# I. Introduction long of various biometrics techniques , In the past few decades, human-beings have been addicted to various technologies such as captured photos, scanned signatures, bar code systems, verification Id & so on. Also, Biometrics is one of the applications in Image processing. Biometrics refers to technologies that measure and analyze human body characteristics for the user authentication. The biometric authentication system based on two modes: Enrolment and Recognition. In the enrolment mode, the biometric data is acquired from the sensor and stored in a database along with the person's identity for the recognition. In the recognition mode, the biometric data is re-acquired from the sensor and compared to the stored data to determine the user identity. Biometric recognition based on uniqueness and permanence. The uniqueness means that there is no similarity of feature between two different biometrics data. For example, there are no two humans having the same fingerprint feature even if they are twins. And when the features of biometrics do not change over the lifetime or aging, it is called permanence. Biometrics can have physiological or behavioural characteristics. The physiological characteristics are included in the physical part of body such as (fingerprint, palm print, iris, face, DNA, hand geometry, retina... etc). The behavioral characteristics are based on an action taken by a person such as (Voice recognition, keystroke-scan, and signature-scan). # II. Biometric Modalities a) Fingerprint The fingertip surface consists of ridges and valleys. The ridge declare as black lines and the valleys declare as white lines Fig. 1 .The minutiae points are the points where the ridge structure changes such as bifurcation and end point The human palm means the inner area between the fingers and wrist. The area of palm print compared to fingerprint is much larger, and then it can extract more features than a fingerprint. The palm print is similar to the fingerprint in ridges and valleys but the palm has also principle lines and wrinkles which can be acquired with a lower resolution scanner. # c) Face Face recognition is the popular way for the humans to recognize each other. The face is the front part of a head from chin to the forehead. Face recognition can be used in surveillance application because the face is one of the few biometric traits that can be recognized by people at distance [1]. # d) Iris Iris means a ring-shaped behind the cornea of the eye. The iris is very difficult to use after death because it's one of the first parts of the body to decay after death. Also the right iris is different from the left iris. # A e) Retina Retina is the layer of blood vessels which is located on the back of the eye. It is one of most secure in Biometrics because it is not easy to change or replicate the retinal vasculature. # f) Hand geometry Hand geometry recognition measures the size and shape of palm, and length and width of fingers. The merits are easy to use, technique is very simple. The demerit of hand geometry is that it can't be embedded to small devices like laptops, because the hand geometry sensor is large. Therefore, the hand geometry is suitable for verification only. # g) Voice Voice Recognition is the task of recognizing people from their voices. It is a combination of behavior and physical biometrics. The physical features of voice are vocal tracts, mouth, nasal cavities, and lips which used to create the voices h) Gait Gait is the way of walking. Gait Biometrics can be used in surveillance application because it can be recognised at a distance. # i) Signature Signature is a type of behavior biometrics and it can be changed by the person. The biometric system identifies the signature from the way of holding the pen and the time taken to sign. Also, it can be online or offline. # j) Keystroke Keystroke is the way of typing on the keyboard. Most people have different ways to deal with the keyboard but this type of biometrics cannot be based for security accessing, thus it can be used after a strong biometrics for verification only 1:1. k) DNA DNA refers to deoxyribonucleic acid. This type of biometric is used in crime investigation. The identical twins have the same DNA pattern. # III. # Fingerprint Fingerprints are graphical patterns of ridges and valleys on the surface of fingertips , the ridge ending and ridge bifurcation is called minutiae as shown in fig. 2. There are many methods based on minutiaebased fingerprint representation were proposed in [1], [2] . Every person has a unique fingerprint from any other person. The fingerprint identification is based on two basic assumptions:-Invariance and Singularity Invariance : means the fingerprint characteristics do not change along the life. Singularity: means the fingerprint is unique and no two persons have the same pattern of fingerprint. The angle between the horizontal and the direction of the ridge. 6 Bifurcation Angle The angle between the horizontal and the direction of the valley ending between the bifurcations. 