Palmprint Images Research Articles

국부 이진패턴 히스토그램을 이용한 장문인식

This paper proposes an efficient method for verifying palmprint which is captured at the natural interface without any physical restriction. The location and orientation of the region of interest (ROI) in palm images are variously appeared due to the translation and rotation of hand. Therefore, it is necessary to extract the ROI stably for palmprint recognition. This paper presents a method that can extract the ROI, which is based on the reference points that are located at the center of the crotch segments between index finger and middle finger and between ring finger and little finger. It also proposes a palmprint recognition method using the histogram of local binary patterns (LBP). Experiments for evaluating the performance of the proposed method were performed on 1,597 palmprint images acquired from 100 different persons. The experimental results showed that ROI was correctly extracted at the rate of 99.5% and the equal error rate (EER) and the decidability index d` indicating the performance of palmprint verification were 0.136 and 3.539, respectively. These results demonstrate that the proposed method is robust to the variations of the translation and rotation of hand.

Palmprint authentication using fusion of wavelet and contourlet features

AbstractLow resolution palmprint images consist of discriminative multisized and multidirectional principal lines and wrinkles. Intuitively, discrete wavelet transform (DWT) is a good choice to extract such patterns due to its space‐frequency localization, multiresolution analysis (MRA) capability, and computational efficiency. However, most of the DWT‐based palmprint recognition systems fail to report low equal error rate (EER) due to inherent limitations of DWT and shift‐rotational variations in the intraclass palmprint images. This paper proposes the techniques for shift and rotation invariant feature extraction using DWT extension. The effectiveness of these techniques is tested on deliberately shifted and rotated palmprints. Further, limited directionality due to DWT is overcome by augmenting with features of contourlet transform. Contourlet transform can extract curve singularities effectively with multidirectional decomposition capability; wavelets are good in extracting point singularities. The different views of contourlet transform and DWT on palmprints motivate us to extract contourlet and wavelet features, and examine them for their individual and combined verification performances. The combined mode is found to perform well over their individual performances. The average EER (0.41%), obtained on PolyU‐Online‐Palmprint‐Database‐II (PolyU), is better than the existing wavelets/transform‐based palmprint recognition approaches and comparable to the other state of the art palmprint recognition approaches. The computational burden on feature extraction and matching is substantially low thereby making the approach suitable for resource constrained environments. Copyright © 2010 John Wiley & Sons, Ltd.

Palmprint Recognition Based on Subspace Analysis of Gabor Filter Bank

This paper introduces a new technique for palmprint recognition based on Fisher Linear Discriminant Analysis (FLDA) and Gabor filter bank. This method involves convolving a palmprint image with a bank of Gabor filters at different scales and rotations for robust palmprint features extraction. Once these features are extracted, FLDA is applied for dimensionality reduction and class separability. Since the palmprint features are derived from the principal lines, wrinkles and texture along the palm area. One should carefully consider this fact when selecting the appropriate palm region for the feature extraction process in order to enhance recognition accuracy. To address this problem, an improved region of interest (ROI) extraction algorithm is introduced. This algorithm allows for an efficient extraction of the whole palm area by ignoring all the undesirable parts, such as the fingers and background. Experiments have shown that the proposed method yields attractive performances as evidenced by an Equal Error Rate (EER) of 0.03%.

Palmprint Recognition Based on Statistical Local Binary Orientation Code

A novel coding based method named as local binary orientation code (LBOCode) for palmprint recognition is proposed. The palmprint image is firstly convolved with a bank of Gabor filters, and then the orientation information is attained with a winner-take-all rule. Subsequently, the resulting orientation mapping array is operated by uniform local binary pattern. Accordingly, LBOCode image is achieved which contains palmprint orientation information in pixel level. Further we divide the LBOCode image into several equal-size and nonoverlapping regions, and extract the statistical code histogram from each region independently, which builds a global description of palmprint in regional level. In matching stage, the matching score between two palmprints is achieved by calculating the two spatial enhanced histograms' dissimilarity, which brings the benefit of computational simplicity. Experimental results demonstrate that the proposed method achieves more promising recognition performance compared with that of several state-of-the-art methods.

