# US 10,872,255 B2 · Method of processing biometric image and apparatus including the same > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,255 B2 - Document ID: US10872255B2 - Status: Granted - Kind: B2 - Application number: 16/059,828 - Filed: 2018-08-09 - Published: 2019-02-14 - Granted: 2020-12-22 - Earliest claimed: 2017-08-14 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Hyoseok Hwang; Jingu Heo; Byungkyu Lee - Web page: https://patentgrep.com/patent/US10872255B2 ## CPC - G06V 40/13: Sensors therefor - G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} - G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints - G06V 10/98: Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns - G06V 40/70: Multimodal biometrics, e.g. combining information from different biometric modalities - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Provided are a biometric image processing method and an apparatus including the same. The biometric image processing method includes acquiring a biometric image from a biometric sensor, evaluating image quality of the biometric image by calculating an evaluation score with respect to each of a plurality of evaluation items corresponding to the biometric image, determining at least one of an improvement algorithm corresponding to an evaluation result and a weight of the improvement algorithm by using an image quality improvement table including an improvement degree of image quality, and correcting the biometric image according to the at least one of the improvement algorithm and determined weight of the improvement algorithm. ## Claims ### Claim 1 A method of processing a biometric image, the method comprising: acquiring a biometric image from a biometric sensor; evaluating image quality of the biometric image by calculating a plurality of evaluation scores, each of the plurality of evaluation scores independently corresponding to one of a plurality of evaluation items corresponding to the biometric image, and each of the plurality of evaluation scores calculated based on an authentication rate; determining at least one of an improvement algorithm corresponding to each of the plurality of evaluation scores and a weight of the improvement algorithm by using an image quality improvement table comprising an improvement degree of image quality; and correcting the biometric image according to the at least one of the improvement algorithm and the weight of the improvement algorithm. ### Claim 2 (depends on 1) The method of claim 1, wherein the evaluating the image quality of the biometric image comprises: calculating a plurality of evaluation values of the biometric image with respect to each of the plurality of evaluation items, based on a pixel value of the biometric image; and converting the plurality of evaluation values into the plurality of evaluation scores. ### Claim 3 (depends on 2) The method of claim 2, wherein the converting of the plurality of evaluation values into the plurality of evaluation scores comprises: calculating a correlation between the respective evaluation value and the respective authentication rate by linear regression. ### Claim 4 (depends on 3) The method of claim 3, wherein the authentication rate is based on a similarity between images which are similar in terms of the evaluation value. ### Claim 5 (depends on 1) The method of claim 1, wherein the image quality improvement table represents an improvement degree according to an evaluation item and an improvement algorithm. ### Claim 6 (depends on 5) The method of claim 5, wherein the image quality improvement table comprises: a first image quality improvement table representing a first improvement degree according to a first evaluation item and a first improvement algorithm; a second image quality improvement table representing a second improvement degree according to the first evaluation item and a second improvement algorithm; a third image quality improvement table representing a third improvement degree according to a second evaluation item and a third improvement algorithm; and a fourth image quality improvement table representing a fourth improvement degree according to the second evaluation item and a fourth improvement algorithm. ### Claim 7 (depends on 1) The method of claim 1, wherein the improvement degree is subdivided by at least one of grade of the evaluation item and weight of the improvement algorithm. ### Claim 8 (depends on 1) The method of claim 1, wherein the improvement degree comprises an expected evaluation score of the biometric image when a particular improvement algorithm of a particular weight is applied to a biometric image having a particular grade of a particular evaluation item. ### Claim 9 (depends on 1) The method of claim 1, wherein the determining the at least one of the improvement algorithm corresponding to the plurality of evaluation scores and the weight of the improvement algorithm comprises: determining the improvement algorithm based on a comparison between the plurality of evaluation scores and the improvement degree; and determining the weight of the improvement algorithm by using the image quality improvement table. ### Claim 10 (depends on 9) The method of claim 9, wherein the determining of the improvement algorithm comprises: determining, as the improvement algorithm, an improvement algorithm of the image quality improvement table when an improvement degree corresponding to one of the plurality of evaluation scores from the image quality improvement table is equal to the respective evaluation score or greater than the respective evaluation score by a first reference value. ### Claim 11 (depends on 9) The method of claim 9, wherein the determining of the weight comprises: determining, as the weight, a weight in a case where a sum or an average of the improvement degree with respect to each evaluation item in the image quality improvement table is a maximum sum or average. ### Claim 12 (depends on 1) The method of claim 1, wherein the determining of the at least one of the improvement algorithm and the weight of the improvement algorithm is performed when at least one of the plurality of