7 Matching Score it is used to calculate the matching score between the input and template data 8 False Non Matching Ratio It is the probability that the system denies access to an approved user. The main stages of fingerprint recognition system are shown in fig. The Image Acquisition stage is the process to obtain images by different ways. There are two ways to capture fingerprint image; online and offline. In the online fingerprint identification the optical fingerprint reader is used to capture the image of fingerprint. The size of fingerprint image will be 260*300 pixels. The offline fingerprint identification is obtained by ink in the area of finger and then put a sheet of white paper on the fingerprint and finally scans the paper to get a digital image. # b) Image Pre-processing Stage The pre-processing stage is the process of removing unwanted data in the fingerprint image such as noise, reflection.etc. The fingerprint image preprocessing is used to increase the clarity of ridge structure. There are many steps for doing this process such as Image Segmentation, Binarization, Elimination of noise ,smoothing and thinning. The propose of all these steps is to enhanced fingerprint image at the time of enrolment. In [3],in addition to Gaussian filter, Short Time Fourier Transform (STFT) analysis is adopted to enhance fingerprint image quality. Sometimes the binarized fingerprint image contains a number of false minutiae. In [4].a detailed pre -processing is mentioned to remove false minutiae. Jiao Ruili et. al., [5] proposed an automatic fingerprint acquisition and pre-processing system with a fixed point DSP, TMS320VC5509A and a fingerprint sensor, MBF200. The system is diminutive and flexible. The author presents a VC5509A based fingerprint pre-processing system, accomplished fingerprint image acquisition. The pre-processing system is accomplished with the properly selected algorithm on a DSP platform. Comparing the results of the algorithms, appropriate algorithms are selected for fingerprint identification pre-processing. They are Median Filtering, Directional Filtering Enhancement, Fixed Threshold Binarization, and Hilditch Thinning. Yun and Cho [6] proposed an adaptive pre-processing method, which extracts five features from the fingerprint images, analyses image quality with clustering method, and enhances the images according to their characteristics. The pre-processing is performed after distinguishing the fingerprint image quality according to its characteristics. The Table show the some recent research of pre-processing. The feature extraction process of fingerprint image applied on the output of pre-processing stage. The process of feature extraction depends on set of algorithms; A fingerprint feature extraction program is to locate, measure and encode ridge endings and bifurcations in the fingerprint. For extracting the features from the fingerprint image, a popular method is minutiae extraction. Minutiae extraction algorithm will find out the minute points from the fingerprint and then map their relative placement on the finger. There are two types of minutiae points: Ridge ending and Ridge bifurcation [7]. In [8] an advanced fingerprint feature extraction method is introduced through which minutiae are extracted directly from original gray-level fingerprint images without binarization and thinning. Gabor filter bank can also be used to extract features from fingerprint [9]. Afsar et. al., [10] presented the minutiae based Automatic Fingerprint Identification Systems. The technique is based on the extraction of minutiae from the thinned, binarized and segmented version of a fingerprint image. The system uses fingerprint classification for indexing during fingerprint matching. Zebbiche and Khelifi [11] presented biometric images as one Region of Interest (ROI). The scheme consists of embedding the watermark into ROI in fingerprint images. Discrete Wavelet Transform and Discrete Fourier Transform are used for the proposed algorithm. Yi Chen and Anil K Jain [12] proposed an algorithm based on fingerprint features viz., minutiae and ridges, Pattern and Pores. The correlation among Fingerprint features and their distributions are considered for the model. Tachaphetpiboont and Amornraksa [13] proposes a feature extraction method based on FFT for the fingerprint matching. The recognition rate obtained from the proposed method is also evaluated by the k-NN classifier. The amount of time required for the extraction and verification is very less in this approach. The matching stage is the process to compare the acquired feature with the template in the database ..In other words the process of matching stage is to calculate the degree of similarity between the input test image(for user when he wants to prove his/her identity)and a training image from database (the template which created at the time of enrolment).Matching can be done in three methods: hierarchical approach which employs simple but computationally effective features to retrieve a subset of templates in a given database. This approach increases matching speed at the cost of accuracy [14], classification: Classification approaches assign a class to each biometric in a database. There are many classification methods including KNN classifier [15].and Coding approaches will use one matching function to search entire databases. Arun Ross et. al., [16] proposed the hybrid fingerprint matcher which employs the combination of ridge strengths and a set of minutiae points. Johg Ku Kum et. al., [17] presented a study on Hybrid fingerprint matching methods. The minutiae and image based fingerprints verification methods are implemented together. The shapes in the fingerprint such as square, diamond, cross and dispersed cross are used for matching. Swapnali Mahadik et. al., [18] described an Alignment based Minutiae Matching algorithm. The minutiae extraction involves Filtering, Binarization, Orientation Estimation, Region of interest, Thinning and Minutiae Extraction. In the matching stage the images are subjected to translation Rotation and Scaling. Anil Jain et. al., [19] described the use of logistic regression method to integrate multiple fingerprint matching algorithms. The integration of Hough transform based matching, string distance based matching and 2D dynamic programming based matching using the logistic regression has minimized the False Rejection Rate for a specified level of False Acceptance Ratio. Aparecido Nilcau Marana and Jain [20] proposed Ridge Based Fingerprint matching using