Automatic Fingerprint Recognition System Research Articles

A novel intelligent 12-layer convolutional neural network model for gender classification using fingerprint images

Fingerprints are widely used as effective personal authentication systems, because they constitute unique, robust, and risk-free evidence. Fingerprinting techniques refer to biometric procedures used for identifying individuals based on their physical characteristics. A fingerprint image contains ridges and valleys forming a directionally-oriented pattern. The robustness of the fingerprint authentication technique determines the quality of the fingerprint image. This study proposed an intelligent 12-layered Convolutional Neural Network (CNN) model using Deep learning (DL) for gender determination based on fingerprints. Further, the study compared the performance of this model to existing state-of-the-art methods. The primary goal of this study was to reduce the number of comparisons within a large database obtained from automatic fingerprint recognition systems. The classification process was found to be swifter and more accurate when analysis of the DL algorithm was performed. With reference to the criteria of precision, recall, and accuracy evaluation during classification, this proposed 12-layered CNN model outperformed the Residual Neural Network with 50 Layers (ResNet-50) and Dense Convolutional Network with 201 Layers (DenseNet-201) models. The accuracies obtained were 97.0%, 95.8%, 98.0%, and 96.8% for female-left, female-right, male-left, and male-right classes respectively, while achieving an overall accuracy of 94.0%.

Sweat Gland Extraction From Optical Coherence Tomography Using Convolutional Neural Network

As the Level 3 features of fingerprint, sweat pores have attracted attention in the field of fingerprint recognition and have been successfully applied to automatic fingerprint recognition systems. Traditional surface sweat pores become unclear or disappeared when the finger is contaminated, dried, or damaged. These unstable factors create major challenges in collecting sweat pores. Subcutaneous sweat glands belong to the internal tissues of fingers, which are stable and immune to external disturbances. This study investigated the extraction of subcutaneous sweat glands from fingertip volume data collected by optical coherence tomography (OCT). First, an improved multitask V-Net is proposed to extract subcutaneous sweat glands from OCT volume data. The network has an encoding path for features extraction and two decoding paths for extracting sweat gland boundaries and regions, respectively. The multitask scheme is designed to enhance the boundary and shape information of sweat glands and to prevent false extraction caused by interference from other tissues. Second, three mapping methods are proposed to address the problem of different spatial orientations of sweat glands. These three mapping methods, namely, global direct mapping (GDM), local direct mapping (LDM), and cylindrical fitting mapping (CFM), are used to map sweat glands to the surface fingerprint. Experiments are conducted in terms of sweat gland extraction, mapping, and matching. The qualitative and quantitative results show that the proposed network for sweat glands extraction outperforms other methods and that the LDM and CFM methods derive more accurate positions of sweat glands on the surface fingerprint than GDM. In the matching experiment, the equal error rate (EER) of dual-decoding V-Net (DDVN) reached 0.58%, which verified the recognition ability of sweat glands and the effectiveness of the proposed network.

Fingerprint Presentation Attack Detector Using Global-Local Model.

The vulnerability of automated fingerprint recognition systems (AFRSs) to presentation attacks (PAs) promotes the vigorous development of PA detection (PAD) technology. However, PAD methods have been limited by information loss and poor generalization ability, resulting in new PA materials and fingerprint sensors. This article thus proposes a global-local model-based PAD (RTK-PAD) method to overcome those limitations to some extent. The proposed method consists of three modules, called: 1) the global module; 2) the local module; and 3) the rethinking module. By adopting the cut-out-based global module, a global spoofness score predicted from nonlocal features of the entire fingerprint images can be achieved. While by using the texture in-painting-based local module, a local spoofness score predicted from fingerprint patches is obtained. The two modules are not independent but connected through our proposed rethinking module by localizing two discriminative patches for the local module based on the global spoofness score. Finally, the fusion spoofness score by averaging the global and local spoofness scores is used for PAD. Our experimental results evaluated on LivDet 2017 show that the proposed RTK-PAD can achieve an average classification error (ACE) of 2.28% and a true detection rate (TDR) of 91.19% when the false detection rate (FDR) equals 1.0%, which significantly outperformed the state-of-the-art methods by ~10% in terms of TDR (91.19% versus 80.74%).

