چکیده مقاله
In this new method before the user enter to the Internet, his fingerprint is checked and allowed to enter the Internet This is performed in a way that it records checking times and scanning of fingerprint with his geographic position in which can be used for identification through fingerprint in Touch Screen Mobiles, Touch Screen Monitors, Laptops, and so on The identification based on biometric image, the comparison image is an important factor in estimating the total time of processing in addition to the processing time of a comparable single image Maeda et al proposes a detection algorithm that reduces the number of comparators image In this paper, in terms of time and accuracy evaluation algorithm SIFT features extracted palm print images Evaluation in this paper show that the algorithm is applicable to SIFT palm print based features However, the survey also proves that the algorithm requires an overhead of processing time depends on the size of the database We formulate quadratic matrix learning QML as a standard semidefinite programming SDP problem However, the conventional interior point SDP solvers do not scale well to the problem of QML for high dimensional data So, for a detection system with a large database, the processing time of an identification card by a simple application of algorithms reduced Maeda and colleagues
کلیدواژهها
نویسندگان
Yousef Farhang
Khoy Branch, Computer Engineering Department, İslamic Azad University, Khoy, Iran;
Maysam Alilou
Young Researchers and Elite Club, Science Islamic Azad University Khoy Branch Iran, Khoy
شیوه ارجاع
Farhang, Yousef and Alilou, Maysam,1395,Innovation for biometric algorithm,3rd National Congress of Electrical and Computer Engineering of Iran,Tehran
ارائهشده در
مجموعه مقالات سومین کنفرانس سراسری نوآوری های اخیر در مهندسی برق و کامپیوتر19 شهریور 1395 · تهران