the Hough transform. The major straight lines that match the fingerprint ridges are used to estimate rotation and translation parameters. # Global Journal of Computer Science and Technology Volume XVI Issue II Version I 1996 Hough transform-based approaches ----------- [77] 1997 Ridge-based relative pre-alignment ----------- [67] 2004 Minutiae matching THU [78] 2005 Global matching of clusters of minutiae ----------- [68] 2006 Invariant moment finger Code and LVQ FVC2002 [80] 2006 Global minutiae matching with image correlation ---------- [69] 2007 Minutiae matching, vector matching ,weight modification and local area matching process FVC2002 [70] 2008 Minutiae matching, which find the similartiy between two images and by calculating the correlation between these images. -------- [83] 2009 Global matching by evolutionary algorithms -------- [82] 2010 Weighted global matching with adjustment of scores -------- [81] 2012 Orientation image-based relative pre-alignment -------- [71] 2013 LDP and SLFNN FVC2002 [79] 2013 Hierarchical and/or multilevel minutiae matching -------- [73] 2007 Minutiae matching, RMI and Fuzzy operator -------- [74] 2012 ELM and R-ELM FVC2002 # IV. Palm Print The palm used in fortune telling 3000 years ago, but in 1998 Wei and David [21] studied the palm print as personal identification and it became one type of physical biometrics. Wei and David found that the features of palm print are geometry, principle lines (life, heart and head), wrinkle, delta point and minutiae. No two humans' palms are identical. The space of palm is greater than the fingerprint space so the palm had more information than a fingerprint. The palmprint is to contain principal lines and wrinkles in addition to pattern of ridges and valleys similar to fingerprints. The principle lines and wrinkles can be captured by a lower resolution sensor fig. 4 (b),whereas the ridges and valleys in palm are captured by high resolution . The ridges are shown as dark lines; and the valleys are the white lines between those black lines. The minutiae are the points where the ridges changed such as bifurcation and endpoint. The area of palm print is larger than the fingerprint area, then the number of minutes in a palm print around ten times the minutes in a fingerprint [22]. The palm can be captured from normal scanners. There are four types of devices that can capture the palm: CCD-based palmprint scanner, digital camera, digital scanner and video camera. The offline palmprint identification obtaines images by ink the area of palm and then put a sheet of white paper on the palm and then scans the paper to get a digital image [23]. Zhang et al [24] were the first research team to develop online palmprint identification (CCD-based palmprint scanner) and it captured high quality palmprint image. The CCD-based palmprint scanner is depended on the lens, camera and the light sources fig. 6. [24] presented the Gaussian smoothing for the original image of palmprint, then transformed it into binary image. After that it used the boundary tracing algorithm for detect the edges, then computed the tangent between the two gaps of fingers to get the Y-axis and finally extracted a sub image of a fixed size based on coordinate system. However, in [25] it cropped the area of fingers to reduce the time of compute the tangent, and enhance the ROI to extend the gray scope into 256 to make the lines clear for feature extraction. C. C. Han et al [26] applied to full palmprint images (scanner image) , it used the border tracing algorithm after convert the image into binary image, then located the five fingers tips and four fingers roots by used wavelet based segmentation, and from the ring fingers points are establish the coordinate of ROI. K. Chuang et al. [27] applied the opening morphology operation for removing the noise of binary image of palm print, and then shrink the region of palm print image by segmented a rectangular region bounded by four lines: upper and lower bound should less than 200 white pixels, right and left bound should be less than 95 white pixels. It detected the boundary by using Sobel edge detection. Then, it took a double derivation of palm boundary to locate three points between the fingers. Next, it created a line by connecting the two points in the upper curve and lower curve, and this line used to align the difference palm print image. It created a point in the middle of the align line M. This point with the middle curve point used to establish the central point of coordinate of ROI. In case of offline palm print image, no need for binarizing the palm print image because it is already black and white. R. Wang et. al. [28] utilized Gaussian filter to remove the noise from the palm print image, and then used canny edge detection and convex hull to detected the end points of heart line and life line (datum points). # Global Journal of Computer Science and Technology Volume XVI Issue II Version I The feature extraction applied on the output of pre-processing phase which is a fixed size of image. And extract the feature of palm like principle lines, wrinkles and minutiae, and each feature belongs to a different resolution. Wei and Zhang [29] extracted the datum points and the line features from the palm print image. The datum points are defined as the points of palm print registration. Therefore, it detected the principle lines and their endpoints by using the directional projection algorithm. Moreover, the authors have improved template algorithm to extract the ridges and wrinkles as straight lines. D. Zhang et al. [24] since the stack filter algorithm is able to extract the principle lines of palm print, but the principle lines are not sufficient to prove the uniqueness of palm print. Thus, the author's proposed the 2D Gabor to represent the palm print for extracting the texture features of palm print from lowresolution. J. Gan and D. Zhou [25] decomposed the palm print image into sub-images by using the 2-dimensional multi-scale wavelet, then four images are obtained; one of those sub-images is the approximation image for lowfrequency components, and the rest of sub-images are demonstrated for the high-frequency component. After that, segment each wavelet sub-image into ?? 