Modified high-order neural network for invariant pattern recognition

被引：32

作者：

Artyomov, E ^{[1
]}

Yadid-Pecht, O ^{[1
]}

机构：

[1] Ben Gurion Univ Negev, VLSI Syst Ctr, IL-84105 Beer Sheva, Israel

来源：

PATTERN RECOGNITION LETTERS | 2005年 / 26卷 / 06期

关键词：

HONN; high-order neural networks; invariant pattern recognition; binary patterns;

D O I：

10.1016/j.patrec.2004.09.029

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A modification for high-order neural networks (HONN) is described. The proposed modified HONN takes into account prior knowledge of the binary patterns that must be learned. This significantly reduces hence computation time as well as memory requirements for network configuration and weight storage. An "approximately equal triangles" scheme for weight sharing is also proposed. These modifications enable the efficient computation of HONNs for image fields of greater that 100 x 100 pixels without any loss of pattern information. (c) 2004 Elsevier B.V. All rights reserved.

引用

页码：843 / 851

页数：9

共 50 条

[21] A NOTE ON A HIGHER-ORDER NEURAL-NETWORK FOR DISTORTION-INVARIANT PATTERN-RECOGNITION
TAKANO, M
KANAOKA, T
SKRZYPEK, J
TOMITA, S
PATTERN RECOGNITION LETTERS, 1994, 15 (06) : 631 - 635
[22] Neural network for invariant recognition
Oparin, AN
Plekhanova, IV
Soloviov, NG
SECOND INTERNATIONAL CONFERENCE ON OPTICAL INFORMATION PROCESSING, 1996, 2969 : 132 - 135
[23] High-order MS_CMAC neural network
Jan, JC
Hung, SL
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (03): : 598 - 603
[24] Adaptive high order neural trees for pattern recognition
Foresti, GL
Christian, M
Snidaro, L
16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL II, PROCEEDINGS, 2002, : 877 - 880
[25] A Modified High-Order Neural Network with Smoothing L1 Regularization and Momentum Terms
Mohamed, Khidir Shaib
Suliman, Ibrhim M. A.
Alfeel, Mahmoud I.
Alhalangy, Abdalilah
Almostafa, Faiza A.
Adam, Ekram
SIGNAL IMAGE AND VIDEO PROCESSING, 2025, 19 (05)
[26] Noise robust and invariant object classification by the high-order statistical pattern spectrum
Foresti, GL
Gentili, S
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 1999, 13 (08) : 1219 - 1232
[27] Learnable high-order MGRF models for contrast-invariant texture recognition
Liu, Ni
Gimel'farb, Georgy
Delmas, Patrice
COMPUTER VISION AND IMAGE UNDERSTANDING, 2016, 143 : 135 - 146
[28] LOCAL VECTOR PATTERN IN HIGH-ORDER DERIVATIVE SPACE FOR FACE RECOGNITION
Hung, Tsung-Yung
Fan, Kuo-Chin
2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 239 - 243
[29] A neural network - Based integrated image processing environment for invariant pattern recognition
Ciuca, I
Ware, JA
WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL 1, PROCEEDINGS: ISAS '98, 1998, : 521 - 526
[30] Scale and rotation invariant pattern recognition using complex-log mapping and augmented second order neural network
Kwon, H.Y., 1600, (29):

← 1 2 3 4 5 →