Content uploaded by Sen Lin
Author content
All content in this area was uploaded by Sen Lin on Jun 13, 2018
Content may be subject to copyright.
A preview of the PDF is not available
Abstract and Figures
Compared with traditional contact collection method, contactless acquisition is the mainstream and trend of palmprint recognition. However, this method may lead to affine deformation caused by non-parallelity between palm plane and sensor plane. In order to improve the limitation of scale invariant feature transform (SIFT) about this problem, a better palmprint recognition method based on affine scale invariant feature transform (ASIFT) is proposed. Firstly, an affine model of the deformed palmprint is established, then the latitude and longitude angles of the camera axis are simulated, and the image features in the affine space are extracted. Based on the practical application environment, the SUT pamlprint database is established for the performance tests. Compared with the SIFT and other typical palmprint recognition methods, the experimental results show that ASIFT has good performance in resisting the affine deformation of palmprint, the equal error rate (EER) is 0.6%. In conclusion, the proposed algorithm can successfully solve the deformation problem of palmprint, and has superiority, and strong robustness and stability.
Figures - uploaded by Sen Lin
Author content
All figure content in this area was uploaded by Sen Lin
Content may be subject to copyright.
... From 2010, some papers began to study the palm feature recognition in contactless imaging (Nesrine et al. 2017;Mohsen et al. 2017a, b, c;Mokni et al. 2016;Tamrakar et al. 2016;Lin et al. 2015;Wang et al. 2014;Han et al. 2012;Yuan et al. 2012) have obtained the distribution information of the palm vein and palmprint by contactless approach. There is non-aggression and high degree of public acceptance through contactless approach to obtain hand features. ...
Contactless acquisition enables palm identification device to be more easily accepted by people who worry about hygiene problems. The uncertainty of the position between the palm and the device leads to the horizontal rotation, translation, scaling of palm image. This paper proposes a novel feature extraction method which can reflect the geometric features of palmprint and palm vein without being affected by the scaling, rotation and translation. Firstly, the inscribed circle of palm is obtained, and then several radiation segments are made between the circle center and circumference. The wiring direction from the center to the root points of both middle finger and ring finger is as the direction of the first radiation segment. Secondly, the gradient value of pixels in the inscribed circle is calculated by creating template. The feature vector space is established by the relative radius of radiation segment’s centroids. Finally, the palm image database is established based on the application. The feature stability in different size of sub-template and recognition performance in different number of feature line segments are analyzed. In the size of sub-template is equal to three and the number of feature line segments is 60, the equal error rate is less than 0.4% and feature extraction time is 0.0019 s. The experimental results show that the method can extract out stable characteristics whenever the hand image is scaled, rotated or translated.
Aiming at the problems that current mainstream non-contact palmprint identification systems have unsatisfied robustness and recognition effect, a palmprint recognition method based on binary robust invariant scalable keypoints (BRISK) is proposed. First of all, the BRISK scale-space feature extraction model and sampling pattern are established, and the algorithm procedures are described afterwards. Secondly, the stable feature points of non-contact palmprint images are extracted with the BRISK algorithm, and the number of the palmprint matching points is calculated, with which the palmprint recognition is conducted. Meanwhile, the selection process of the feature threshold is analyzed and given. The presented method was tested on the general IITD non-contact palmprint database established based on the actual environment. Experimental results show that the correct recognition rate of the proposed method can reach 98.124 2%, and the recognition time is only 0.012 1 s. The method illustrated in this paper can further improve the robustness and recognition effect of the non-contact palmprint identification system; the method features fast speed and high efficiency, can satisfy the requirements of online palmprint identification and has considerable application value.
In the field of palmprint recognition, the orientation information of the principal lines and winkles has long been considered the most dominant and reliable feature. Numerous studies have tried to extract the line orientation information. Among them, the orientation based coding methods such as robust line orientation code (RLOC) and binary orientation co-occurrence vector (BOCV) showed highly promising results. However, the orientation information of pixels that are not located on the palm lines could be greatly affected by the lighting conditions. To solve this problem, this paper proposes a new combined approach using both the line orientation and the slope orientation. When a palm image is hypothetically considered as a 3-D terrain, the principal lines and winkles are deep and shallow valleys on a palm landscape. If the previous line-based approaches focus only on the direction of valleys to investigate the palm landscape, this study focuses on the slope direction of local plains as well as the direction of valleys. The proposed method extracts two different orientation features according to the location of pixels and computes the feature distance between two images by a pixel-to-area matching method. Experimental results show that the proposed approach is superior to several state-of-the-art methods based on the line orientation coding.
A palmprint is a relative new biometric feature for personal authentication. A feature extraction method for palmprint recognition based on Two-Dimensional Principal Component Analysis (2DPCA) is proposed in this paper. A series of experiments was performed on the PolyU-Online-Palmprint-Database with a nearest neighbor classifier and cosine distance. The success rate in recognition is 99.14%. The 2DPCA method has higher recognition success rate and is more computationally efficient than PCA, especially for small training samples. The selection of threshold values is also discussed for different application systems.