2 blocks C. C. Han et al [26] applied four directions of Sobel operators to extract the feature points of ROI of palm print, and then applied a complex morphology operator to extract the features of palm print image. Yao et al. [30] proposed Gabor transformation to extract the texture of palm print features which divided the palm print image into 32 regions. And it was used eight direction (0, ??/8, ??/4,3??/8, ??/2,5??/8,3??/4,7??/8) and four scales (2,4,8,16) 8*4=32 regions to obtain the image texture characteristics. Then it was resized the domination of Gabor image into 1/16 of original image. After that, researchers used ICA (Independent Compo nent Analysis) for further extracted features. The matching stage is to compare the acquired feature with the template in the database. In [29] proposed the Euclidean distances to match between the endpoints of two lines. And computed the three parameters (slope, intercept and angle) of each line segmented in the two palm print images and decided whether the two lines are equal or not. But in [31] it utilized the energy difference and Hausdroff distance to match between the two palms features. Gan and Zhou [25] the matching based on Euclidean distance between feature vectors and NND (Nearest Neighbour Distance) rule. D. Zhang et al. [24] determined the similarity measurement of two palm print by using the Humming distance. And in [26] authors proposed two verification mechanisms, one is the correlation function to measure the similarity between the two feature vectors, and the second is Back propagation neural network (BPNN) with the scaled conjugate-gradient algorithm. Also, researchers in [30] identified the weight features by BBNN. X.Y Jing and D. Zhang [32] took the first five samples of each individual in database as training samples and the reminders as test samples, and then the number of training and testing will be 950 training and 2090 testing. The first twenty low frequency bands are selected. Thus, the principle components are 210 and it obtained 181 discrimination vectors. In this paper the result of the recognition accuracy is 98.13%. Year 2016 ( ) F d) Matching # It contains pattern of ridges and Valleys It contains pattern of ridges and Valleys also it contains additional features such as principal lines, wrinkles, dathm points. # 2. It is difficult to be captured even with the lower resolution scanner. It is easy to be captured even with a lower resolution scanner. # 3. Both deal with the some problems like noisy data, Non-universality, intra-class variations, spoof attack.etc. # 4. The area of finger is less. The area of palm is much large in comparison to finger. # 5. It is less distinctive It is more distinctive. V. # Multi-Modal The multimodal biometrics combine more than one modalities of biometrics to improve the recognition accuracy [37]. The recognition system which acquires biometric information from many sources for the same person in order to determine the identity of a person known as multi-biometrics system. Any piece of evidence can be independently used to recognize a person is called a source of biometric information [38]. Biometric systems are becoming popular as measures to identify human being by measuring one's physiological or behavioral characteristics. The multimodal biometric systems provide advantage over the conventional Unimodal biometric systems in various ways [39]. The main goals of multi-modal biometrics are to reduce at least one of the following; FAR (False Accept Rate), FRR (False Reject Rate), FTE (Failure To Enrollment rate) and Susceptibility to artifacts or mimics. But it also increases sensor cost, enrollment time, transit time and system development [37,39].Multimodal biometric system acquires the input from one or more sensors measuring two or more different modalities of biometric characteristics. # VI. [30] Proposed two steps for fusion the palm print and face feature at the feature level: firstly, since the huge difference between the face and palm then it normalized their features as certain range. Secondly, utilized User-specific weighting rule, where the weights of palm print are varies from 0.1 to 0.9, and the weights of face are varies from 0.9 to 0.1. Then selected the weight based on the highest recognition rate of all pairs weights of palm print and face varies weight. In [33] proposed fusion of face and palm print at the four levels and each level had difference techniques: at the sensor level used wavelets based image fusion scheme, at the feature level used few normalization techniques, at the score level used a some rules of fusion such as sum, max and min rule to combine the matching score, finally at the score level used a logical AND & OR operators. raw biometric data (e.g., a face image) acquired from an individual represents the richest source of information although it is expected to be contaminated by noise (e.g., non-uniform illumination, background clutter, etc.). Sensor level fusion refers to the consolidation of (a) raw data obtained using multiple sensors, or (b) multiple snapshots of a biometric using a single sensor. ii. Feature-level fusion In feature-level fusion, the feature sets originating from multiple biometric algorithms are consolidated into a single feature set by the application of appropriate feature normalization, transformation and reduction