A Comprehensive Evaluation Method of Palmprint Image Quality Based on Rank Sum Ratio Method

Abstract

The present invention relates to a method for comprehensively evaluating the quality of palmprint images based on the rank sum ratio method, comprising: step S01: performing a preliminary evaluation on the quality of palmprint images, and identifying palmprint images that do not meet the preliminary evaluation requirements as palmprint image quality The comprehensive evaluation is unqualified; step S02: block and number the palmprint image to form an evaluation sequence of palmprint image blocks; step S03: calculate each evaluation index of each palmprint image block respectively; step S04: adopt rank sum ratio method to compare All palmprint image blocks are comprehensively evaluated for quality; step S041: rank each evaluation index of the palmprint image blocks; step S042: define the rank sum ratio matrix of all palmprint image blocks; step S043: calculate each palmprint in sequence Block rank sum ratio; step S05: preset several rank sum ratio thresholds, count the number of palmprint image blocks greater than different thresholds, and determine the quality level of each palmprint image. The present invention can quickly and accurately complete the comprehensive evaluation of the quality of the palmprint image through the two-level evaluation mode of the preliminary evaluation of the quality of the palmprint image and the comprehensive evaluation of the quality of the palmprint image based on the rank sum ratio method.

Description

technical field [0001] The invention provides a comprehensive evaluation method of palmprint image quality based on a rank sum ratio method, which belongs to the field of biological feature recognition, and in particular relates to a palmprint recognition method. Background technique [0002] Compared with other biometric identification technologies, palmprint automatic recognition technology has excellent accuracy and high economic practicability, and its current application prospect is very clear. Palmprint image quality evaluation is one of the most direct and important factors affecting the accuracy of palmprint recognition. High-quality palmprint images can ensure that the palmprint recognition system can extract more palmprint feature data, allowing the palmprint comparison algorithm to more efficiently distinguish all palmprint data in the palmprint database. Although the palmprint image is similar to the fingerprint image in terms of texture and shape, and the commo...

AI Technical Summary

Problems solved by technology

[0004] The technical solution of the present invention is to solve the problem of palmprint image quality evaluation, to overcome the long evaluation time of the prior art; the pressure is uneven and the focus points are scattered; there is no scientific and effective evaluator shortage, and a method based on the rank sum ratio method is provided. Palmprint image quality comprehensive evaluation method, through the two-level evaluation mode of preliminary palmprint image quality evaluation and palmprint image quality comprehensive evaluation based on rank sum ratio method, the comprehensive evaluation of palmprint image quality can be completed quickly and accurately

Images