Performance comparison of feature extraction methods for neural network based object recognition

被引：0

作者：

Neubauer, C ^{[1
]}

Fang, M ^{[1
]}

机构：

[1] Siemens Corp Res Inc, Princeton, NJ 08540 USA

来源：

PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3 | 2002年

关键词：

D O I：

10.1109/IJCNN.2002.1007758

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Preprocessing and feature extraction can significantly enhance the performance of a neural network based classifier. In this paper several feature extraction techniques including edge filters, local features and distance transformation are selected for image preprocessing in order to improve the recognition accuracy in combination with a neural network classifier. The visual object recognition performance of these algorithms is extensively compared based on a real world data set with significant variation of viewpoint and illumination.

引用

页码：1608 / 1613

页数：2

共 50 条

[41] Comparison of Speaker Adaptation Methods as Feature Extraction for SVM-Based Speaker Recognition
Ferras, Marc
Leung, Cheung-Chi
Barras, Claude
Gauvain, Jean-Luc
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2010, 18 (06): : 1366 - 1378
[42] A Performance Comparison of Feature Extraction Methods for Sentiment Analysis
Hung, Lai Po
Alfred, Rayner
ADVANCED TOPICS IN INTELLIGENT INFORMATION AND DATABASE SYSTEMS, 2017, 710 : 379 - 390
[43] A review of three neural network methods for manufacturing feature recognition
Shi Y.
Zheng G.
Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica, 2019, 40 (09):
[44] Comparison between handcraft feature extraction and methods based on Recurrent Neural Network models for gesture recognition by instrumented gloves: A case for Brazilian Sign Language Alphabet
Dias, Thiago Simoes
Mendes Junior, Jose Jair Alves
Pichorim, Sergio Francisco
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 80
[45] Feature extraction methods for neural network-based transmission line fault discrimination
Websper, S
Dunn, RW
Aggarwal, RK
Johns, AT
Bennett, A
IEE PROCEEDINGS-GENERATION TRANSMISSION AND DISTRIBUTION, 1999, 146 (03) : 209 - 216
[46] A neural network based ATC assessment incorporating novel feature selection and extraction methods
Othman, MM
Mohamed, A
Hussain, A
ELECTRIC POWER COMPONENTS AND SYSTEMS, 2004, 32 (11) : 1121 - 1136
[47] Analysis of similar object classification performance of deep neural network-based object recognition technique
Kim S.-H.
Journal of Institute of Control, Robotics and Systems, 2021, 27 (11) : 858 - 863
[48] Pattern recognition without feature extraction using probabilistic neural network
Polat, Ovunc
Yildirim, Tulay
INTELLIGENT COMPUTING IN SIGNAL PROCESSING AND PATTERN RECOGNITION, 2006, 345 : 402 - 409
[49] Radar Based Object Recognition with Convolutional Neural Network
Loi, Kin Chong
Cheong, Pedro
Choi, Wai Wa
PROCEEDINGS OF THE 2019 IEEE ASIA-PACIFIC MICROWAVE CONFERENCE (APMC), 2019, : 87 - 89
[50] Face recognition using deep learning feature injection: An accurate hybrid network combining neural networks based on feature extraction with convolutional neural network
Sisco, Yilber J.
Carmona, Rhadames
2022 XVLIII LATIN AMERICAN COMPUTER CONFERENCE (CLEI 2022), 2022,

← 1 2 3 4 5 →