A Gradient Based Approach for Fingerprint Image Segmentation using Morphological Operators

A fingerprint image is composed of a foreground and background areas. The foreground area is composed of ridges and valleys, while the background area is the region that surrounds the fingertip and is mainly noisy. Fingerprint recognition techniques amount to extracting minutiae as well as identifying ridge and valley regions. As the captured fingerprint images may be of poor quality due to various reasons, it is necessary to enhance the image prior to minutiae extraction. Usually, fingerprint images are enhanced either in the spatial or frequency domains. However, due to the complicated ridge structures, the quality of the enhanced images is not satisfactory. In this paper, a novel enhancement method is proposed. It makes use of a recently developed fingerprint segmentation technique, in order to separate the fingerprint foreground and background areas, and subsequently speeds up the enhancement process. Next, a novel interpolation-based technique is proposed to join broken ridges. Finally, in order to estimate the ridge-valley spatial spacing, an accurate Radon-based technique is proposed. This accurate spacing is necessary for the design of 2-D directional Gabor filter that removes artifacts, and isolated black regions. The enhancement algorithm has been implemented and tested on fingerprint images drawn from FVC2002 and FVC2004 databases. A qualitative measure of the enhanced performance is also described. Simulation results show that our proposed algorithm has verified significant quality improvement over the existing published techniques.

In this paper, we propose an innovative approach to improve the performance of an Automatic Fingerprint Identification System (AFIS). The method is based on the design of a Possibilistic Fingerprint Quality Assessment (PFQA) filter where ground truths of fingerprint images of effective and ineffective quality are built by learning. The first approach, QS_I, is based on the AFIS decision for the image without considering its paired image to decide its effectiveness or ineffectiveness. The second approach, QS_PI, is based on the AFIS decision when considering the pair (effective image, ineffective image). The two ground truths (effective/ineffective) are used to design the PFQA filter. PFQA discards the images for which the AFIS does not generate a correct decision. The proposed intervention does not affect how the AFIS works but ensures a selection of the input images, recognizing the most suitable ones to reach the AFIS’s highest recognition rate (RR). The performance of PFQA is evaluated on two experimental databases using two conventional AFIS, and a comparison is made with four current fingerprint image quality assessment (IQA) methods. The results show that an AFIS using PFQA can improve its RR by roughly 10% over an AFIS not using an IQA method. However, compared to other fingerprint IQA methods using the same AFIS, the RR improvement is more modest, in a 5–6% range.

Lack of robust segmentation against degraded quality image is one of the open issues in fingerprint segmentation. Good fingerprint segmentation effectively reduces the processing time in automatic fingerprint recognition systems. Poor segmentation result in spurious and missing features thus degrading performance of overall system. Segmentation will be more effective if done in accordance to the quality of image. Fingerprint images with high quality have wide range of features which can be used for segmentation than the low quality image, where the fingerprint features are not clearly visible. This paper focus on the two folded segmentation process comprising of quality evaluation and segmentation based on it. Various global and local features are used for assessing quality of image and thereby using them for segmenting ridge area from plain background. The segmented images are compared using percentage of foreground area to total area, genuine number of minutiae points extracted from segmented area. The time taken for image segmentation is also used as a performance parameter. The proposed approach has been tested with images of different qualities from NIST and FVC data sets and the results are proven to be better than the conventional segmentation approaches.

Fingerprint segmentation is an important pre-processing step in automatic fingerprint identification system. Traditional fingerprint segmentation methods either highly depend on empirical thresholds sophistically chosen by experts or a learned model trained by elements generated from manually segmented fingerprints. It is manpower and time consuming. They always try their best to tune their fingerprint segmentation methods to be universal to all unseen fingerprints. However, one fingerprint may have a significantly distinct distribution from another in feature space because fingerprint acquisition is affected by several factors, such as pressure, the types of sensors, finger tip condition (dry, wet etc.). As a result, the delicate threshold and the well trained model may not be suitable to the new input fingerprints from a new finger or a new person. And it makes worse when automatic fingerprint identification systems meet sensor interoperability. To solve the problem, we propose a personalized fingerprint segmentation method: Automatic Labeling based Linear Neighborhood Propagation (ALLNP), which learns a segmentation model special for each input fingerprint image based on the input image only. The proposed method is tested with typical fingerprint images from four heterogeneous data bases of FVC2000. Experimental results show its effectiveness and encouraging strength when fingerprint segmentation meets sensor interoperability.