Palmprint recognition based on Mel frequency Cepstral coefficients feature extraction

Palmprint identification is a measurement of palmprint features for recognizing the identity of a user. Palmprint is universal, easy to capture and it does not change much across time. This paper presents an application of Mel frequency Cepstral coefficients (MFCCs) for identification of palmprint. Palmprint feature extraction is based on transforming the palmprint image into one dimensional (1-D) signal and then extracting MFCCs from this signal. Wavelet transform (DWT) of the 1-D palmprint signals are used for extracting additional features to help in the recognition process. The features from MFCCs of this DWT vector are added to the MFCCs feature vector, generated from the original palmprint signal, to form a large feature vector that can be used for palmprint identification. Feature matching is performed in this research using feed forward back propagation error neural network. Experimental results show that the proposed method is robust in the presence of noise.

A SCANNER BASED PALMPRINT VERIFICATION SYSTEM FOR CIVIL APPLICATION

The concept of capturing a palmprint using a scanner is not new, but the current palmprint capture devices based on a scanner have the limitations of low speed and large weight. A new palmprint capture device based on a scanner has been developed, which can overcome these limitations. A scanner based palmprint verification system (PVS) has also been designed using the proposed palmprint capture device. A commercially available mobile internet device (MID) was used to execute the whole program and to store the collected palmprint images. A small palmprint database was built using the developed palmprint capture device and the experimental results on this palmprint database showed that the designed system achieved an acceptable level of performance. The proposed PVS has a stable performance, small size and low price, and can meet the practical needs of civil palmprint applications.

A Novel Method for Palmprint Recognition Based on Tensor Subspace Learning

Recently, palmprint identification has been developed for security purpose. In this paper, we propose a novel palmprint recognition scheme which has three features: 1) representation of palmprint images by Local Binary Pattern (LBP); 2) dimensionality reduction by tensor subspace learning; and 3) recognition by multiple kernel classification method based on tensor analysis. LBP can effectively capture substantial palm features while keeping robustness to illumination. Then we reduce the dimensionality of each palmprint samples based on tensor subspace learning which can preserve the spatial structure of LBP. Tensor multiple kernel SVM classifier is finally employed for palmprint recognition. Experimental results on PolyU palmprint database show the effectiveness of the proposed method.

Palmprint matching algorithm based on-àtrous-Contourlet transform and invariant moments

In order to improve the speed and accuracy of palmprint identification system and overcome the weakness of Contourlet transform in dealing with high-dimensional signals,a novel identification algorithm of palmprint feature was proposed.Firstly,the atrous-Contourlet transformation for palmprint image was decomposed to obtain high frequency coefficients and low frequency coefficients in the different sub-band of different direction.Then,different feature weighting coefficients according to the statistical characteristics extracted from different frequency domains were chosen,which were calculated to get some new invariant moments vectors.Finally,the palmprint identification was achieved.The experimental results show that the method here is more effective in matching than wavelet moment algorithm,Hu's invariant moment algorithm and Contourlet algorithm.

Survey of Palmprint Recognition Algorithms

As an emerging biometric technology,palmprint recognition has recently received considerable research interest.Because of its low-price capture device,fast execution speed,and high verification accuracy,palmprint recognition is very competitive in biometric research and is expected to have a wide range of security applications.This paper first introduces the characteristics of the palmprint,the acquisition and the preprocessing method for palmprint image,and then presents a survey of the palmprint recognition algorithms.According to different feature extraction and matching approaches,we roughly group these algorithms into four categories:structure based,statistics based,subspace based and coding based methods.After surveying and comparing these algorithms in each category,we conclude this paper with a discussion of future trends.

An Online System of Multispectral Palmprint Verification

Palmprint is a unique and reliable biometric characteristic with high usability. With the increasing demand of highly accurate and robust palmprint authentication system, multispectral imaging has been employed to acquire more discriminative information and increase the antispoof capability of palmprint. This paper presents an online multispectral palmprint system that could meet the requirement of real-time application. A data acquisition device is designed to capture the palmprint images under Blue, Green, Red, and near-infrared (NIR) illuminations in less than 1 s. A large multispectral palmprint database is then established to investigate the recognition performance of each spectral band. Our experimental results show that the red channel achieves the best result, whereas the Blue and Green channels have comparable performance but are slightly inferior to the NIR channel. After analyzing the extracted features from different bands, we propose a score level fusion scheme to integrate the multispectral information. The palmprint verification experiments demonstrated the superiority of multispectral fusion to each single spectrum, which results in both higher verification accuracy and antispoofing capability.

