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

页码：175 / 179

页数：5

共 50 条

[21] Feature extraction and classification techniques for handwritten Devanagari text recognition: a survey
Sukhjinder Singh
Naresh Kumar Garg
Munish Kumar
Multimedia Tools and Applications, 2023, 82 : 747 - 775
[22] Efficient Feature Extraction Techniques for Offline Handwritten Gurmukhi Character Recognition
Kumar, Munish
Sharma, R. K.
Jindal, M. K.
NATIONAL ACADEMY SCIENCE LETTERS-INDIA, 2014, 37 (04): : 381 - 391
[23] Feature extraction and classification techniques for handwritten Devanagari text recognition: a survey
Singh, Sukhjinder
Garg, Naresh Kumar
Kumar, Munish
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (01) : 747 - 775
[24] Comparison of Feature Extraction Techniques for Handwriting Recognition
Bartos, Gaye Ediboglu
Hajnal, Eva
Hoscan, Yasar
2018 IEEE 12TH INTERNATIONAL SYMPOSIUM ON APPLIED COMPUTATIONAL INTELLIGENCE AND INFORMATICS (SACI), 2018, : 405 - 410
[25] FPGA Implementation of Feature Extraction and MLP Neural Network Classifier for Farsi Handwritten Digit Recognition
Moradi, Marzieh
Poormina, Mohammad Ali
Razzazi, Farbod
2009 THIRD UKSIM EUROPEAN SYMPOSIUM ON COMPUTER MODELING AND SIMULATION (EMS 2009), 2009, : 231 - 234
[26] A genetic algorithm based feature selection for handwritten digit recognition
Ahlawat S.
Rishi R.
Recent Patents on Computer Science, 2019, 12 (04) : 304 - 316
[27] Offline Handwritten Numeral Recognition using Combination of Different Feature Extraction Techniques
Munish Kumar
M. K. Jindal
R. K. Sharma
Simpel Rani Jindal
National Academy Science Letters, 2018, 41 : 29 - 33
[28] Offline Handwritten Numeral Recognition using Combination of Different Feature Extraction Techniques
Kumar, Munish
Jindal, M. K.
Sharma, R. K.
Jindal, Simpel Rani
NATIONAL ACADEMY SCIENCE LETTERS-INDIA, 2018, 41 (01): : 29 - 33
[29] A handwritten digit recognition algorithm using two-dimensional hidden markov models for feature extraction
Wierer, Jay
Boston, Nigel
2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PTS 1-3, 2007, : 505 - +
[30] Handwritten digit recognition: benchmarking of state-of-the-art techniques
Liu, CL
Nakashima, K
Sako, H
Fujisawa, H
PATTERN RECOGNITION, 2003, 36 (10) : 2271 - 2285

← 1 2 3 4 5 →