Palmprint recognition is an efficient method to identify a person. The small size of palmprint identification equipment will facilitate applications and extend application scope. This paper implements a practical schema of the palmprint identification system based on ARM and WinCE. The ARM processor acquires the palm image from a digital camera, extracts the features from the palm image and matches the feature with corresponding template in the database, finally gives out the identification result. Experimentations proved that the proposed system could identify palmprints with high accuracy. Furthermore, the proposed algorithm is invariant to image translation and rotation, and is partially invariant to affine distortion, image scale, changes in 3D viewpoint and illumination. The palmprint could be captured in contactless manner and does not need any fixing facility, which is much friendly to the users. Besides, the proposed system has the merits of small size, cost-effective and low-power, which are appropriate to be adopted in power and cost sensitive civilian applications.
In image matching process, the affine transformation is difficult to avoid. In exiting algorithms, Scale Invarian Feature Transform(SIFT) has strong resistance to changes of scale, rotation, translation and illumination changes generated by affine transformation. However, when an image has a view angle change, especially large change, the SIFT is not satisfactory. This paper researches the principle of the SIFT and improves its matching function. The latitude and longitude of camera axis are simulated firstly, and then the images are matched by using the improved SIFT algorithm. Experiments show that the algorithm not only retains the original advantages of the SIFT algorithm, but also been robust to changes of the angle. It has achieved a complete anti-affine transformation. In conclusions, the proposed algorithm is more suitable to affine transformation, especially large angle changes, as compared with SIFT algorithm.
A remote sensing image registration algorithm based on SIFT and NSCT is proposed in this paper. It combines the flexibility of NSCT for image decomposition with the effectiveness of SIFT algorithm for feature representation to register remote sensing images. Firstly, two related images are decomposed with NSCT. Secondly, the decomposed low frequency images are inputted to SIFT algorithm to obtain matching results. Finally, the optimal parameters of transformation model are estimated based on the matching results; and re-sampling and bilinear interpolation are employed to complete the registration of the two related images. Experimental results demonstrate that the proposed algorithm has better effectiveness and higher matching accuracy than the other two algorithms.
Hand-shape and palm-print as biological characteristics can be used for identification. In this paper, the method of combining the hand-shape and palm-print in the matching layer was adopted according to the merit of the high speed of palm-print identification and high matching rate of hand-shape. This method successfully conquered the weakness of the low recognition rate of hand-shape and the low matching speed of palm-print identification. The hand fingers relative length in hand-shape could be used as feature vector, and the 2-D Gabor in palm-print was used to extract the direction of palm-print lines as the feature information from the region of interest (ROI) of palm-print. The recognition rate of combining with them can achieve 98.57%, and the matching time was reduced. In addition, the collected palm image in different distance was also researched in this paper. The experimental results show that the advantages of combination of the palm-print and hand-shape image is more obvious.
In this paper, biometric methods for contactless and unrestricted access control for mobile devices are proposed. The major contribution of this paper are palmprint and knuckles feature extraction methods dedicated for the mobile contactless biometrics. We use texture mask-based features for the palmprint. For the knuckles, we use Probabilistic Hough Transform and Speeded Up Robust Features as well as the 3-step classification methodology. We prove the efficiency of the presented methods by reporting promising results.
This paper presents an innovative contactless palm print and palm vein recognition system. We design a hand sensor that could capture the palm print and palm vein image using low-resolution web camera. Both the visible and infrared images can be captured at the same time, and we do not need specialized infrared sensor to image the vein pattern. The design of the device is simple and low-cost. The subject can be shielded completely from the complication of undergoing two separate acquiring processes. We allow subjects to position their hands freely above the sensor and they can move their hands during the acquisition process. In order to obtain clear image of the palm vascular pattern, we propose a novel image enhancement technique called local-ridge-enhancement (LRE). The proposed method removes illumination error while keeping good contrast between the print/vein pattern and the background image. Besides, we introduce a simple yet robust directional coding technique to encode the palm print and palm vein features in bit string representation. The bit string representation offers speedy template matching and enables more effective template storage and retrieval. The scores output by the palm print and palm vein experts are fused using Support Vector Machine. The fusion of these features yields promising result for practical implementation.
A new branch of biometrics, palmprint authentication, has attracted increasing amount of attention because palmprints are abundant of line features so that low resolution images can be used. In this paper, we propose a new texture based approach for palmprint feature extraction, template representation and matching. An extension of the SAX (Symbolic Aggregate approXimation), a time series technology, to 2D data is the key to make this new approach effective, simple, flexible and reliable. Experiments show that by adopting the simple feature of grayscale information only, this approach can achieve an equal error rate of 0.3%, and a rank one identification accuracy of 99.9% on a 7752 palmprint public database. This new approach has very low computational complexity so that it can be efficiently implemented on slow mobile embedded platforms. The proposed approach does not rely on any parameter training process and therefore is fully reproducible. What is more, besides the palmprint authentication, the proposed 2D extension of SAX may also be applied to other problems of pattern recognition and data mining for 2D images.