Motion invariant palm-print texture based biometric security

Biometric based identification is an emerging technology that can solve many security problems. Although systems based on fingerprint and eye features have so far achieved the best matching performance, human hand also contains a wide variety of features, e.g. shape, texture and principal palm lines etc. This feature of the human hand is quite stable and hand images can be extracted very easily. Palm-print is a new and emerging biometric feature for personal recognition. This paper describes an automated approach to palm-print recognition. In contrast to existing palm-print based biometric systems, a new system which is resistant to motion variance of the palm has been proposed. A Palm-print image is taken as an input and then a low pass Gaussian filter is applied to remove the noise from image. Further, since the centre of mass always remains constant, so this property has been taken into account to extract the ROI (Region of Interest) from palm-print image. SIFT (Scale Invariant Feature Transformation) features have been used further for extracting stable texture features from the ROI and are stored. These stable features extracted from the ROI are further used for comparison with stable texture features extracted from ROI of other palmprint images to provide biometric based identification and security.

Multisensor biometric evidence fusion of face and palmprint for person authentication using Particle Swarm Optimisation (PSO)

This paper presents a novel biometric sensor fusion technique for face and palmprint images using Particle Swarm Optimisation (PSO). The proposed method can be visualised in the following steps: we first decompose the face and palmprint image obtained from different sensors using wavelet transformation and then, we employ PSO to select most informative wavelet coefficients from face and palmprint to produce a new fused image. We then employed Kernel Direct Discriminant Analysis (KDDA) for feature extraction and the decision about accept/reject is carried out using Nearest Neighbour Classifier (NNC). Extensive experiments carried out on a virtual multimodal biometric database of 250 users indicate the efficacy of the proposed method.

Development of a New Cryptographic Construct Using Palmprint-Based Fuzzy Vault

The combination of cryptology and biometrics has emerged as promising component of information security. Despite the current popularity of palmprint biometric, there has not been any attempt to investigate its usage for the fuzzy vault. This paper therefore investigates the possible usage of palmprint in fuzzy vault to develop a user friendly and reliable crypto system. We suggest the use of both symmetric and asymmetric approach for the encryption. The ciphertext of any document is generated by symmetric cryptosystem; the symmetric key is then encrypted by asymmetric approach. Further, Reed and Solomon codes are used on the generated asymmetric key to provide some error tolerance while decryption. The experimental results from the proposed approach on the palmprint images suggest its possible usage in an automated palmprint-based key generation system.

Invariant pattern recognition using contourlets and AdaBoost

In this paper, we propose new methods for palmprint classification and handwritten numeral recognition by using the contourlet features. The contourlet transform is a new two dimensional extension of the wavelet transform using multiscale and directional filter banks. It can effectively capture smooth contours that are the dominant features in palmprint images and handwritten numeral images. AdaBoost is used as a classifier in the experiments. Experimental results show that the contourlet features are very stable features for invariant palmprint classification and handwritten numeral recognition, and better classification rates are reported when compared with other existing classification methods.

Palmprint Recognition Using 3-D Information

Palmprint has proved to be one of the most unique and stable biometric characteristics. Almost all the current palmprint recognition techniques capture the 2-D image of the palm surface and use it for feature extraction and matching. Although 2-D palmprint recognition can achieve high accuracy, the 2-D palmprint images can be counterfeited easily and much 3-D depth information is lost in the imaging process. This paper explores a 3-D palmprint recognition approach by exploiting the 3-D structural information of the palm surface. The structured light imaging is used to acquire the 3-D palmprint data, from which several types of unique features, including mean curvature image, Gaussian curvature image, and surface type, are extracted. A fast feature matching and score-level fusion strategy are proposed for palmprint matching and classification. With the established 3-D palmprint database, a series of verification and identification experiments is conducted to evaluate the proposed method. The results demonstrate that 3-D palmprint technique has high recognition performance. Although its recognition rate is a little lower than 2-D palmprint recognition, 3-D palmprint recognition has higher anticounterfeiting capability and is more robust to illumination variations and serious scrabbling in the palm surface. Meanwhile, by fusing the 2-D and 3-D palmprint information, much higher recognition rate can be achieved.

