Comparison of Feature Extraction Techniques for Handwritten Digit Recognition with a Photonic Reservoir Computer

被引：0

作者：

Antonik, Piotr ^{[1
,2
]}

Marsal, Nicolas ^{[1
,2
]}

Brunner, Daniel ^{[3
,4
]}

Rontani, Damien ^{[1
,2
]}

机构：

[1] Univ Paris Saclay, Cent Supelec, LMOPS EA 4423, F-57070 Metz, France

[2] Univ Lorraine, Cent Supelec, LMOPS, F-57000 Metz, France

[3] CNRS, Opt Dept, FEMTO ST Inst, F-25030 Besancon, France

[4] Univ Bourgogne Franche Comte, F-25030 Besancon, France

来源：

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: WORKSHOP AND SPECIAL SESSIONS | 2019年 / 11731卷

关键词：

Photonic reservoir computing; Handwritten digit classification; Feature extraction; MNIST dataset;

D O I：

10.1007/978-3-030-30493-5_19

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Reservoir computing is a bio-inspired computing paradigm for processing time-dependent signals. Its photonic implementations have received much interest recently, and have been successfully applied to speech recognition and time-series forecasting. However, few works have been devoted to the more challenging computer vision tasks. In this work, we use a large-scale photonic reservoir computer for classification of handwritten digits from the MNIST database. We investigate and compare different feature extraction techniques (such as zoning, Gabor filters, and HOG) and report classification errors of 1% experimentally and 0.8% in numerical simulations.

引用

下载

页码：175 / 179

页数：5

共 50 条

[41] Comparison of different preprocessing and feature extraction methods for offline recognition of handwritten arabic words
El Abed, Haikal
Maegner, Volker
ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2007, : 974 - 978
[42] Devanagari handwritten characters recognition using DCT, geometric and hue moments feature extraction techniques
Gaikwad, Snehal S.
Nalbalwar, S. L.
Nandgaonkar, A. B.
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2022, 47 (03):
[43] Deep Photonic Reservoir Computer for Speech Recognition
Picco, Enrico
Lupo, Alessandro
Massar, Serge
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, : 1 - 9
[44] Devanagari handwritten characters recognition using DCT, geometric and hue moments feature extraction techniques
Snehal S Gaikwad
S L Nalbalwar
A B Nandgaonkar
Sādhanā, 47
[45] Zoning Feature Extraction for Handwritten Java']Javanese Character Recognition
Herwanto, Heru Wahyu
Handayani, Anik Nur
Chandrika, Katya Lindi
Wibawa, Aji Prasetya
2019 INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONICS AND INFORMATION ENGINEERING (ICEEIE), 2019, : 264 - 268
[46] Hybrid feature extraction and feature selection for improving recognition accuracy of handwritten numerals
Zhang, P
Bui, TD
Suen, CY
EIGHTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS 1 AND 2, PROCEEDINGS, 2005, : 136 - 140
[47] Efficient Way of Feature Extraction for the Recognition of Handwritten Arabic Characters
Boulid, Youssef
Souhar, Abdelghani
Elkettani, Mohamed Youssfi
PROCEEDINGS OF SAI INTELLIGENT SYSTEMS CONFERENCE (INTELLISYS) 2016, VOL 2, 2018, 16 : 946 - 958
[48] Feature extraction with convolutional neural networks for handwritten word recognition
Bluche, Theodore
Ney, Hermann
Kermorvant, Christopher
2013 12TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2013, : 285 - 289
[49] Sensing Analysis of Feature Extraction Types for Handwritten Character Recognition
Gao, Jin-feng
Yao, Ru-xian
Zhang, Yu
Lai, Han
Zhang, Jun-ming
Chang, Ting-Cheng
SENSORS AND MATERIALS, 2020, 32 (05) : 1711 - 1729
[50] RECOGNITION OF HANDWRITTEN CHARACTERS BY TOPOLOGICAL FEATURE EXTRACTION AND MULTILEVEL CATEGORIZATION
TOU, JT
GONZALEZ, RC
IEEE TRANSACTIONS ON COMPUTERS, 1972, C 21 (07) : 776 - &

← 1 2 3 4 5 →