Finger Print Authentication on Web-Services One Step to Next Security

The system that automatically identifies the anthropometric fingerprint is one of the systems that interact directly with the user, which every day will be provided with a diverse database. This requires the system to be optimized to handle the process to meet the needs of users such as fast processing time, almost absolute accuracy, no errors in the real process. Therefore, in this paper, we propose the application of machine learning methods to develop fingerprint classification algorithms based on the singularity feature. The goal of the paper is to reduce the number of comparisons in automatic fingerprint recognition systems with large databases. The combination of using computer vision algorithms in the image pre-processing stage increases the calculation time, improves the quality of the input images, making the process of feature extraction highly effective and the classification process fast and accurate. The classification results on 3 datasets with the criteria for Precision, Recall, Accuracy evaluation and ROC analysis of algorithms show that the Random Forest (RF) algorithm has the best accuracy (≥96.75%) on all 3 databases, Support Vector Machine (SVM) has the best results (≥95.5%).

Cross-Sensor Pore Detection in High-Resolution Fingerprint Images

With the emergence of high-resolution fingerprint sensors, there has been a lot of focus on level-3 fingerprint features, especially the pores, for the next generation automated fingerprint recognition systems (AFRS). Following the success of deep learning in various computer vision tasks, researchers have developed learning-based approaches for detection of pores in high-resolution fingerprint images. Generally, learning-based approaches provide better performance than hand-crafted feature-based approaches. However, domain adaptability of the existing learning-based pore detection methods has never been studied. In this paper, we study this aspect and propose an approach for pore detection in cross-sensor scenarios. For this purpose, we have generated an in-house 1000 dpi fingerprint dataset with ground truth pore coordinates (referred to as IITI-HRFP-GT), and evaluated the performance of the existing learning-based pore detection approaches. The core of the proposed approach for detection of pores in cross-sensor scenarios is DeepDomainPore, which is a residual learning-based convolutional neural network (CNN) trained for pore detection. The domain adaptability in DeepDomainPore is achieved by embedding a gradient reversal layer between the CNN and a domain classifier network. The proposed approach achieves state-of-the-art performance in a cross-sensor scenario involving public high-resolution fingerprint datasets with 88.12% true detection rate and 83.82% F-score.

A comparative study on handcrafted features v/s deep features for open-set fingerprint liveness detection

Abstract A fingerprint liveness detector is a pattern classifier that is used to distinguish a live finger from a fake (spoof) one in the context of an automated fingerprint recognition system. As liveness detectors or presentation attack detectors are vulnerable to presentation attacks, the security and reliability of fingerprint recognition are compromised. Presentation attack detection mechanisms rely on handcrafted or deep features to classify an image as live or spoof. In addition, to strengthen the security, fingerprint liveness detectors should be robust to presentation attacks fabricated using unknown fabrication materials or fingerprint sensors. In this paper, we conduct a comprehensive study on the impact of handcrafted and deep features from fingerprint images on the classification error rate of the fingerprint liveness detection task. We use LBP, LPQ and BSIF as handcrafted features and VGG-19 and Residual CNN as deep feature extractors for this study. As the problem is targeted as an open-set problem, the emphasis is on achieving better robustness and generalization capability. In our observation, handcrafted features outperformed their deep counterparts in two of the three cases under the within-dataset environment. In the cross-sensor environment, deep features obtained a better accuracy, and in the cross-dataset environment, handcrafted features obtained a lower classification error rate.

3D Fingerprint Recognition based on Ridge-Valley-Guided 3D Reconstruction and 3D Topology Polymer Feature Extraction.

An automated fingerprint recognition system (AFRS) for 3D fingerprints is essential and highly promising for biometric security. Despite the progress in developing 3D AFRSs, achieving high-quality real-time reconstruction and high-accuracy recognition of 3D fingerprints remain two challenging issues. To address them, we propose a robust 3D AFRS based on ridge-valley (RV)-guided 3D fingerprint reconstruction and 3D topology polymer (TTP) feature extraction. The former considers the unique fingerprint characteristics of the RV and achieves real-time reconstruction. Unlike traditional triangulation-based methods that establish correspondences between points by cross-correlation-based searching, we propose to establish RV correspondences (RVCs) between ridges/valleys by defining and calculating a RVC matrix based on the topology of RV curves. To enhance depth reconstruction, curve-based smoothing is proposed to refine our novel RV disparity map. The TTP feature codes the 3D topology by projecting the 3D minutiae onto multiple planes and extracting their corresponding 2D topologies and has proven to be effective and efficient for 3D fingerprint recognition. Comprehensive experimental results demonstrate that our method outperforms the state-of-the-art methods in terms of both reconstruction and recognition accuracy. Also, due to its very short running time, it is appropriate for practical applications.

