Showing papers on "Fingerprint recognition published in 1986"

Fingerprint recognition and retrieval system

Abstract: Fingerprints are scanned by a scanning system (13). Topological systems for coding and comparing fingerprints are described, including a system for recording a description of fingerprints. In a preferred embodiment, a central point of the fingerprint is selected as a center of rotating scan line. The scan line is rotated to different topological characteristics. A code (T) representing the type of irregularity is recorded (16, 17). A measure (M) of the scanning position when encountering the irregularity is made (16, 17). In the case of a rotating scan line the angular coordinate (θ) is recorded as the measure (M) of scanning position. The ridge count (R) (16) is also recorded. A list of coordinate sets (T, θ, R) specifies the topology of a sector. For fragmentary prints similar coordinate sets are generated. A fourth coordinate can be added corresponding to the radial distance (D) (16). A full set of coordinates (T,θ, R, D) gives a complete topological and spatial description of a fingerprint. Comparison of fingerprints can then be conducted by a computer (20).

A Tree System Approach for Fingerprint Pattern Recognition

Abstract: The purpose of this paper is to demonstrate how a syntactic approach and, in particular, a tree system may be used to represent and classify fingerprint patterns. The fingerprint impressions are subdivided into sampling squares which are preprocessed and postprocessed for feature extraction. A set of regular tree languages is used to describe the fingerprint patterns and a set of tree automata is used to recognize the coded patterns. In order to infer the structural configuration of the encoded fingerprints, a grammatical inference system is developed. This sytem utilizes a simple procedure to infer the numerous substructures and relies on a reachability matrix and a man-machine interactive technique for the inference of complex structures. The 92 fingerprint impressions were used to test the proposed approach. A set of 193 tree grammars was inferred from each sampling square of the 4 × 4 sampling matrix which is capable of generating about 2 × 1034 classes for the fingerprint patterns.

Fingerprint collating device

Abstract: PURPOSE: To perform accurate processing in response to the importance of various processes by setting individually a collation coincidence rate for judgement of identity in accordance with various processings. CONSTITUTION: An automatic teller machine cash dispenser 1 is connected to a host CPU20 of a calculation center and the CPU20 has a fingerprint data file 30. Then the coincidence rate for judgement of identity is divided into three steps in accordance with importance of the transaction processing, i.e., 70% is set with deposit together with 80% set in the case of payment of cash and 50% set in other cases (inquiry for balance, alarm to center, etc.) respectively. For instance, the deposit is selected and a first finger is set to a fingerprint reader of an input part of the machine 1. When the fingerprint is read, a data file corresponding to the corresponding account number is extracted. Then the read fingerprint is deposit processing is carried out if a ≥70% coincidence rate is obtained from said collation of fingerprints. COPYRIGHT: (C)1988,JPO&Japio

Fingerprint discriminating device

Abstract: PURPOSE:To improve individual identification precision and reliability by collating fingerprint information which is obtained by a fingerprint reader with previously stored fingerprint data and outputting a confirmation signal which identifies a registered person when the both coincides with each other as to >=2 fingers. CONSTITUTION:When a person who is allowed to enter a specific area inserts his ID card into a card reader, an address 2a where fingerprint data on the person corresponding to the ID number is stored is applied from a decoder 2 to fingerprint data memories 5A and 5B and signals 2b and 2c showing which fingers are placed on finger print readers 4A and 4B are applied to read finger display parts 3A and 3B. Then, the pieces of information when the fingers are placed on the fingerprint readers 4A and 4B are compared with fingerprint data latched in registers 6A and 6B by coincidence detectors 7A and 7B, so that an H-level detection signal is outputted when the both coincide with each other. When both detection signals are at a level H, an AND circuit 8 outputs an electric lock releasing command OPEN and a coincidence display device 9 displays the identification of a previously registered person. Consequently, the individual identification precision is improved.

Automatic Fingerprint Identification Terminal For Personal Verification

Abstract: A prototype fingerprint identification system for personal verification has beendeveloped. This system has a unique identification strategy, in the "top- down" direction,to map the features registered onto a raw input fingerprint image. Feature extraction byvarious image processing methods is not required and features used to make the top -down directional identification are selected that are easily detected on a raw input image.Therefore, this strategy makes identification possible with a personal computer.Introduction In complicated modern society, it is very important and meaningful to identify one's individuality. A fingerprint is mentioned as one of the tools to identify one'sindividuality. It is a pattern in the skin that exists on a finger tip surface.Fingerprints have been playing important roles in personal verification, due to theirimportant characteristics, such as "unchangeability" and "uniqueness ". Primarily, a fingerprint has been used as reliable material evidences

Optical Enhancement of Degraded Fingerprints.

Abstract: : The similarities and differences between fingerprints enable degraded fingerprints to be optically enhanced for the purpose of identification. A coherent optical processing system was used to locate and analyze the spectra of features that uniquely identify fingerprints. The spectra of these ridges and ridge characteristics (minutiae) are located in harmonic bands of spatial frequencies for all types of fingerprints. A general set of simple filters was developed to enhance the identifying features of degraded fingerprints. Simple binary filters (lowpass, bandpass, highpass, and contrast reversal) use the circular symmetry of fingerprint spectra to enhance the degraded fingerprints. Schlieren and Laplacian filters perform an edge enhancement on the fingerprint ridges. These techniques improved the identifiability of degraded fingerprints while maintaining the generality of the procedure and the integrity of the fingerprints. (Author)