Browse Prior Art Database

Fingerprint Classification and Identification

IP.com Disclosure Number: IPCOM000094076D
Original Publication Date: 1966-May-01
Included in the Prior Art Database: 2005-Mar-06
Document File: 2 page(s) / 19K

Publishing Venue

IBM

Related People

Malek, K: AUTHOR

Abstract

This method broadly classifies fingerprint patterns. Each fingerprint is first divided into a matrix of cells. The number of ridge crossings per cell is then determined by an automatic raster scan such as by use of a flying spot scanner. The scan should, for example, be of the type indicated in the preceding article, so that the slope of the lines can be determined. A positive slope value is then assigned to ridges sloping, for example, from lower left to upper right. A negative slope value is assigned to ridges sloping from lower right to upper left. A vertical ridge is considered as having a zero slope.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 76% of the total text.

Page 1 of 2

Fingerprint Classification and Identification

This method broadly classifies fingerprint patterns. Each fingerprint is first divided into a matrix of cells. The number of ridge crossings per cell is then determined by an automatic raster scan such as by use of a flying spot scanner. The scan should, for example, be of the type indicated in the preceding article, so that the slope of the lines can be determined. A positive slope value is then assigned to ridges sloping, for example, from lower left to upper right. A negative slope value is assigned to ridges sloping from lower right to upper left. A vertical ridge is considered as having a zero slope.

The number of ridge crossings per cell are then recorded, with the appropriate sign, in a matrix of the type shown. When ridges having both positive and negative slope appear in the same cell, an algebraic addition is performed. The result of this addition is recorded in the cell with the appropriate sign.

The matrix is then examined for the cell interfaces at which the ridge count changes its sign. Boundary lines, such as line 12, are then drawn through these interfaces. The shape of these boundary lines can be used to indicate, under certain conditions, the type of fingerprint being looked at. For example, the boundary line for a properly oriented arch is nearly a straight line. The boundary for a whorl is four lines radiating from a common point. The boundary line for a loop is a curved line, such as line 12 shown...