Deep Learning Algorithms based Fingerprint Authentication: Systematic Literature Review

Deep Learning algorithms (DL) have been applied in different domains such as computer vision, image detection, robotics and speech processing, in most cases, DL demonstrated better performance than the conventional machine learning algorithms (shallow algorithms). The artificial intelligence research community has leveraged the robustness of the DL because of their ability to process large data size and handle variations in biometric data such as aging or expression problem. Particularly, DL research in automatic fingerprint recognition system (AFRS) is gaining momentum starting from the last decade in the area of fingerprint pre-processing, fingerprints quality enhancement, fingerprint feature extraction, security of fingerprint and performance improvement of AFRS. However, there are limited studies that address the application of DL to model fingerprint biometric for different tasks in the fingerprint recognition process. To bridge this gap, this paper presents a systematic literature review and an insightful meta-data analysis of a decade applications of DL in AFRS. Discussion on proposed model’s tasks, state of the art study, dataset, and training architecture are presented. The Convolutional Neural Networks models were the most saturated models in developing fingerprint biometrics authentication. The study revealed different roles of the DL in training architecture of the models: feature extractor, classifier and end-to-end learning. The review highlights open research challenges and present new perspective for solving the challenges in the future. The author believed that this paper will guide researchers in propose novel fingerprint authentication scheme.

One-Class Fingerprint Presentation Attack Detection Using Auto-Encoder Network.

Automated Fingerprint Recognition Systems (AFRSs) have been threatened by Presentation Attack (PA) since its existence. It is thus desirable to develop effective presentation attack detection (PAD) methods. However, the unpredictable PAs make PAD be a challenging problem. This paper proposes a novel One-Class PAD (OCPAD) method for Optical Coherence Technology (OCT) images based fingerprint PA detection. The proposed OCPAD model is learned from a training set only consists of Bonafides (i.e. real fingerprints). The reconstruction error and latent code obtained from the trained auto-encoder network in the proposed model is taken as the basis for the following spoofness score calculation. To get more accurate reconstruction error, we propose an activation map based weighting model to further refine the accuracy of reconstruction error. We test different statistics and distance measures and finally use a decision level fusion to make the final prediction. Our experiments are performed using a dataset with 93200 bonafide scans and 48400 PA scans. The results show that the proposed OCPAD can achieve a True Positive Rate (TPR) of 99.43% when the False Positive Rate (FPR) equals to 10% and a TPR of 96.59% when FPR=5%, which significantly outperformed a feature based approach and a supervised learning based model requiring PAs for training.

Robust and high-security fingerprint recognition system using optical coherence tomography

Traditional fingerprint recognition systems are vulnerable to attacks, such as the use of artificial fingerprints, and poor performance will be achieved if the captured surface fingerprints are of low-quality. Developing high-security and robust fingerprint recognition systems is of increasing concern in modern society. The introduction of optical coherence tomography (OCT) for fingerprint imaging opens up a new research domain for fingerprint recognition due to its ability to capture the depth information of skin layers. This paper proposes a fingerprint recognition system based on OCT. The research first establishes a database with normal, worn-out, artificial and degraded fingerprints imaged by our custom-built, in-house OCT device. Then, we propose to reconstruct three layers of subsurface fingerprints by considering diverse skin layer information. For each of the subsurface fingerprints divided according to the physical structure of the fingertip, we propose a simple yet effective projection-based reconstruction method. Finally, a pixel-level fusion strategy based on the local image quality is proposed to the fuse the three levels of subsurface fingerprints for robust fingerprint recognition. In our experiments, we show that as much diverse fingerprint information can be retained as possible by the proposed subsurface fingerprint reconstruction method. We also demonstrate the effectiveness and efficiency of the proposed method by comparing it with existing state-of-the-art internal fingerprint reconstruction approaches. The robustness and high anti-spoofing ability of the proposed system is verified by comparing the matching performance evaluated on the established OCT-based database and another database with the same fingerprints imaged by a commercial optical sensor. The best EER and FMR100 evaluated on OCT-based fingerprints are 0.42% and 0.36%, respectively. The best EER and FMR100 evaluated on traditional 2D surface fingerprints are 8.05% and 18.18%, respectively, which shows the vast potential of the proposed system in current automated fingerprint recognition systems (AFRSs).

