Showing papers on "Fingerprint recognition published in 1994"

Symmetric phase-only matched filtering of Fourier-Mellin transforms for image registration and recognition

Abstract: Presents a new method to match a 2D image to a translated, rotated and scaled reference image. The approach consists of two steps: the calculation of a Fourier-Mellin invariant (FMI) descriptor for each image to be matched, and the matching of the FMI descriptors. The FMI descriptor is translation invariant, and represents rotation and scaling as translations in parameter space. The matching of the FMI descriptors is achieved using symmetric phase-only matched filtering (SPOMF). The performance of the FMI-SPOMF algorithm is the same or similar to that of phase-only matched filtering when dealing with image translations. The significant advantage of the new technique is its capability to match rotated and scaled images accurately and efficiently. The innovation is the application of SPOMF to the FMI descriptors, which guarantees high discriminating power and excellent robustness in the presence of noise. This paper describes the principle of the new method and its discrete implementation for either image detection problems or image registration problems. Practical results are presented for various applications in medical imaging, remote sensing, fingerprint recognition and multiobject identification. >

Automated system for fingerprint authentication using pores and ridge structure

Abstract: A novel technique for automated fingerprint authentication is presented which utilizes pore information extracted from live scanned images. The position of the pores on the fingerprint ridges is known to provide information that is unique to an individual and is sufficient for use in identification. By combining the use of ridge and pore features, we have developed a unique multilevel verification/identification technique that possesses advantages over systems employing ridge information only. An optical/electronic sensor capable of providing a high resolution fingerprint image is required for extraction of pertinent pore information, which makes it unlikely that electronically scanned inked fingerprints would contain adequate pore data that is sufficient, or consistent enough, for use in authentication. The feasibility of this technique has been demonstrated by a working system that was designed to provide secure access to a computer. Low false reject and zero false accept error rates have been observed based on initial testing of the prototype verification system.© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Method and apparatus for fingerprint characterization and recognition using auto correlation pattern

Abstract: Apparatus for use with an autocorrelation technique for characterizing fingerprints includes an imaging device for providing an image of a fingerprint. The image so produced is then utilized by a microprocessor in order to generate an autocorrelation pattern for statistical comparison with stored data so as to determine whether the image of the fingerprint under test is derived from the fingerprint representated by the stored data.

Restoration and enhancement of fingerprint images using M-lattice-a novel nonlinear dynamical system

Abstract: Develops a method for the simultaneous restoration and halftoning of fingerprints using the "M-lattice", a new nonlinear dynamical system. This system is rooted in the reaction-diffusion model, first proposed by Turing to explain morphogenesis (the formation of patterns in nature). But in contrast with the general reaction-diffusion, the state variables of the M-lattice are guaranteed to be bounded. The M-lattice system is closely related to the analog Hopfield network and the cellular neural network, but has more flexibility in how its variables interact. These properties make it better suited than reaction-diffusion for several new engineering applications. The proposed method for enhancing fingerprints explores the ability of the M-lattice to form oriented spatial patterns (like reaction-diffusion), while producing binary outputs (like feedback neural networks). The fingerprints synthesized by the M-lattice retain and emphasize more of the relevant detail than do those obtained by adaptive thresholding, a common halftoning method employed in traditional fingerprint classification systems.

Optical pattern recognition for validation and security verification

Abstract: We propose an idea for security verification of credit cards, passports, and other ID so that they cannot easily be reproduced. A new scheme of complex phase/amplitude patterns that cannot be seen and cannot be copied by an intensity sensitive detector such as a CCD camera is used. The basic idea is to permanently and irretrievably bond a phase mask to a primary identification amplitude pattern such as a fingerprint, a picture of a face, or a signature. Computer simulation results and tests of the proposed system will be provided to verify that both the phase mask and the primary pattern are separately readable and identifiable in an optical processor or correlator.© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Compression of gray-scale fingerprint images

Abstract: The FBI has developed a specification for the compression of gray-scale fingerprint images to support paperless identification services within the criminal justice community. The algorithm is based on a scalar quantization of a discrete wavelet transform decomposition of the images, followed by zero run encoding and Huffman encoding.

