Finger vein pattern learning models and techniques — A study

Finger vein recognition is the process of determining whether or not the input finger image belongs to a specific person Finger-vein recognition is a new research area in the field of biometric recognition. Finger vein patterns are considered to be diverse even in identical twins and between an individual’s different fingers. Gabor Filter is the main algorithm utilized in this paper. Finger-vein Pattern Extraction is done with the Gabor Filter. Prior to feature extraction, many preprocessing processes must be completed. Image Normalization, ROI Extraction using Background Separation, and Image Contrast Enhancement are the preprocessing steps. During post-processing, we also applied certain approaches to improve the clarity of the retrieved finger vein pattern. Morphological Operations are employed during post-processing to expand the vein pattern’s shape and structure. The SURF technique is also utilized to detect descriptive important points in the Vein pattern image, which aids us in the matching process. An experimental result shows that the suggested system extracts vein patterns with near-perfect accuracy and recognizes them with high accuracy.

Authentication is a major gateway towards exploring unsecure treasure of information and data. In today’s modern technology driven society requires a full proof validation and authentication mechanism. Henceforth, this paper discusses on the finger vein pattern extraction and processed based on dual mode authentication system. Typically, the finger vein print based authentication is saturated research field and thus the paper explores authentication based on the pattern rather than print. The technique develops a Dynamic Finger Vein Extraction for dis-Sampled Datasets (DFVdSD). The technique provides an internal level enhancive approach of understanding and processing the finger vein patterns. The process is then authenticated with dual model of signal validation, the patterns of each finger vein is further synchronized with user signal data. Thus making the system secure and unbreakable. The technique also evaluates techniques on untrained dataset classification.

Finger vein patterns have recently been recognized as an effective biometric identifier and many related work can achieve satisfied results. However, these methods usually suppose the database is non-rotated or slightly rotated, which are strict for preprocessing stages, especially for capture. As we all know, user-friendly capture tends to cause the rotation problem, which degrades the recognition performance due to the unregulated images or feature loss. In this paper, we propose a new finger vein recognition method to solve the common rotation problem of finger vein images. Two experiments are designed to evaluate the recognition performance in both verification mode and identification mode and to demonstrate the advantages and robustness of our method in different rotated databases compared with pattern binary based method like LBP. Experimental results show that the proposed method can not only achieve a lower EER (1.71%) than LBP (2.67%), but also can overcome the difficulties of rotation in rotated databases. The EERs of proposed method in three different rotated databases are 2.15%, 2.98% and 2.75% respectively, which shows that our method has better robustness in rotation than LBP.

A novel method for finger vein pattern extraction from infrared images is presented. This method involves four steps: preprocessing which performs local normalization of the image intensity, image enhancement, image segmentation, and finally postprocessing for image cleaning. In the image enhancement step, an image which will be both smooth and similar to the original is sought. The enhanced image is obtained by minimizing the objective function of a modified separable Mumford Shah Model. Since, this minimization procedure is computationally intensive for large images, a local application of the Mumford Shah Model in small window neighborhoods is proposed. The finger veins are located in concave nonsmooth regions and, so, in order to distinct them from the other tissue parts, all the differences between the smooth neighborhoods, obtained by the local application of the model, and the corresponding windows of the original image are added. After that, veins in the enhanced image have been sufficiently emphasized. Thus, after image enhancement, an accurate segmentation can be obtained readily by a local entropy thresholding method. Finally, the resulted binary image may suffer from some misclassifications and, so, a postprocessing step is performed in order to extract a robust finger vein pattern.

A finger vein authentication system is proposed in this research. Biometrics is the science of determining a person's identity based on physiological or behavioral characteristics. Physical characteristics like fingerprints, a face or a retina, as well as personal characteristics like a signature, are included in these characteristics. Biometric features are significantly more difficult for attackers to replicate or fabricate than traditional methods, and they are extremely rare to lose. Biometric traits are used in the identification system, which increases security and dependability. The technology to verify vein patterns is still relatively new, compared with other human characteristics. The proposed work focuses on developing a contactless sensor to retrieve features from the hand's finger vein pattern using a Deep attribute Representation based Fractional Firefly method (DAR-FFF). Vein pattern identification scans the blood for hemoglobin using an infrared light source. After the participant's palm is placed over the sensing device, an infrared region beam from the device measures the orientation of the arteries. These ultraviolet wavelengths are absorbed by liquid hemoglobin in the vasculature, resulting in dark streaks on the map. The hand's finger has more intricate circulatory pathways and a variety of distinguishing characteristics. Image enhancement, skeletonization, and vein pattern chain code comparison are all processes in this procedure.

In any organization, providing a secured authentication system is a challenge. Here, we propose a secured authentication process using finger-vein patterns. Finger vein is a reliable biometric trait because of its distinctiveness and permanence properties. The proposed algorithm initially captures the finger-vein image and is preprocessed using Gaussian blur and morphological operations. Then features like number of corner points and the location of these corner points are extracted. The features fetched for an individual from database are compared against the extracted features. If the comparison satisfies predefined threshold value, then the authentication is successful. The simulation results of the proposed algorithm have produced the FAR as 2.78%, FRR as 0.09% and the overall performance as 99.96%.