schemes. The primary benefit of feature-level fusion is the detection of correlated feature values generated by different biometric algorithms and, in the process, identifying a salient set of features that can improve recognition accuracy. Eliciting this feature set typically requires the use of dimensionality reduction methods and, therefore, feature-level fusion assumes the availability of a large number of training data. Also, the feature sets being fused are typically expected to reside in commensurate vector space in order to permit the application of a suitable matching technique upon consolidating the feature sets. iii. Score-level fusion In score-level fusion the match scores output by multiple biometric matchers are combined to generate a new match score (a scalar) that can be subsequently used by the verification or identification modules for rendering an identity decision. Fusion at this level is the most commonly discussed approach in the biometric literature primarily due to the ease of accessing and processing match scores (compared to the raw biometric data or the feature set extracted from the data). Fusion methods at this level can be broadly classified into three categories: density-based schemes [56], transformation-based schemes [58] and classifier based schemes. The fig 8 .show levels of fusions. # iv. Decision-level fusion Many commercial off-the-shelf (COTS) biometric matchers provide access only to the final recognition decision. When such COTS matchers are used to build a multi biometric system, only decision level fusion is feasible. Methods proposed in the literature for decision level fusion include "AND" and "OR" rules [57], majority voting weighted majority voting, Bayesian decision fusion the Dumpster-Shafer theory of evidence and behavior knowledge space [59]. BBNN for recognition the fusion [33] Face & palmprint All levels ----------------- [35] Face & palmprint Feature level ------------------- [36] Palmprint & fingerprint Feature level Fuzzy vault -------- Fingerprint and voice Match score Functional link network [53] Many researches for person verification using multi biometrics with decision fusion traits are done. Table10 : Summarized most important researches [55] Researcher /Year Multibiometric traits Algorithm Arun R., et al /2004 # Information fusion in biometrics The research used score level fusion multibiometrics system by combining three traits(face, fingerprint and hand geometry) are presented, using compare for the feature extraction in each single traits [5] Rajiv The researchers applied palmprint and hand geometry over other biometric modalities. It implemented particle swarm based optimization technique for selecting optimal parameters through decision level fusion of two modalities: palmprint and hand geometry [42]. # Global Journal of Computer Science and Technology Volume XVI Issue II Version I This research applied likelihood ratio-based score fusion and Bayesian approach for consolidating ranks and a hybrid scheme that utilizes both ranks and scores to perform fusion in identification systems [43]. # Giot R., et al /2010 Fast Learning For Multibiometrics Systems Using Genetic Algorithms This research use algorithm to learn the parameters of different multibiometrics fusion functions. It interested in biometric systems usable on any computer (they do not require specific material). In order to improve the speed of the learning, we defined a fitness function based on a fast ERR, FAR and GAR also, the search calculate the time that required to recognition the person [12] It presents a feature level fusion algorithm based on texture features. The system combines fingerprint, face and off-line signature. Texture features are extracted from Curvelet transform. The Curvelet feature dimension is selected based on d-prime number [45]. # VII. Conclusions This paper gave an overview of the fingerprint and palm print recognition . We highlighted in details the fingerprint and palm separately. We also referred to the image acquisition stage , image pre-processing stage, feature extraction stage and matching stage for recognition purpose in details. In addition to that we introduced some techniques for both modalities .Also ,we gave an elaboration about multimodal biometric system recognition and the fusion of biometric trait. 1![Figure 1 : Graphical of ridge and valleys Ridge Ending, Bifurcation and short Ridge[14] b) Palm Print](image-2.png "Figure 1 :") 2![Figure 2 : Fingerprint image showing different ridge features](image-3.png "Figure 2 :") 3![](image-4.png "3") 3![Figure 3 : Fundamental Steps of Fingerprint Recognition System a) Image Capture or Image Acquisition stage](image-5.png "Figure 3 :") 4![Figure 4 : (a) CCD-based palm print image, (b) ROI, ridges and valleys of palm The palm print system recognition consists of four parts as shown in fig.5](image-6.png "Figure 4 :") 5![Figure 5 : Palm print recognition system a) Image Acquisition](image-7.png "Figure 5 :") 67![Figure 6 : Diagram of the palm print captured devices CCD [24]](image-8.png "Figure 6 :Figure 7 :") ![a) Levels of Fusion i. Sensor-level fusion Global Journal of Computer Science and Technology Volume XVI Issue II Version I Recognition System based on Fusion of Fingerprint and PalmPrint: A Review](image-9.png "") 8![Figure 8 : Levels of fusions in biometric system](image-10.png "Figure 8 :") 9![Figure 9 : Fusion Methods[59]](image-11.png "Figure 9 :") 2RefYearPre-processingDatabase[67]2004Orintation field :Modal-based method, region segmention, orientation filed, ridge enhancementTHU[68]2006Hierarchical Discrete wavelet Transformation(DWT)FVC2002[69]2007Gabor filters, mask estimation, Binarization, ThinnigFVC2002[70]2008Minutiae feature by using CNN[71]2013Normalization, Ridge segmention, Ridge orintation Core