Fingerprint pore matching using deep features

As a popular living fingerprint feature, sweat pore has been adopted to build robust high resolution automated fingerprint recognition systems (AFRSs). Pore matching is an important step in high resolution fingerprint recognition. This paper proposes a novel pore matching method with high recognition accuracy. The method mainly solves the pore representation problem in the state-of-the-art direct pore matching method. By making full use of the diversity and large quantities of sweat pores on fingerprints, deep convolutional networks are carefully designed to learn a deep feature (denoted as DeepPoreID) for each pore. The inter-class difference and intra-class similarity of pore patch pairs can be well solved using deep learning. The DeepPoreID is then used to describe the local feature for each pore and finally integrated into the classical direct pore matching method. More specifically, pore patches, which are cropped from both Query and Template fingerprint images, are imported into the well-trained networks to generate DeepPoreID for pore representation. The similarity between those DeepPoreIDs are then obtained by calculating the Euclidian Distance between them. Subsequently, one-to-many coarse pore correspondences are established via comparing their similarity. Finally, classical Weighted RANdom SAmple Consensus (WRANSAC) is employed to pick true pore correspondences from coarse ones. The experiments carried on the two public high resolution fingerprint database have shown the effectiveness of the proposed DeepPoreID, especially for fingerprint matching with small image size. Meanwhile, better recognition accuracy is achieved by the proposed method when compared with the existing state-of-the-art methods. About 35% rise in equal error rate (EER) and about 30% rise in FMR1000 when compared with the best result evaluated on the database with image size of 320 × 240 pixels.

Multi-task CNN for restoring corrupted fingerprint images

Fingerprint image enhancement is one of the fundamental modules in an automated fingerprint recognition system (AFRS). While the performance of AFRS advances with sophisticated fingerprint matching algorithms, poor fingerprint image quality remains a major issue to achieve accurate fingerprint recognition. In this paper, we present a multi-task convolutional neural network (CNN) based method to recover fingerprint ridge structures from corrupted fingerprint images. By learning from the noises and corruptions caused by various undesirable conditions of finger and sensor, the proposed CNN model consists of two streams that reconstruct the fingerprint image and orientation field simultaneously. The enhanced fingerprint is further refined using the orientation field information. Moreover, we create a deliberately corrupted fingerprint image dataset associated with ground truth images to facilitate the supervised learning of the proposed CNN model. Experimental results show significant improvement on both image quality and fingerprint matching accuracy after applying the proposed fingerprint image enhancement technique to several well-known fingerprint datasets.

Analysis of Fingerprint Recognition System Using Neural Network

Fingerprint identification has a substantial efficacy in forensic science and aids criminal investigations. Fingerprints are distinctive and remain enduring throughout a person’s life. The automatic fingerprint recognition systems are based on ridges and their characteristics known as minutiae. Hence it is extremely important to mark these minutiae accurately and reject the false ones. In this work, we have used ridge termination and ridge bifurcation as minutiae for fingerprint recognition systems. At the time of the analysis of algorithms, the approaches of attributes impart better results. The recognition rate is increased & the error rate diminishes with the aid of this technique. The most important step here in automatic fingerprint matching is to securely extract the minutiae from the captured fingerprint binary images. There are already a variety of techniques are available for extracting fingerprint minutiae. The recognition rate of this intended method of fingerprint recognition system using neural networks is 91.10%. From the extricate outcome, we may infer about a very affirmative impact of neural networks on the comprehensive recognition rate, specifically in low excellence images.

Fingerprints Classification through Image Analysis and Machine Learning Method

The system that automatically identifies the anthropometric fingerprint is one of the systems that interact directly with the user, which every day will be provided with a diverse database. This requires the system to be optimized to handle the process to meet the needs of users such as fast processing time, almost absolute accuracy, no errors in the real process. Therefore, in this paper, we propose the application of machine learning methods to develop fingerprint classification algorithms based on the singularity feature. The goal of the paper is to reduce the number of comparisons in automatic fingerprint recognition systems with large databases. The combination of using computer vision algorithms in the image pre-processing stage increases the calculation time, improves the quality of the input images, making the process of feature extraction highly effective and the classification process fast and accurate. The classification results on 3 datasets with the criteria for Precision, Recall, Accuracy evaluation and ROC analysis of algorithms show that the Random Forest (RF) algorithm has the best accuracy (≥96.75%) on all 3 databases, Support Vector Machine (SVM) has the best results (≥95.5%) 2 / 3 databases.