Identification process for personal data card such as credit card - has fingerprint data held in card ROM that is compared with data obtained by reading of users fingerprint

Abstract: The identification method providing improved access control for the use of such items as credit or bank cards (10) involves a fingerprint check. The card has a built-in ROM memory that contains data relating to the fingerprint of the user. When the card is inserted into the reader (3), the ROM data is read. In order that access can be given, the user presents his finger (6) to a fingerprint reader (2). The digitised fingerprint data is compared with the stored data. After a predetermined number of unsuccessful attempts the card ROM is automatically destroyed. USE/ADVANTAGE - Provides improved protection against illegal use.

Fingerprint matching device

Abstract: PURPOSE:To provide a fingerprint matching device capable of matching a fingerprint with high similarity equal to the time of registration, in the fingerprint matching device for comparing an inputted fingerprint image and a dictionary pattern stored in a dictionary, and confirming the person himself. CONSTITUTION:The device is constituted of a fingerprint sensor 1 for inputting a fingerprint image, a binarizing circuit 2 for binarizing an output of the fingerprint sensor 1, a binarizing memory 3 for storing an output of the binarizing circuit 2, a feature extracting part 10 for extracting a feature point from a fingerprint image read out of the binarizing memory 3, a complicateness evaluating means 11 for extracting and storing data related to the complicatedness of the fingerprint image from the fingerprint image read out of the binarizing memory 3 in the same way, and comparing and evaluating the complicatedness of a matching fingerprint image and the complicatedness of the registered fingerprint image at the time of matching the fingerprint, a fingerprint dictionary storage part 12 for registering a feature pattern extracted by the feature extracting part 11 as a dictionary, and a matching part 13 for matching the matching fingerprint image and a fingerprint dictionary registered in the fingerprint dictionary storage part 12.

Morphological scale-space fingerprints and their use in object recognition in range images

Abstract: We present the theory of multiscale dilation-erosion scale-space and the process of feature extraction via morphological scale-space fingerprints. We then discuss the reduced form of the fingerprints and state the scale-space causality theorem. These fingerprints are then applied to the recognition of multiple objects from range data. The proposed recognition system is invariant to translation, rotation, scale, and partial occlusion. We demonstrate results for the recognition of human faces in a scene, and the recognition of mountain features in a digital elevation map. >

Automated coincident sequencing for fingerprint verification

Abstract: The increasing need for security in present day society has generated considerable interest in the use of biometrics. This has renewed research in the area of automatic fingerprint recognition and the related computer technology capable of coping with the complex nature and speed requirements of the task. Due to the complexity of the problem, there has been limited success in obtaining a satisfactory sytem. In this paper, a high speed and low cost system for scanning, identifying and coding fingerprints is described. The system automates the manual method for the positive identification of fingerprints using a technique called coincident sequencing which is legally and internationally accepted. >

Fingerprint recognition device

Abstract: PURPOSE:To remove noise on account of the distortion of the image of a fingerprint and to improve a recognition rate by moving or rotating a transparent body perpendicularly to the pressure-installation direction of the transparent body and to a two-dimensional direction. CONSTITUTION:A fingerprint pattern is obtained from the difference of a reflection condition when light is projected from a light source (LED) 330 to a prism 320 and a finger 301 is pressed. A lens 312 imageforms the fingerprint pattern on a CCD camera 310, and the CCD camera 310 converts the pattern into a video signal and transmits it to a recognition device 10. It frequently occurs that distortion is generated in the fingerprint pattern by the inputting method of force into the finger 301 and an attitude, and therefore erroneous recognition is liable to occur. Thus, erroneous recognition is prevented by driving stages 422, 424 and 426 and giving vibration. The recognition device 101 collates all the generated fingerprint patterns with a previously registered pattern so as to recognize them on a real time basis. When the coincident pattern exists, it is recognized to be the same or the previously registered one.