point detection.FVC2002[74]2012Enhancement using two stage determination of reference point and determination of ROIFVC2002[73]2007Gray scale image, binarization------[84]2013Gabor filter and FFT, Normalization, local orientation, local frequency, region mask, filter, BinarizationFVC2004c) Feature extraction stage 3RefYearFeature extractionDatabase[60]1992Orientation fieldNIST4[61]1996SingularitiesNIST4[62]1998Ridge structureNIST4[63]1999Singularities and ridgeNIST4[64]2001FingercodeNIST4[65]2002Ridge DistributionNIST4[66]2003Relational graph, fingercodeNIST4[67]2004Minutiae extractionTHU[68]2006Seven Invariant moment, fingercode, refrences pointFVC2002[69]2007Ridge ending and ridge bifurcationFVC2002[70]2008Minutiae feature by using CNNA dina2012Scale Invariant Feature Transformtion (SIFT)FVC2002[71]2013ROI,Compute LDP Code (local Directional pattern)FVC2002[72]2014Fixed length represntion that provide extract aligment between features.FVC2002/ FVC2004[74]2012Local and globle Invariant moment Feature and PCA for feature selectionFVC2002d) Matching stage 4RefYearMatchingDatabase[76] 5AuthorRemove noiseEdge detectionKey pointsnameD. Zhang et al. [24]Gaussian smoothing then BinarizingBoundary tracking algorithmGap fingers tangentK. Chuang et al. [27]Binarizing then opening operationSobel edge detectionDouble derivation and get 3 points between fingersC. C. Han et al [26]Binarizing by using threshold histogramBorder tracing algorithmWavelet to locate the five fingers tips and four fingers rootR. Wang et. al.[28]Gaussian filterCanny edge detectionConvex hull to detect the end points of heart line and life linec) Feature Extraction 6RefFeature basedFeature extractionMatching techniqueDatabaseno[29]Straight linesDirectional projectionEuclidian distanceOffline, 200 samplesalgorithm[31]Texture & feature points--------Hausdroff distance Energy different &Offline, 200 samples[24]Lines & texturesStack filter& 2DHumming distanceOnline, 193*40 samplesGabor[33]TexturesLPQ--------PolyU 189*20[26]Lines featureSobel operator & morphologyCorrelation function & BPNN--------[25]Features vectorMulti-scale waveletEuclidean distance &Online, 100*60 samplesNND rules[30]TextureGabor transformation &BPNN50*10 samplesICA[34]Orientation featuresSix Gabor filter on diff directionHumming distance--------[32]Discriminant DCTImprove Fisher PalmNeural networkOnline 190*16 samplesfeaturesmethod 7NoFingerprintPalm print1. 8RefBiometrics modalitiesFusion level TechniquesNotes[30]Face & palmprintfeature levelWeightingrules 9ModalityLevel of FusionFusion StrategiesAuthorsPalmprint and FaceMatching LevelSum of Score[40]Fingerprint and FaceScore and DecisionSum Rule and Likelihoods[41]Face, Fingerprint, andMatching LevelSum Rule[42]Hand GeometryFingerprint and Hand-Combination ApproachSum, Max, Min Scores[43]GeometryFingerprint, Palmprint,Feature LevelANN[44]and Hand-GeometryFace and FingerprintMatching LevelSum, Min-Max, and Zscore[44]Face and palmprintFeatureFeature concatenation[ 45]Fingerprint and signatureMatch scoreSVM in which quality measures[46]are incorporatedFace and fingerprintMatch ScoreProduct rule[47]Face, fingerprint andMatch ScoreLikelihood ratio[48]voiceFace, fingerprint andMatch ScoreSum rule; decision trees; linear[ 49]hand geometrydiscriminant functionFace and fingerprintMatch ScoreSum rule, Weighted sum rule[50]Fingerprint, handMatch scoreWeighted sum rule[51]geometry and voiceFingerprint andMatch scoreReduced multivariate[52]hand geometrypolynomial model .J, etMultimodalal /2006BiometricusingFace, Iris, palmprintandSignatureFeaturesKumar, A,Fusion of Handet al. /2008Based BiometricsusingParticleSwarm optimization © 2016 Global Journals Inc. (US) * A real-time matching system for large fingerprint data bases NKRatha KKaru SChen AKJain IEEE Trans. Pattern Anal.Mach Intell 18 8 Aug.1996 * Online fingerprint verification KJain LHong IEEE Trans. Pattern Anal. Mach Intell 19 4 Apr.1997 * Combining fingerprint, palmprint and hand-shape for user authentication AKumar DZhang Pattern Recognition, 2006. ICPR 2006. 18th International Conference on IEEE 2006 4 * Preprocessing and post processing for skeleton-based fingerprint minutiae extraction FZhao XTang Pattern Recognition 40 2007. 2007 * VC5509A Based Fingerprint Identification Preprocessing System JiaoRuili FanJing International Conference on Signal Processing 2008 * Adaptive Fingerprint Image Enhancement with Fingerprint Image Quality Analysis EKYun SBCho International conference of Image and Vision Computing 2006 * A Multimodel Biometric Recognition System based on ADeshpande SPatil S MLathi R International Journal of Electronics and Computer Science Engineering -2277-1956 2012 * Preprocessing and post processing for skeleton-based finger print minutiae extraction FZhao XTang Pattern Recognition 40 4 2007 * A multichannel approach to fingerprint classification. Pattern Analysis and Machine Intelligence AKJain SPrabhakar LHong IEEE Transactions on 21 4 1999 * Fingerprint Identification and Verification System using Minutiae Matching FAAfsar MArif MHussain National Conference on Emerging Technologies 2004 * Region-Based Watermarking of Biometrics Images: Case Study in Fingerprint Images KZebbiche Khelifi Proceedings of International Journal of Digital Multimedia Broadcasting International Journal of Digital Multimedia Broadcasting 2008 * Beyond Minutiae: A Fingerprint Individuality Model with Patteren, Ridge and Pore Features YiChen A KJain International Conference on Biometrics 2009 * Applying FFT Features for Fingerprint Matching STachaphetpiboont Amornraksa Proceedings of the IEEE Conference on Wireless Pervasive Computing the IEEE Conference on Wireless Pervasive Computing 2006 * On hierarchical palmprint coding with multiple features for personal identification in large databases JYou