Automated flexion crease identification using internal image seams

Palmar flexion crease recognition is a palmprint identification method for verifying biometric identity. This paper proposes a method of automated flexion crease recognition that can be used to identify palmar flexion creases in online palmprint images. A modified image seams algorithm is used to extract the flexion creases, and a matching algorithm, based on kd-tree nearest neighbour searching, is used to calculate the similarity between them. Experimental results show that in 1000 images from 100 palms, when compared to manually identified flexion creases, a genuine acceptance rate of 100% can be achieved, with a false acceptance rate of 0.0045%.

Competitive code–based fast palmprint identification using a set of cover trees

A palmprint identification system recognizes a query palmprint image by searching for its nearest neighbor from among all the templates in a database. When applied on a large-scale identification system, it is often necessary to speed up the nearest-neighbor searching process. We use competitive code, which has very fast feature extraction and matching speed, for palmprint identification. To speed up the identification process, we extend the cover tree method and propose to use a set of cover trees to facilitate the fast and accurate nearest-neighbor searching. We can use the cover tree method because, as we show, the angular distance used in competitive code can be decomposed into a set of metrics. Using the Hong Kong PolyU palmprint database (version 2) and a large-scale palmprint database, our experimental results show that the proposed method searches for nearest neighbors faster than brute force searching.

USER AUTHENTICATION USING FUSION OF FACE AND PALMPRINT

This paper presents a new method of personal authentication using face and palmprint images. The facial and palmprint images can be simultaneously acquired by using a pair of digital camera and integrated to achieve higher confidence in personal authentication. The proposed method of fusion uses a feed-forward neural network to integrate individual matching scores and generate a combined decision score. The significance of the proposed method is more than improving performance for bimodal system. Our method uses the claimed identity of users as a feature for fusion. Thus the required weights and bias on individual biometric matching scores are automatically computed to achieve the best possible performance. The experimental results also demonstrate that Sum, Max, and Product rule can be used to achieve significant performance improvement when consolidated matching scores are employed instead of direct matching scores. The fusion strategy used in this paper outperforms even its existing facial and palmprint modules. The performance indices for personal authentication system using two-class separation criterion functions have been analyzed and evaluated. The method proposed in this paper can be extended for any multimodal authentication system to achieve higher performance.

Orientation selection using modified FCM for competitive code-based palmprint recognition

Coding-based methods are among the most promising palmprint recognition methods because of their small feature size, fast matching speed and high verification accuracy. The competitive coding scheme, one representative coding-based method, first convolves the palmprint image with a bank of Gabor filters with different orientations and then encodes the dominant orientation into its bitwise representation. Despite the effectiveness of competitive coding, few investigations have been given to study the influence of the number of Gabor filters and the orientation of each Gabor filter. In this paper, based on the statistical orientation distribution and the orientation separation characteristics, we propose a modified fuzzy C-means cluster algorithm to determine the orientation of each Gabor filter. Since the statistical orientation distribution is based on a set of real palmprint images, the proposed method is more suitable for palmprint recognition. Experimental results indicate that the proposed method achieves higher verification accuracy while compared with that of the original competitive coding scheme and several state-of-the-art methods, such as ordinal measure and RLOC. Considering both the computational complexity and the verification accuracy, competitive code with six orientations would be the optimal choice for palmprint recognition.

Multifractal characteristics of palmprint and its extracted algorithm

The palmprint is one of the most reliable physiological characteristics that can be used to distinguish between individuals. In this paper, we propose a palmprint recognition method based on multifractal spectrum technology using statistical moment approaches. The multifractal spectrum of palmprint is calculated by developing an algorithm for extracting palmprint characteristics. The three parameters proposed as the distinguishing palmprint features include the width spread and maximum of multifractal spectrum, and a parameter which describes the asymmetry of the spectrum curve. The identification process can be divided into the following main steps: (1) capturing palmprint image, extracting and normalizing the subimages; (2) defining a coordinate system and calculating partition function; (3) estimating multifractal spectrum; (4) extracting the three parameters and, finally, (5) the feature matching and palmprint identification. The experimental results demonstrate the feasibility of the proposed method.