Update system for dictionary image of fingerprint recognition device

Abstract: PURPOSE: To shorten the time up to success in collation by providing each feature point data with coincidence data indicating the degree of matching with an input fingerprint image, performing pattern matching between all feature point data and the input fingerprint image for an optional period, and constituting dictionary data in the decreasing order of matching data CONSTITUTION: A command for starting collation processing is sent out of a control part 20 and read by a core part 10 The fingerprint image is inputted from a sensor 12 and stored as a multi-valued image in a frame memory 13 The multi-valued image stored in the frame memory 13 is binarized and stored in a binary memory 15, and dictionary data having a specified dictionary number is transferred from the control part 20 to a memory 17 for collation Then, the pattern matching between the binary image read out of the binary memory 15 and the dictionary data read out of the memory 17 for collation is performed in the order of feature points to obtain the dictionary data in the decreasing order of matching data, thereby shortening the time up to success in collation

Fingerprint detection sensor

Abstract: PURPOSE:To reduce the load on the hardware and software of a fingerprint matching system and a fingerprint recognition system as to the fingerprint detection sensor used for those systems CONSTITUTION:The fingerprint detection sensor, equipped with a fingerprint input plate 1 where a finger is placed, an illumination light source 2 which irradiates the finger on the fingerprint input plate 1 with light, and a photoelectric converting means 3 which converts a fingerprint image generated by the fingerprint input plate 1 into electric energy, is equipped with a convex lens 4 which has its front focal plane at the arrangement position of the fingerprint mount surface of the fingerprint input body 1 and its rear focal plane at the arrangement position of the photoelectric converting means 3 and an optical shutter means 5 which is arranged at the fingerprint mount surface position of the fingerprint input plate 1 and has only one partial area made sequentially optically open Further, the photoelectric converting means 3 detects spatial phase information on the fingerprint image extracted by the convex lens 4

Fingerprint preclassification using key-points

Abstract: A new idea of fingerprint preclassification named the key-point recognition method (KMF) is proposed which only pays attention to whether there is a general feature key-point in a certain area and takes no notice of what the feature is. Using this method, an automatic fingerprint recognition system has been developed, which is characterized by fewer requirements imposed on the preprocessing, lower sensitivity to the noise, higher capacity and parallelism being compared with other traditional ones. The system can list out the most promising fingerprints as a preclassifier. >

Ridge-flow determination in fingerprint images

Abstract: The paper describes how, given a ridge-and-valley image of a fingerprint, a flow map can be extracted. The first step is a unique grayscale algorithm based on 3D mathematical morphology to extract the ridge lines under a wide range of conditions. The paper then compares the results of finding the ridge flow using micropatterns, extended templates (on binary and grayscale images), and several well-known, traditional techniques. The question of spatial resolution is also addressed.

Region-of-interest detection for fingerprint classification

Abstract: This paper discusses the use of neural networks to locate regions of interest for fingerprint classification using feature-encoded fingerprint images. The target areas are those useful for the classification of fingerprints: whorls, loops, arches, and deltas. Our approach is to limit the amount of data which a classification algorithm must consider by determining with high accuracy those areas which are most likely to contain relevant features (effective for classification). Several feature sets were analyzed and successful preliminary results are summarized. Five feature sets were tested: (1) grayscale data, (2) binary ridges, (3) binary projection, and (4 & 5) 4- and 8-way directional convolutions. Four-way directional convolution produced accurate results with a minimal number of false alarms. All work was conducted using fingerprint data from NIST Special Database 4. The approach discussed here is also applicable to other general computer vision problems. In addition to fingerprint classification, an example of face recognition is also provided to illustrate the generality of the algorithmic approach.