WKKong DZhang KHCheung IEEE Transactions on Circuits and Systems for Video Technology 14 2 2004 * Fingerprint and palmprint Recognition Approach based on Multiple Feature extraction RGayathri PRamamoorthy European Journal of scientific research 76 4 2012 * A Hybrid Fingerprint Matcher ArunRoss AnilJain JamesReisman Proceedings of International Conference on Pattern Recognition International Conference on Pattern Recognition 2003 * A Study on the Performance Analysis of Hybrid Fingerprint Matching Methods Jong Ku Kin Seung -Hoon Chae, Sung Jin Lim and Sung Bum Pan 2008 * Access Control System using Fingerprint Recognition SwapnaliMahadik DNarayanan DarshanaBhoir Shah International Conference on Advances in Computing, Communication and Control 2009 * Combining Multiple Matchers for a High Security Fingerprint Verification System SA K Jain Prabhakar Chen Pattern Recognition Letters 20 1999 Elsevier Science Direct * Ridge-Based Fingerprint Matching using Hough Transform A KA N Marana Jain Proceedings of the IEEE Brazilliab Symposium on Computer Graphica and Image Processing the IEEE Brazilliab Symposium on Computer Graphica and Image Processing 2005 * automated personal identification by palmprint WShu DZhang SPIE [s0091-3286(98) 01908 -4 1998 * Karthik Nandakumar, "introduction to biometrics KAnil ArunAJain Ross Springer Sciences + Business Media, LLC, 233 Spring Street New York, NY 10013, USA July 2011 * DavidDZhang 2004 Springer science palmprint authentication * online palmprint identification DZhang WKong JYou MWong IEEE transactions on pattern analysis and machine intelligence Sep 2003 25 * a novel method for palmprint recognition based on wavelet transform JGan DZhou IEEE icsp 2006 proceedings 2006 * personal authentication using palmprint features CHan HCheng CLin KFan PERGAMON pattern recognition 36 2003 * a region of interest segmentation algorithm for palmprint images KChuang SLiu Zheng the 29th workshop on combinatorial mathematics and computation theory Taiwan Yi University of Technology * automatic region segmentation for high-resolution palmprint recognition: towards forensic scenarios RWang DRamos JFierrez RPKrish Spain ATVS-biometric recognition group, Universidad autonoma de Madrid(UAM) * two novel characteristics in palmprint verification: datum point invariance and line feature matching DZhang Shu PERGAMON pattern recognition 32 society published by Elsevier science 1999 * a novel user-specific face and palmprint feature level fusion YFu ZMa MQi JLi XLi YLu 987-0- 7695-3497-8/08 IEEE second international symposium on intelligent information technology application 2008 * hierarchical palmprint identification via multiple feature extraction JYou WLi DZhang PERGAMON pattern recognition 35 2002 * a face and palmprint recognition approach based on discriminant DCT feature extraction XYJing DZhang IEEE transaction on system, man, and cybernetics-part B: cybernetics 2004 2415 * Tow novel characteristics in palmprint verification: datum point invariance and line feature machine DZhang WShu pattern recognition 32 4 1999 * an online system of multispectral palm print verification DZhang GGuo LLu WZhang Zuo IEEE transaction on instrumentation and measurement 59 2 Feb 2010 * Communication Systems Networks and Digital Signal Processing (CSNDSP) MIAhmad WLWoo SSDlay 7th International Symposium on 2010. July 2010 Multimodal biometric fusion at feature level: Face and palmprint * multi-modal biometric template security: fingerprint and palmprint based fuzzy vault VEBrindha Nataajan 2012 OMICS publishing group * multimodal biometric identification for large user population using fingerprint, face and iris recognition TeddyKo IEEE Proceedings of the 34th Applied Imagery and Pattern Recognition Workshop (AIPR05) 2005 * Karthik Nandakumar, "introduction to biometrics KAnil ArunAJain Ross Springer Sciences + Business Media, LLC, 233 Spring Street New York,NY 10013, USA July 2011 * An Efficient Secure Multimodal Biometric Fusion Using Palm print and Face Image AshishMishra ; M MaheshPk MNShanmukhaswamy IJCSI International Journal of Computer Science Issues 3 4 june 2010. 2009 International journal of computer applications * Decision-level Fusion Strategies for Correlated Biometric Classifiers LisaKalyanveeramachaneni ArunrossOsadciw Nishasrinivas Biometric Authentication Springer 2004 * RohingovindarajanbArunross Feature Level Fusion Using Hand and Face Biometrics SPIE Conference on Biometric Technology for Human * Score normalization in multimodal biometric systems AnilJain KarthikNandakumara ArunRoss Pattern Recognition 38 2005. 18 January 2005 * Multibiometric Systems Based Verification Technique FarhatAnwar ArafaturRahman SaifulAzad European Journal of Scientific Research 1450-216X 34 2 2009 EuroJournals Publishing * Multimodal Biometrics: Issues in Design and Testing RobertSnelick MikeIndovina JamesYen AlanMink ACM 1-58113-621- 8/03/0011 November 5-7, 2003 Vancouver, British Columbia, Canada * When Faces are Combined with Palmprints: A Novel Biometric Fusion Strategy GFeng KDong DHu DZhang First International Conference on Biometric Authentication (ICBA) Hong Kong, China July 2004 * Discriminative Multimodal Biometric Authentication based on Quality Measures JFierrez-Aguilar JOrtega-Garcia JGonzalez-Rodriguez JBigun Pattern Recognition 38 5 May 2005 * Integrating Faces and Fingerprints for Personal Identification LHong AKJain IEEE Transactions on Pattern Analysis and Machine Intelligence 20 12 December 1998 * A Multimodal Biometric System using Fingerprint, Face and Speech KJain LHong YKulkarni Second International Conference on Audio and Video-based Biometric Person Authentication (AVBPA) USA March 1999 * A Hybrid Fingerprint Matcher AKRoss JJain Reisman Pattern Recognition 36 7 July 2003 * Large Scale Evaluation of Multimodal Biometric Authentication Using State-of-the-Art Systems RSnelick UUludag AMink MIndovina AKJain IEEE Transactions on Pattern Analysis and Machine Intelligence 27 3 March 2005 * Exploiting Global and Local Decisions for Multimodal Biometrics Verification K.