Automated Fingerprint Identification Systems (AFIS) play a vital role in modern law enforcement by aiding in the identification and apprehension of criminals through fingerprint analysis. However, despite their significance, challenges in operating AFIS remain the main hindrance to its effective utilization. Thus, this study aims to investigate the issues and challenges faced by police officers in the Philippines with AFIS. Employing a convergent parallel mixed methods research design, quantitative data were collected through a survey questionnaire, while qualitative data were obtained through in-depth interviews. The study participants comprised six experienced Filipino police officers purposively chosen for their exposure to AFIS operations. The study uses the mixed method. Descriptive statistics and Mann-Whitney U Test were used during quantitative data analysis, while thematic analysis was used in analyzing qualitative data. The study findings revealed that the top challenge faced by police officers in the Philippines is comparing and storing fingerprints in the AFIS database, primarily due to insufficient training and technical support. Themes such as regular training, technical support, and continuous learning emerged to address the challenges related to fingerprint quality, technical issues, storage limitations, and hardware problems. The study also revealed that Filipino police officers encounter moderate challenges when operating AFIS, with variations depending on sex, age, and length of service. In conclusion, the study underscores the significance of continuous training, technical support, and effective communication for successful AFIS operations. Law enforcement agencies are urged to prioritize providing proper training and technical support to ensure accurate and reliable utilization of this technology in policing.

Automatic matching of poor quality latent fingerprints to rolled/slap fingerprints using an Automated Fingerprint Identification System (AFIS) is still far from satisfactory. Therefore, it is a common practice to have a latent examiner mark features on a latent for improving the hit rate of the AFIS. We propose a synergistic crowd powered latent identification framework where multiple latent examiners and the AFIS work in conjunction with each other to boost the identification accuracy of the AFIS. Given a latent, the candidate list output by the AFIS is used to determine the likelihood that a hit at rank-1 was found. A latent for which this likelihood is low is crowdsourced to a pool of latent examiners for feature markup. The manual markups are then input to the AFIS to increase the likelihood of making a hit in the reference database. Experimental results show that the fusion of an AFIS with examiner markups improves the rank-1 identification accuracy of the AFIS by 7.75% (using six markups) on the 500 ppi NIST SD27, 11.37% (using two markups) on the 1000 ppi ELFT-EFS public challenge database, and by 2.5% (using a single markup) on the 1000 ppi RS&A database against 250,000 rolled prints in the reference database.

Fingerprint segmentation is a crucial and important step of image processing in automatic fingerprint identification. Because, it is very important for alright fingerprint features extraction, such as, singular points, bifurcation and ridge ending minutia’s. The aim of the segmentation of fingerprint is to extract the interest area (foreground) and to exclude the background regions, in order to reduce the time of subsequent processing and to avoid detecting false features. This paper presents a new approach of fingerprints segmentation. This approach is based on variance image and combined fuzzy C-mean algorithm with the statistical features. Fingerprint segmentation results from the proposed method are validated and the accuracy of segmentation sensitivity for the test data available is evaluated. We have tested this technique on more than 1000 images fingerprint taken from “CASIA Fingerprint Image Database Version 5.0” (CASIA-FingerprintV5). Then a comparative study with the existing techniques is presented. The experimental results demonstrate the superiority, the effectiveness and the robustness of the proposed method. Key words: Fuzzy C-means, biometrics, fingerprint image, segmentation, statistical features.

Sweat pores on the human fingertip have meaningful patterns that enable individual identification. Although conventional automatic fingerprint identification systems (AFIS) have mainly employed the minutiae features to match fingerprints, there has been minimal research that uses sweat pores to match fingerprints. Recently, high-resolution optical sensors and pore-based fingerprint systems have become available, which motivates research on pore analysis. However, most existing pore-based AFIS methods use the minutia-ridge information and image pixel distribution, which limit their applications. In this context, this paper presents a stable pore matching algorithm which effectively removes both the minutia-ridge and fingerprint-device dependencies. Experimental results show that the proposed pore matching algorithm is more accurate for general fingerprint images and robust under noisy conditions compared with existing methods. The proposed method can be used to improve the performance of AFIS combined with the conventional minutiae-based methods. Since sweat pores can also be observed using various systems, removing of the fingerprint-device dependency will make the pore-based AFIS useful for wide applications including forensic science, which matches the latent fingerprint to the fingerprint image in databases.

