in the text images, different parameters for the modelling part and different scoring techniques. The obtained results show that the use of i -vectors clearly improves the performance of the system even for configurations where the overhead of the additional calculations is minimal.

Face detection is the determination of the positions and sizes of faces, primarily human, within digital images and videos, often as a component of a broader facial recognition system. It is seen as technologically mature, yet its operational performance typically remains sub-optimal, even within the less difficult frontal face detection tests. Empirical evidence shows that the Viola–Jones framework, a standard face detection solution with generally superior performance and other desirable properties, underdetects in some instances. Some true faces survive all but the final stages of the rejection cascade, resulting in missed faces. A hybrid framework consisting of a neural network following a truncated Viola–Jones cascade is constructed in an attempt to recover the undetected faces. Presumably, the neural network could fine tune and augment the face decision. Its inputs are a subset of the thresholding (detection) values of a rejection cascade's intermediate stages. Experiments reveal significantly improved performance, with increased detection rates if no false alarm increases are tolerated, with a greater detection rate increase if some false alarm increases are acceptable, and with a substantial false alarm reduction with no detection reduction. These improved face detection results could address shortcomings in widely-varying applications.

Accurate gathering of phenotypic information is a key aspect in several subject matters, including biometrics, biomedical analysis, forensics, and many other. Automatic identification of anatomical structures of biometric interest, such as fingerprints, iris patterns, or facial traits, are extensively used in applications like access control and anthropological research, all having in common the drawback of requiring intrusive means for acquiring the required information. In this regard, the ear structure has multiple advantages. Not only the ear's biometric markers can be easily captured from the distance with non intrusive methods, but also they experiment almost no changes over time, and are not influenced by facial expressions. Here we present a new method based on Geometric Morphometrics and Deep Learning for automatic ear detection and feature extraction in the form of landmarks. A convolutional neural network was trained with a set of manually landmarked examples. The network is able to provide morphometric landmarks on ears' images automatically, with a performance that matches human landmarking. The feasibility of using ear landmarks as feature vectors opens a novel spectrum of biometrics applications.

The problem of fingerprint liveness detection has received an increasing attention in the last decade, as attested by the organisation of three editions of an international competition, named LivDet, dedicated to this challenge. LivDet editions and other works in the literature showed that the performance of current fingerprint liveness detection algorithms is not good enough to allow empowering a fingerprint verification system with a module aimed to distinguish alive from fake fingerprint images. However, recent developments have shown that texture-based features can provide promising solutions to this problem. In this study, a novel fingerprint liveness descriptor named binarised statistical image features (BSIFs) is adopted. Similarly to local binary pattern and local phase quantisation-based representations, BSIF encodes the local fingerprint texture into a feature vector by using a set of filters that, unlike other methods, are learnt from natural images. Extensive experiments with over 40,000 live and fake fingerprint images show that the authors’ proposed method outperforms most of the state-of-the-art algorithms, allowing a step ahead to the real integration of fingerprint liveness detectors into verification systems.

In this study, the authors propose a multimodal biometric system by combining the finger knuckle and finger vein images at feature-level fusion using fractional firefly (FFF) optimisation. Biometric characteristics, like finger knuckle and finger vein are unique and secure. Initially, the features are extracted from the finger knuckle and finger vein images using repeated line tracking method. Then, a newly developed method of feature-level fusion using FFF optimisation is used. This method is utilised to find out the optimal weight score to fuse the extracted feature sets of finger knuckle and finger vein images. Thus, the recognition is carried out by the fused feature set using layered k-SVM (k-support vector machine) which is newly developed by combining the layered SVM classifier and k-neural network classifier. The experimental results are evaluated and the performance is analysed with false acceptance ratio, false rejection ratio and accuracy. The outcome of the proposed FFF optimisation system obtains a higher accuracy of 96%.