-AToh XJiang W.-YYau IEEE Transactions on Signal Processing (Supplement on Secure Media) 52 10 October 2004 * Combining Fingerprint and Hand-Geometry Verification Decisions K.-AToh WXiong W.-YYau XJiang Fourth International Conference on Audio-and Video-based Biometric Person Authentication (AVBPA) Guildford, UK June 2003 * Fingerprint and Speaker Verification Decisions Fusion Using a Functional Link Network K.-AToh W.-YYau IEEE Transactions on Systems, Man, and Cybernetics, Part A: Applications and Reviews 35 3 August 2005 * Decision Level Fusion of Iris and Signature Biometrics for Personal Identification using Ant Colony Optimization IbrahimASaleh MLaheeb Alzoubiady (IJEIT) 3 11 May 2014 * On Combining Classifiers JKittler MHatef RP WDuin JMatas IEEE Trans. Pattern Analysis and Machine Intelligence 20 3 Mar. 1998 * Sheeps, Goats, Lambs and Wolves: A Statistical Analysis of Speaker Performance in the NIST 1998 Speaker Recognition Evaluation GDoddington WLiggett AMartin MPrzybocki DReynolds Proc. ICSLD 98 ICSLD 98 Nov. 1998 * Information fusion in biometrics ArunRoss AnilJain * Pattern Recognition Letters 24 2003 * Level of Fusion in Multimodal Biometrics: a Review GaganpreetDapinder February 2013 3 * Massively parallel neural network fingerprint classification system. National Institute of Standards and Technology CLWilson GTCandela PJGrother CIWatson RAWilkinson NISTIR 4880. 1992 * KKaru AJain Patt Recog 29 3 1996 Fingerprint classification * A hidden Markov model fingerprint classifier ASenior Conference record of the Thirty-First Asilomar Conference on Signals 1997 1 * Classification of fingerprint images LHong Jain Proceedings of the 11th Scandinavian Confere nce on Image Analysis the 11th Scandinavian Confere nce on Image AnalysisKangerlussuaq, Greenland June 1999 * Fingerprint classification with combinations of support vector machines YYao PFrasconi MPontil Proceedings of the 3rd International Conference on Audio and Video Based Biometric Person Authentication the 3rd International Conference on Audio and Video Based Biometric Person AuthenticationHalmstad, Sweden June 2001 * A new model for fingerprint classification by ridge distribution sequences JChang KFan Patt Recog 35 6 2002 * Combining flat and structured representations for fingerprint classification with recursive neural networks and support vector machines YYao GMarcialis MPontil PFrasconi FRoli Patt Recog 36 2 2003 * A model-based method for the computa tion of fingerprints' orientation field JinweiGu 10.1109/TIP.2003.822608 IEEE Transactions on Image Processing 13 2004 * Fingerprint Matching Using Invariant Moment FingerCode and Learning Vector Quantization Neural Network ; Jongbin Park; DongsunJuchengyang; Jinwook Shin; Bungjun Min Park DOI: 10.1109/ ICCIAS.2006.294231 IEEE Conference Publications on Computational Intelligence and Security 2006 * Wangyuan * YaoLixiu Zhou Fuqiang A Real Time Fingerprint Recognition System Based On Novel Fingerprint Matching Strategy 10.1109/ICEMI.2007.4350576 8th International Conference on Electronic Measurement and Instruments. ICEMI '07 2007 * A fully CNN based fingerprint recognition system RAbrishambaf Demirel ;Hasan IKale 10.1109/CNNA.2008.4588667 11th International Workshop on Cellular Neural Networks and Their Applications. CNNA 2008. IEEE Conference Publications 2008 * Local directional pattern (LDP) based fingerprint matching using SLFNN RKumar PChandra MHanmandlu 10.1109/ICIIP.2013.6707640 IEEE Second International Conference on Image Information Processing (ICIIP) Pages 2013 * Learning Minutiae Neighborhoods: A New Binary Representation for Matching Fingerprints AkhilVij AnoopNamboodiri 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops 2014 * Fingerprints Recognition Using Minutiae Extraction:a Fuzzy Approach AMontesanto PBaldassarri GVallesi GTascini 10.1109/ICIAP.2007.4362784 IEEE Conference Publications,14th International Conference on Image Analysis and Processing 2007. 2007 * Fingerprint matching based on extreme learning machine JuchengYang ShanjuanXie SookYoon DongsunPark ZhijunFang ShouyuanYang 10.1007/s00521-011-0806-0 DOI 10. 1007/s00521-011-0806-0 Neural comput & applic 22 2013. 2012 Springer-Verlag * A hierarchical hough transform for fingerprint matching TLiu HXia Li International Conference on Biometric Authentication (ICBA) Lecture 737 Notes in Computer Science Springer 2004 3072 * A real-time matching system for large fingerprint databases NKRatha KKaru SChen AKJain IEEE Trans. Pattern Anal. Mach. Intell 18 1996 * On-line fingerprint verification AKJain LHong RMBolle IEEE Trans. Pattern Anal. Mach. Intell 19 1997 * Fingerprint matching based on global alignment of multiple reference minutiae, Pattern Recogn EZhu JYin GZhang 2005 38 * Hierarchical minutiae matching for fingerprint and palmprint identification FChen XHuang JZhou IEEE Trans. Image Process 22 2013 * Fingerprint recognition using modelbased density map JWan Zhou IEEE Trans. Image Process 15 2006 * A method using long digital straight segments for fingerprint recognition XJiang XYou YYuan MGong Neurocomputing 77 2012 * Fingerprint matching using multi-dimensional ann RKumar BR DVikram Eng. Appl. Artif. Intell 23 2010 * Consensus fingerprint matching with genetically optimised approach, Pattern Recogn WSheng GHowells MFairhurst FDeravi KHarmer 2009 42 * Combining Gabor filter and FFT for fingerprint enhancement based on a regional adaption method and automatic segmentation MortezaZahedi RostamiOzra Ghadi 10.1007/s11760-013-0436-3 springer verlag london 2013,SIViP,DOI 1