High-accurate and robust fingerprint anti-spoofing system using Optical Coherence Tomography

Traditional commercial automated fingerprint recognition systems (AFRSs) are vulnerable to fake attacks by the use of artificial fingerprints, due to its limitation on resolution and the difficulty of obtaining depth information. Developing new systems with strong anti-spoofing ability are of increasing concern in the current digital age. Inspired by the observation and comparison of fingertip skin structure and the one dimensional (1D) depth signals derived from OCT acquisition images between real finger and artificial fingerprints, two novel anti-spoofing features, namely depth-double-peak feature and sub-single-peak feature, were specifically defined. Depth-double-peak feature refers that there must be two and only two peaks in the 1D depth signal which reflects the double-peak structure of real fingertip skin. While sub-single-peak feature means that there must be a peak in the 1D depth signal intercepted before the maximum peak which distinguishes the extra layer covered on a real finger. Real and fake images could be presented by these two features and classified by a pre-learned threshold. Four types of artificial fingerprint, i.e., Normal Thickness Fingerprint Layer (NTFL), thin Fingerprint Layer (TFL), Ultra-Thin Fingerprint Layer (UTFL and Artificial Fingers Model (AFM) were collected to verify system robustness. 30 sets of real finger data (each set includes 400 images) and 60 sets of artificial fingerprint data (15 sets of each type) were collected by our designed OCT device. Experimental results show that our proposed anti-spoofing system could achieve 100% accuracy over all four types of artificial fingerprints and outperform the other automated anti-spoofing method in comparison.

A New Algorithm for Locating and Extracting Minutiae from Fingerprint Images

Fingerprints are considered as the oldest and most widely used in the world for biometric identification. Every person has unique and permanent fingerprints. Most automatic fingerprint recognition systems are based on features formed from lines known as minutiae. Building a database of unique minutiae is very important in the security systems because it concerns the identification of the person committing a crime through the latent left in the crime scene. This research presents a new algorithm to give a minutia a unique value leading to accelerating the search process for a person. The algorithm splits the fingerprint image into four sections, then calculates the values for each minutia in each section and stores it in a database that is designed for this purpose. This research provides a great opportunity and additional options to fingerprint experts in order to solve many cases that are still undiscovered while searching for the latent in the database of minutiae. The results of testing this algorithm were very successful, very encouraging and helpful to fingerprint experts in their work.

A BROAD SURVEY ON FEATURE EXTRACTION METHODS FOR FINGERPRINT IMAGE ANALYSIS

This paper focused on the study of various feature extraction techniques applied for fingerprint identification, verification and classification as it is the most important step for image processing. Feature extraction techniques are classified into local (low level) and global (high level) features. Global features such as arch, loop, delta and whorl where as local features such as ridge end and bifurcation called minutiae are majors of automatic fingerprint recognition system. In this study, it has been observed that most of the fingerprint recognition systems are based on minutiae features. In this paper we analyze the various feature extraction methods used so far with their mathematical background to the readers.

Low‐quality fingerprint classification using deep neural network

Fingerprint recognition systems mainly use minutiae points information. As shown in many previous research works, fingerprint images do not always have good quality to be used by automatic fingerprint recognition systems. To tackle this challenge, in this work, the authors are focusing on very low-quality fingerprint images, which contain several well-known distortions such as dryness, wetness, physical damage, presence of dots, and blurriness. They develop an efficient, with high accuracy, deep neural network algorithm, which recognises such low-quality fingerprints. The experimental results have been obtained from the real low-quality fingerprint database, and the achieved results show the high performance and robustness of the introduced deep network technique. The VGG16-based deep network achieves the highest performance of 93% for dry and the lowest performance of 84% for blurred fingerprint classes.