evaluation scores with respect to each of the plurality of evaluation items is equal to or smaller than a second reference value. ### Claim 13 (depends on 1) The method of claim 1, wherein the calculating the evaluation score with respect to each of the plurality of evaluation items corresponding to the biometric image comprises: calculating a first evaluation score corresponding to a first evaluation item, which represents a first type of image quality of the biometric image, and calculating a second evaluation score corresponding to a second evaluation item, which represents a second type of image quality of the biometric image. ### Claim 14 (depends on 1) The method of claim 1, wherein the determining the at least one of the improvement algorithm corresponding to the evaluation score and the weight of the improvement algorithm comprises: obtaining a first improvement algorithm and a first weight for the first improvement algorithm based on the first evaluation score; and obtaining a second improvement algorithm and a second weight for the second improvement algorithm based on the second evaluation score. ### Claim 15 An electronic apparatus comprising: a biometric sensor configured to detect a biometric image from an object; and a processor configured to: acquire the biometric image from the biometric sensor, evaluate image quality of the biometric image by calculating a plurality of evaluation scores, each of the plurality of evaluation scores independently corresponding to one of a plurality of evaluation items corresponding to the biometric image, and each of the plurality of evaluation scores calculated based on an authentication rate; determine at least one of an improvement algorithm corresponding to each of the plurality of evaluation scores and a weight of the improvement algorithm by using an image quality improvement table comprising an improvement degree of image quality; and correct the biometric image according to the determined at least one of the improvement algorithm and weight of the improvement algorithm. ### Claim 16 (depends on 15) The electronic apparatus of claim 15, wherein the processor is further configured to: calculate a plurality of evaluation values of the biometric image with respect to each of the plurality of evaluation items, based on a pixel value of the biometric image; and convert the plurality of evaluation values into the plurality of evaluation scores. ### Claim 17 (depends on 16) The electronic apparatus of claim 16, wherein the processor is further configured to: convert the plurality of evaluation values into the plurality of evaluation scores by calculating a correlation between the respective evaluation value and the respective authentication rate by linear regression. ### Claim 18 (depends on 17) The electronic apparatus of claim 17, wherein the authentication rate is based on a similarity between images that are similar in terms of the evaluation value. ### Claim 19 (depends on 15) The electronic apparatus of claim 15, wherein the image quality improvement table represents an improvement degree according to an evaluation item and an improvement algorithm. ### Claim 20 (depends on 19) The electronic apparatus of claim 19, wherein the improvement degree is subdivided by at least one of grade of the evaluation item and weight of the improvement algorithm. ### Claim 21 (depends on 19) The electronic apparatus of claim 19, wherein the improvement degree comprises an expected evaluation score of the biometric image when a particular improvement algorithm of a particular weight is applied to a biometric image having a particular grade of a particular evaluation item. ### Claim 22 (depends on 15) The electronic apparatus of claim 15, wherein the processor is further configured to: determine the improvement algorithm based on a comparison between the plurality of evaluation scores and the improvement degree; and determine the weight of the improvement algorithm by using the image quality improvement table. ### Claim 23 (depends on 22) The electronic apparatus of claim 22, wherein the processor is further configured to: determine, as the improvement algorithm, an improvement algorithm of the image quality improvement table when an improvement degree corresponding to one of the plurality of evaluation scores from the image quality improvement table is equal to the respective evaluation score or greater than the respective evaluation score by a first reference value. ### Claim 24 (depends on 22) The electronic apparatus of claim 22, wherein the processor is further configured to: determine, as the weight, a weight in a case where a sum or an average of the improvement degree with respect to each evaluation item in the image quality improvement table is a maximum sum or average. ### Claim 25 (depends on 15) The electronic apparatus of claim 15, wherein the processor is further configured to: determine the at least one of the improvement algorithm and the weight of the improvement algorithm when at least one of the plurality of evaluation scores with respect to each of the plurality of evaluation items is equal to or smaller than a second reference value. ### Claim 26 (depends on 15) The electronic apparatus of claim 15, wherein the processor is further configured to authenticate the corrected biometric image by comparing the corrected biometric image with an authentication template. ### Claim 27 (depends on 15) The electronic apparatus of claim 15, wherein the biometric image comprises one of a fingerprint image, an iris image, a sweat gland image, a blood vessel image, and a face image. ### Claim 28 An electronic apparatus comprising: a processor configured to: acquire an image, calculate a plurality of evaluation scores, each of the plurality of evaluation scores independently corresponding to one of a plurality of evaluation items corresponding to the biometric image, and each of the plurality of evaluation scores calculated based on an authentication rate, determine an improvement algorithm corresponding to each of the plurality of evaluation scores, and correct the image according to the determined improvement algorithm.