COMPUTATIONAL INTELLIGENCE FOR SHOEPRINT RECOGNITION

被引：5

作者：

Acevedo Mosqueda, M. E. ^{[1
]}

Acevedo Mosqueda, M. A. ^{[1
]}

Carreno Aguilera, R. ^{[2
]}

Martinez Zuniga, F. ^{[1
]}

Pacheco Bautista, D. ^{[2
]}

Patino Ortiz, M. ^{[1
]}

Yu, Wen ^{[3
]}

机构：

[1] Inst Politecn Nacl, Escuela Super Ingn Mecan & Elect Zacatenco, Mexico City, DF, Mexico

[2] Univ Istmo, Cd Univ S-N, Tehuantepec 70760, Oaxaca, Mexico

[3] Inst Politecn Nacl, CINVESTAV, Mexico City, DF, Mexico

来源：

FRACTALS-COMPLEX GEOMETRY PATTERNS AND SCALING IN NATURE AND SOCIETY | 2019年 / 27卷 / 04期

关键词：

Forensic Science; Computational Forensics; Computational Intelligence; Associative Models; Morphological Associative Memories; Shoeprint Recognition;

D O I：

10.1142/S0218348X19500804

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

Shoeprint marks present valuable information for forensic investigators to resolve a crime. These marks can be helpful to find the brand of the shoe and can make the investigation easier. In this paper, we present an associative model-based algorithm to match noisy shoeprint patterns with a brand of shoe. The shoeprints are corrupted with additive, subtractive and mixed noises. A particular case of subtractive noise are partial shoeprints such as toe, heel, left-half and right-half prints. The Morphological Associative Memories (MAMs) were applied. Both memories, max and min, recognize noisy shoeprints corrupted with 98% additive and subtractive noise, respectively, with an effectiveness of 100%. The images corrupted with mixed noise were recognized when the additive or subtractive noise applied was greater than the mixed noise; in this case, the recalling was around 70%, otherwise, both memories failed to recognize the shoeprints.

引用

页数：13

共 21 条

[1] Acevedo E., 2013, RES COMPUT SCI, V68, P91
[2] ANDERSON J A, 1972, Mathematical Biosciences, V14, P197, DOI 10.1016/0025-5564(72)90075-2
[3] Bouridane A, 2000, IEEE IMAGE PROC, P474, DOI 10.1109/ICIP.2000.900998
[4] An Automatic Shoeprint Retrieval Method Using Neural Codes for Commercial Shoeprint Scanners
Cui, Junjian
Zhao, Xiaorui
Li, Daixi
[J]. COMPUTER VISION, PT II, 2017, 772 : 158 - 169
[5] Robust Shoeprint Retrieval Method Based on Local-to-Global Feature Matching for Real Crime Scenes
Cui, Junjian
Zhao, Xiaorui
Liu, Nini
Morgachev, Sergey
Li, Daixi
[J]. JOURNAL OF FORENSIC SCIENCES, 2019, 64 (02) : 422 - 430
[6] Deshmukh M.P., 2009, INT J COMPUT SCI COM, V2, P281
[7] Dong Y., 2016, INT J ENG RES SCI, V2, P167
[8] Fajri P. S., 2014, STUD COMPUT INTELL, V555, P1
[9] Ferreira A, 2014, RES COMPUTING SCI, V78, P111
[10] NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES
HOPFIELD, JJ
[J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08): : 2554 - 2558

← 1 2 3 →