Combining multi-scale composite windows with hierarchical smoothing strategy for fingerprint orientation field computation

BackgroundOrientation field (OF) plays a very significant role in automatic fingerprint recognition systems. Many algorithms have been proposed for the estimation of fingerprints’ OF but it is hard to solve the dilemma of correcting spurious ridge structure and avoiding singularity location deviation, especially for poor images. So far, the following drawbacks still need to be solved for OF construction methods for practical application: (1) How to adaptively choose block scales to resolve the contradiction between accuracy and anti-noise, since small scale is beneficial to accuracy but is sensitive to noise, while large scale is more resistant to noise, but the accuracy is deteriorated. (2) How to construct the genuine OF in the areas close-by singular points and to evade singularity location deviation? Current block based methods give spurious OF estimates in the area near singular points because these areas have large curvature thus the detected singular points deviate from the genuine localizations. When these singular points are used as the anchor for referencing minutiae, it makes the average error of matching or recognition even larger. Therefore, it is essentials to construct the genuine OF in the areas close-by singular points and to evade singularity deviation.MethodsTo overcome the above-mentioned limitations, a novel method, combining a weighted multi-scale composite window (WMCM) with a hierarchical smoothing strategy has been proposed for the computation of fingerprint OF. This method mainly contains two procedures: the approximate OF estimation and the hierarchical OF smoothing. In the first procedure, a series of OFs are established under multiple scales of composite windows by using a gradient based method then a coarse OF is estimated using the weight of each scale determined by a squared gradient consistency. In the second procedure, the OF is first quantized into a two-digitized orientation zone and a two-orientation-zone filtering strategy is adapted to the OF blocks based on a filtering mask obtained after eliminating the isolated blocks. In the end a similar three-digitized orientation zone is performed to obtain an accurate and smooth OF. To validate the performance, the proposed method has been applied to OF computation using the FVC2004 databases and three experiments are designed. Experiment 1 aims to validate whether the weighted multi-scale composite window can balance the dilemma of accuracy and robustness more effectively than the previous works do. Experiment 2 is designed to examine whether the hierarchical smoothing method can correct the spurious ridge flow and preserve the genuine localization of singular points. The purpose of experiment 3 is to test the performance of the proposed method on OF reconstruction in low quality fingerprint images. The fingerprint databases FVC 2004 DB1–DB4 are employed in this study.ResultsThe results of experiment I shows that the proposed method is capable to extract the information of OF reliably and it is more robust against singularity localization deviation in comparison with the other three gradient based methods. The results of experiment II indicates that the proposed smoothing method can balance the contradiction in correcting spurious ridge structures and preserving genuine singularity localization. The results of experiment III illustrates that our approach combing WMCW with the hierarchical smoothing method is capable to extract the information of OF ridge reliably and it is more robust against singularity deviation in comparison with the other three gradient based methods. In a word, the experiment results demonstrate that the proposed method can correct spurious ridge structure and meanwhile avoid singularity deviation compared with the previous works.ConclusionsA novel gradient based algorithm has been proposed which is more reliable for the estimation of the ridge information for fingerprint OF and is more accurate in preserving the singularity localization. Compared with the previously proposed gradient based methods, the advantages of the proposed RBSF lie in three aspects. Firstly a weighted multi-scale composite window is put forward to replace the single window used by conventional gradient based methods and to adaptively choose the scales of the blocks. Secondly, a hierarchical smoothing strategy is proposed to enhance the OF by using the two-orientation-zone filtering and the three-orientation-zone filtering, aiming to correct the spurious ridges and preserving the genuine location of singular points. Finally, three experiments are designed to test the proposed algorithm together with other popular gradient based methods on real fingerprint images, which are selected from different categories and all are suffering from obvious noise effects. All the experiment results show that the proposed method is superior with respect to reliable OF construction and avoiding singularity localization deviation.

A Gradient Based Approach for Fingerprint Image Segmentation using Morphological Operators

The advancement of science and technology has made the reliable individual recognition and identification systems to become very popular. From the various biometric characteristics, fingerprint is one of the popular method because of its easiness and not much effort is required to acquire fingerprint. First step for an Automated Fingerprint Identification System (AFIS) is the segmentation of fingerprint from the acquired image. During fingerprint segmentation process the input image is decomposed into foreground and background areas. The foreground area contains information that are needed in the automatic fingerprint recognition systems. However, the background is a noisy region that contributes to the extraction of false features. So in an AFIS, fingerprint image segmentation plays an important role in carefully separating ridge like part (foreground) from noisy background. Gradient based method is commonly used for segmentation process. Since gradient estimation is erroneous in noisy images, the study proposes a combination of gradient mask and morphological operations to segment fingerprint foreground effectively. The results obtained prove that the new method is suited for fingerprint segmentation.