Multispectral Palmprint Recognition Using Score-Level Fusion

Palm print is a unique and reliable biometric characteristic with high usability. Many palm print recognition algorithms and systems have been successfully developed in the past decades. Most of the previous works use the white light sources for illumination. Recently, it has been attracting much research attention on developing new biometric systems with both high accuracy and high anti-spoof capability. Multispectral palm print imaging and recognition can be a potential solution to such systems because it can acquire more discriminative information for personal identity recognition. One crucial step in developing such systems is how to determine the minimal number of spectral bands and select the most representative bands to build the multispectral imaging system. This paper presents preliminary studies on feature band selection by analyzing hyper spectral palm print data (420nm~1100nm). Our experiments showed that 2 spectral bands at 700nm and 960nm could provide most discriminate information of palm print. This finding could be used as the guidance for designing multispectral palm print systems in the future.

Biometrics recognition takes advantage of feature extraction and pattern recognition to analyze the physical and behavioral characteristics of biological individuals to achieve the purpose of individual identification. As a typical biometric technology, palm print and palm vein have the characteristics of high recognition rate, stable features, easy location and good image quality, which have attracted the attention of researchers. This paper designs and develops a multispectral palm print and palm vein acquisition platform, which can quickly acquire palm spectrum and palm vein multispectral images with seven different wavelengths. We propose a multispectral palm print palmar vein recognition framework, and feature-level image fusion is performed after extracting features of palm print palmar vein images at different wavelengths. Through the multispectral palm print palm vein image fusion experiment, a more feasible multispectral palm print and palm vein image fusion scheme is proposed. Based on the results of image fusion, we further propose an improved convolutional neural network (CNN) for model training to achieve identity recognition based on multispectral palm print palm vein images. Finally, the effects of different CNN network structures and learning rates on the recognition results were analyzed and compared experimentally.

Palm print identification has been used in various applications in several years. Various methods have been proposed for providing biometric security through palm print authentication. One such a method was feature level fusion which used multiple feature extraction and gives higher accuracy. But it needed to design a new matcher and acquired many training samples. However, it cannot adapt to scenarios like multimodal biometric, regional fusion, contactless and complete direction representation. This problem will be overcome by score level fusion method. In this article, we propose a salient and discriminative descriptor learning method (SDDLM) and gray-level co-occurrence matrix (GLCM).The score values of SDDLM and GLCM are integrated using score level fusion to provide enhanced score. Experiments were conducted on IITD palm print V1 database. The combination of SDDLM AND GLCM methods will be useful in achieving higher performance. It provides good recognition rate and reduces computation burden.

Palmprint is a very unique and distinctive biometric trait because of features such as a person's inimitable principal lines, wrinkles, delta points, and minutiae. These constitute the main reasons why palmprint verification is considered as one of the most reliable personal identification methods. However, a clear majority of the research on palm-prints are concentrated on 2-D palmprint images irrespective of the fact that the human palm is a 3D-surface. While 2-D palmprint recognition has proved to be efficient in terms of verification rate, it has some essential downsides. These restrictions can adversely affect the performance and robustness of the palmprint recognition system. One of the possible solutions to resolve the limitations associated with 2-D palm print authentication systems is (i) to use a 3-D scanning system and to produce high quality 3-D images with depth information; (ii) to map 3-D palm-print images into 2-D images which may support the usage of 3-D images with both biometric palmprint 2-D image databases and 2-D palmprint recognition tools. The bloom of 3-D technologies has made it easier to capture and store 3-D images. The problem of a direct mapping approach is that a large section of the palm is hard-pressed on the scanner surface during 2-D based acquisition. This paper proposes a novel technique to unravel/map 3-D palm images to its equivalent 2-D palm-print image. This image can be then used to perform efficient and accurate 2-D identification/ verification. Experimental results and discussions will also be presented.