Recent years have seen a plenty of personal identification methods with different biometrics such as finger pattern, face, palm-print and vein. The majority of these methods focus on complex image data projections and transforms in Fourier space, wavelet space or other domains, which usually bring heavy load in computation and difficult understanding in perceptual intuition. Moreover, these methods, oriented to multiple samples learning, are constricted usually in application. Among so much biometrics, vein, as a living feature with high anti-counterfeiting capability, has attracted considerable attention. In this paper, we propose a structured personal identification approach using finger vein Location and Direction Coding(LDC). First of all, we design a finger vein imaging device with near-infrared(NIR) light source, by which a database for finger vein images is established. Subsequently, we make use of the brightness difference in the finger vein image to extract the vein pattern. Furthermore, finger vein LDC is proposed and performed, which creates a structured feature image for each finger vein. Finally, the structured feature image is utilized to conduct the personal identification on our image database for finger vein, which includes 440 vein images from 220 different fingers. The equal error rate of our method for this database is 0.44%.

Finger vein recognition has received more attention in recent years due to its high security and promising development potential. However, extracting complete vein patterns and obtaining features from the original images suffer from the low contrast of finger vein images, which dramatically restrains the performance of finger vein recognition algorithms. Inspired by this motivation, we propose an explicit and implicit feature fusion Network (EIFNet) for finger vein verification. It can extract more comprehensive and discriminative features by complementarily fusing the features extracted from binary vein masks and gray original images. We design a feature fusion module (FFM) acting as a bridge between mask feature extraction module (MFEM) and contextual feature extraction module (CFEM) to achieve the optimal fusion of features. To obtain more accurate vein masks, we develop a novel finger vein pattern extraction method and provide the first finger vein segmentation dataset THUFVS. We solve the difficulty of building finger vein segmentation datasets in a simple but effective way, and develop a complete process encompassing dataset creation, data augmentation refinement and network design, which refers to the Mask Generation Module (MGM), for the deep learning based finger vein pattern extraction method. Experimental results demonstrate the superior verification performance of EIFNet on three widely used datasets compared with other existing methods.

Exploring finger vein based personal authentication for secure IoT

Finger vein pattern recognition using image processing technique

Recently, finger vein sensors have been embedded in all kinds of electronic devices for personal identification, such as intelligent door locks and attendance machines. The embedded sensors are generally small, thus capturing only part of the finger vein. However, prior studies have focused on near-full finger vein recognition, without considering the partial finger vein image caused by the small imaging window of the finger vein sensor. This paper aims to study personal identification based on partial finger vein images, known as small-area finger vein recognition. The effect of the small-area finger vein on recognition performance is first analyzed by cutting out the local part from the near-full finger vein image to model a small-area finger vein image. Second, a small-area finger vein database is built using a commercial finger vein imaging device, in which the vein pattern from approximately one-third of one adult finger is captured. To explore more discriminative information from small-area finger vein images, we propose a locality-constrained consistent dictionary learning (LCDL) method to fuse multiple features for small-area finger vein recognition. Finally, the proposed method is evaluated on the self-built small-area finger vein database and four synthetic small-area finger vein databases. Experimental results show the promising recognition performance of the proposed method.

In the process of image acquisition, the contrast between veins and non-veins in finger vein images is not high due to the influence of the fuzzy light source, skin scattering and finger movement. To solve this problem, a finger vein image enhancement method is proposed (GTGFs), which enhances finger vein patterns by setting guided image as input image firstly. On this basis, the tri-Gaussian model is based on disinhibitory properties of the concentric receptive field used to locally enhancing the image. The parameters of the tri-Gaussian model are determined based on the finger vein width information. The experiment results show that the proposed enhancement method can significantly enhance the finger vein patterns and improve the recognition effect of the methods based on vein pattern segmentation.

Nowadays personal information security is an important issue. Number of valuable data and files are stored in server and moreover private data are shared in worldwide. To access the private information only by the authorized user is becoming indispensable. Biometric plays a big role in strong security and large attention in research field. The biometric characteristics like palm print, finger print, Iris, DNA, face detection, finger vein etc. are used. Now finger vein is leading technique now. The big advantages of finger vein pattern are lively detection, present under the skin, and cant possible to copy or stolen. Finger vein authentication base applications are widely used in Japan’s like bank, airport, person authentication, jail etc. This paper, we study comparatively the various techniques of finger vein identification or authentication. The main focus is comparative study of existing vein pattern acquisition methods, feature extraction techniques and its results.

Finger vein patterns have been proposed as a suitable biometric feature for authentication applications. Systems using this feature are generally low cost, accurate and easy to use. Our goal in this paper is to improve the efficiency of vinous extraction. For robust and precise extraction of the depicted veins, a method of calculating local maximum curvatures in cross-sectional profiles of a vein image was used. The results obtained from image quality assessment were promising.

Biometrics are unique physical characteristics, such as fingerprints, that can be used for automatic recognition. Biometric identifiers are often classified as physiological characteristics associated with body shape. The goal is to capture a piece of biometric data from that person. It could be a photograph of their face, a recording of their voice, or a picture of their fingerprints. While there are numerous types of biometrics for authentication, the six most common are facial, voice, iris, near-field communication, palm or finger vein patterns, and Quick Response (QR) code. Biometrics is a subset of the larger field of human identification science. This paper explores computational approaches to speaker recognition, face recognition, speech recognition, and fingerprint recognition to assess the overall state of digital signal processing in biometrics.