Automated Fingerprint Identification Systems (AFIS)

Removal of digitization errors in fingerprint ridgelines using B-splines

Fingerprint recognition has wide application prospect in all fields which contain identity authentication. Construction of accurate and reliable，safe and Practical automatic fingerprint identification system(AFIS) has become researc hotspot. Although theoretical research and application developmen of AFIS have got a significant Progress，accuracy of the algorithm and proeessing speeds till need to be improved. In this paper, fingerprint image preprocessing algorithms，fingerprint singular Points and minutiae extraction algorithm and fingerprint matching algorithm are analyzed and discussed in detail.

The accuracy of Automatic Fingerprint Identification Systems (AFIS) is dependent on many variables ranging from the quality of the friction skin surface itself, to the ability of the image acquisition device to accurately image the fingerprint, to the feature extraction and matching software to detect the feature set and declare a correlation (a match/no match) based on some criteria. The genesis of these systems exclusively used rolled impression fingerprint imagery. As AFIS developers attempted to reduce the cost and improve the usability of these systems for commercial applications, plain impression imagery was adopted and total scanned image area was significantly reduced. This paper will quantify the effects of reduced image area on overall system accuracy in a single finger plain impression environment.

Animal identification is a topic of many studies, with a range of biometric methods currently in use. The cattle muzzle serves as a unique source of biometric traits. The aim of this study was to determine the best method for muzzle visualisation using imprints, the most frequent forms and minutiae points on imprints, and the minimum number of minutiae points required to establish an identity profile. Noseprints of 30 calves were taken on different surfaces and visualised using different methods (white paper and cardboard/ninhydrin solution and glass tile/small particle reagents and ceramic tile/fluorescent powder and glossy photopaper/grey instant or magnetic powder). The imprint of the entire muzzle was photographed and analysed using the Automated Fingerprint Identification System (AFIS) to detect the most frequent forms based on friction ridges and minutiae points. Further mathematical simulation revealed the minimal number of points required for animal identification. The best imprint was obtained on glossy black photopaper with grey instant powder. After analysing the digitised images with the AFIS magnifier, the six forms of beads and ridges in the selected 12 minutiae points were detected, thus creating an identity chart. Computer simulation confirmed that the lowest number of minutiae points necessary for unique animal identification, and 0% possibility of form repetition at points, was nine of the 12 selected points. As a biometric method, the muzzle imprint in combination with AFIS has the potential to be stored on large scale and used internationally, enabling identity control that is not susceptible to the issues involved with other biometric methods.

AFIS (Automated Fingerprint Identification System) is the most widely used identification system. But the most critical part in fingerprint identification is reliable extraction and matching of fingerprint features which depends on quality of input fingerprint image. But it is quite rare that the input fingerprint image will be of very good quality. So there is necessity of some fingerprint enhancement technique to enhance the features of fingerprints before extraction and matching. In this experiment, variable traditional gabor filter (TGF) and modified gabor filter (MGF) are compared in terms of performance, particularly for average and poor quality fingerprint images. Simulation results indicate that, as the quality of fingerprint image degrades, MGF performs more better than TGF in terms of reducing spurious minutiae.

This paper discusses a system to determine the identification request for a given person already exists. The check is performed by comparing Applicant attributes (except for signature) against the registration database. For biometric information searches, a Biometric Identification System (BIS), which is an Automated Fingerprint Identification System (AFIS) Database, is searched against the captured biometric data on the application record. If a matched record already exists or a number of partially matched records exist, then application processing is routed to the “Resolve Duplicate” process. The Fraud Investigation application is built on Privacy Identification and Management Solutions (PRIMS) framework which is based on Identification and Credentialing solutions. The solutions are structured to capture biographic and biometric data in real-time with immediate checks on a person's identity, and produce e-ID cards and passports using this framework. The PRIMS framework supports identity management such as personnel enrolment and application processing, identity verification, secure document production and card inventory control, issuance and post-issuance management, authentication/authorization at point-of-service. The PRIMS framework is built with a flexible, component-based, service-oriented architecture. The PRIMS framework integrates a number of functions required to manage end-to-end life cycle of registered persons and secure documents. PRIMS provides a highly configurable workflow and business rules engine and allows for significant variability to support unique client requirements in the areas of enrolment processing, different technologies for secure documents, and different solutions and uses of biometrics.