Person recognition by fusing palmprint and palm vein images based on "Laplacianpalm" representation

Palmprint has been widely used in personal recognition. To improve the performance of the existing palmprint recognition system, multispectral palmprint recognition system has been proposed and designed. This paper presents a method of representing the multispectral palmprint images by quaternion and extracting features using the quaternion principal components analysis (QPCA) to achieve better performance in recognition. A data acquisition device is employed to capture the palmprint images under Red, Green, Blue and near-infrared (NIR) illuminations in less than 1s. QPCA is used to extract features of multispectral palmprint images. The dissimilarity between two palmprint images is measured by the Euclidean distance. The experiment shows that a higher recognition rate can be achieved when we use QPCA. Given 3000 testing samples from 500 palms, the best GAR is 98.13%.

C-Organic is an important component of soil fertility. The intensity of agricultural land use affects the organic matter content in the soil. A spectrometer can be used to measure organic matter content through reflectance values. This study aimed to compare reflectance values and C-Organic content in rice fields with planting Index (IP) of 100 and IP of 300 in Maros Regency, as well as to analyze the relationship between reflectance values and laboratory test results. The method used involved collecting soil samples from both types of rice fields, measuring reflectance using a spectrometer in the Blue, Green, Red, and NIR spectra, and analyzing their relationship with C-Organic content. The results showed that reflectance values and C-Organic content in 300 IP were higher than in 100 IP, with the highest coefficient of determination (R²) was in red spectrum, i.e. 0.9425. The C-Organic content at the research field was classified as very low, ranging from 0.61 to 1.05%, with a higher average in 300 IP (0.96%) compared to 100 IP (0.74%). This study concluded that a spectrometer can be a fast and accurate alternative for detecting soil C-Organic content, especially at a wavelength of 650 nm.

We propose ‘Contour Code’, a novel representation and binary hash table encoding for multispectral palmprint recognition. We first present a reliable technique for the extraction of a region of interest (ROI) from palm images acquired with non-contact sensors. The Contour Code representation is then derived from the Nonsubsampled Contourlet Transform. A uniscale pyramidal filter is convolved with the ROI followed by the application of a directional filter bank. The dominant directional subband establishes the orientation at each pixel and the index corresponding to this subband is encoded in the Contour Code representation. Unlike existing representations which extract orientation features directly from the palm images, the Contour Code uses a two stage filtering to extract robust orientation features. The Contour Code is binarized into an efficient hash table structure that only requires indexing and summation operations for simultaneous one-to-many matching with an embedded score level fusion of multiple bands. We quantitatively evaluate the accuracy of the ROI extraction by comparison with a manually produced ground truth. Multispectral palmprint verification results on the PolyU and CASIA databases show that the Contour Code achieves an EER reduction upto 50%, compared to state-of-the-art methods.

Superior voice recognition in a patient with acquired prosopagnosia and object agnosia

Automatic palmprint identification has received much attention in security applications and law enforcement. The performance of a palmprint identification system is improved by means of feature extraction and classification. Feature extraction methods such as Subspace learning are highly sensitive to the rotation variances, translation and illumination in image identification. Thus, Histogram of Oriented Lines (HOL) has not obtained promising performance for palmprint recognition so far. In this paper, we propose a new descriptor of palmprint named Improved Histogram of Oriented Lines (IHOL), which is an alternative of HOL. Improved HOL is not very sensitive to changes of translation and illumination, and has the robustness against small transformations whereas the small translation and rotations make no change in histogram value adjustment of the proposed work. The experiment results show that based on IHOL, with Principal Component Analysis (PCA) subspace learning can achieve high recognition rates. The proposed method (IHOL-Cosine distance) improves 1.30% on PolyU I database, and similarly (IHOL-Euclidean distance) improves 2.36% on COEP database compared with existing HOL method.

A Multi-biometric System amalgamates the evidences collected from the multiple sources or single source for person recognition based on templates like fingerprint, palm print and iris. These evidences can be combined at various levels like pixel level, score level, feature level, and decision level. A rich set of information is present at feature level, but there is a problem of dimensionality which affects the recognition system. This study focuses on a dimensionality reduction technique Principal Component Analysis (PCA), which reduces the feature vector after feature level fusion in three different multi-biometric systems. The Pre and Post analysis of reduction compares the size of feature vector and recognition time per template in the following systems. Fingerprint based recognition where two evidences like bifurcations and ridge endings are fused, palmprint recognition where 2D-Gabor and Log-Gabor features are concatenated, and Iris Recognition in which Log-Gabor and 2D-Gabor features are integrated. And also Performance of the system is evaluated Based on False Acceptance Rate and False Rejection Rate. The study has been carried out on FVC 2004 fingerprint, IIT Delhi palmprint, and IIT Delhi Iris datasets. The results have shown that a drastic improvement in the multimodal system performance after reduction in all metrics.

Background: A large category of evidence has the potential to suggest the dynamic events in crime scenes such as directionality, movement of the crime operators, leaving body fluids and many other impression evidence. Impression evidence such as footprints, fingerprints, and hand prints forms valuable physical evidence to determine stature, gender and living body weight, followed by person identification. Aim: The present study aimed to determine stature from hand print anthropometry among Indians of Malaysia. Methodology and result: The study recruited 100 males and 100 females of Malaysian Indians and collected hand prints and stature measurements following my earlier research. The data were analysed statistically and derived regression formulae to determine stature from various handprint measurements. There is a strong relationship exists between stature and palm print in the present study population. The correlation coefficient value is higher in the right middle& index handprint (R = 0.545) of males while the R-value of right-hand index handprint length is higher (0.643) in females. Conclusion: The research finally concluded with the creation of population-specific regression formulae to determine stature from handprint lengths among Indians of Malaysia for person identification.

Biometric authentication is a security procedure used to verify a person's identity, based on his or her unique physical characteristics. It is used to control access to both physical and digital resources, such as organizations, rooms, and different gadgets. Multiple biometric authentication systems use more than one physiological feature of an individual for the purpose of identification and verification and they are a superior solution for every industry that demands higher accuracy as well as security. This method proposes a contact less multiple biometric authentication system which uses palm print and hand geometry features. A temperature sensor is integrated in this system for detecting elevated body temperatures. A high body temperature or fever is related to many diseases and can be a first indicator whether a person is healthy or not. Using the SIFT (Scale Invariant Feature Transform) algorithm, this design achieves robust local feature detection and extraction in an image.

Because of their high recognition rates, coding-based approaches that use multispectral palmprint images have become one of the most popular palmprint recognition methods. This paper describes a new multispectral palmprint recognition method that aims to further improve the performance of coding-based approaches by focusing on the local binary pattern (LBP) filters and spiral moments features. The final feature map is derived through a staged process of creating a composite of spiral and LBP features by fusing them together and passing the features through the minimum redundancy maximum relevance transformers. Using Hamming distances, the inter- and intra-similarities of the palmprint feature maps are determined. The experimental technique was evaluated using the available data on the IITD, MSPolyU and PolyU PPDB databases. The results indicate that the method achieved high levels of accuracy in the identification and verification modes. Furthermore, this method outperforms the existing advanced techniques.

Biometrics based individual identification is observed as an effective technique for automatically knowing, with a high confidence a person's identity. Multi-modal biometric systems consolidate the evidence accessible by multiple biometric sources and normally better recognition performance associate to system based on a single biometric modality.Multi biometric systems are used to overcome this issue by providing multiple pieces of indication of the same identity. This system provides effective fusion structure that combines information provided by the multiple field experts based on decision-level and score-level fusion method, thereby increasing the efficiency which is not conceivable in uni-modal system.Multi-modal biometrics can be attained through a fusion of two or more images, where the subsequent fused image will be more protected. This paper discusses various fusion techniques, architecture of multi-modal biometric authentication and working of biometric fusion i.e. Iris and Fingerprint recognition that are used in multi-modal biometrics.