A Writer Adaptation Method for Isolated Handwritten Digit Recognition Based on Ensemble Projection of Features

被引：0

作者：

Hosseinzadeh, Hamidreza ^{[1
]}

Razzazi, Farbod ^{[1
]}

机构：

[1] Islamic Azad Univ, Sci & Res Branch, Dept Elect & Comp Engn, Tehran, Iran

来源：

2015 2ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION AND IMAGE ANALYSIS (IPRIA) | 2015年

关键词：

writer adaptation; domain adaptation; handwriting recognition; feature learning; ensemble learning; STYLE;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Learning handwriting categories fail to perform well when trained and tested on data from different databases. In this paper, we propose a novel framework of Ensemble Projection (EP) for writer adaptation. We employed EP as a feature transformation method which can be combined with different types of classifiers for unsupervised and semi-supervised adaptation. Experiments on a handwritten digit dataset demonstrate that EP learning can increase recognition rates significantly, both in the unsupervised and semi-supervised cases.

引用

页数：5

共 50 条

[41] Handwritten Digit Recognition Based on Pooling SVM-Classifiers Using Orientation and Concavity Based Features
Saavedra, Jose M.
PROGRESS IN PATTERN RECOGNITION IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2014, 2014, 8827 : 658 - 665
[42] Handwritten Digit Recognition Based on a New Combination Feature
Zhang, Xinbo
Wu, Lili
ASIA-PACIFIC YOUTH CONFERENCE ON COMMUNICATION TECHNOLOGY 2010 (APYCCT 2010), 2010, : 826 - 829
[43] Handwritten Digit Recognition: Hyperparameters-Based Analysis
Albahli, Saleh
Alhassan, Fatimah
Albattah, Waleed
Khan, Rehan Ullah
APPLIED SCIENCES-BASEL, 2020, 10 (17):
[44] A genetic algorithm based region sampling for selection of local features in handwritten digit recognition application
Das, Nibaran
Sarkar, Ram
Basu, Subhadip
Kundu, Mahantapas
Nasipuri, Mita
Basu, Dipak Kumar
APPLIED SOFT COMPUTING, 2012, 12 (05) : 1592 - 1606
[45] A selective attention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition
Salah, AA
Alpaydin, E
Akarun, L
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (03) : 420 - 425
[46] Improved method of handwritten digit recognition tested on MNIST database
Kussul, E
Baidyk, T
IMAGE AND VISION COMPUTING, 2004, 22 (12) : 971 - 981
[47] Projection-Based Features: A Superior Domain for Handwritten Bangla Basic Characters Recognition
Kabir, Kazi Lutful
Shafin, Md. Kishwar
Anannya, Tasmiah Tamzid
Debnath, Deepon
Kabir, Md. Rayhan
Islam, Md. Aminul
Sarwar, Hasan
PROCEEDINGS OF 2015 IEEE 9TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND CONTROL (ISCO), 2015,
[48] Bangla Handwritten Digit Classification and Recognition Using SVM Algorithm with HOG Features
Rehana, Hasin
2017 3RD INTERNATIONAL CONFERENCE ON ELECTRICAL INFORMATION AND COMMUNICATION TECHNOLOGY (EICT 2017), 2017,
[49] Handwritten digit recognition with a novel vision model that extracts linearly separable features
Teow, LN
Loe, KF
IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, VOL II, 2000, : 76 - 81
[50] A genetic algorithm based feature selection for handwritten digit recognition
Ahlawat S.
Rishi R.
Recent Patents on Computer Science, 2019, 12 (04) : 304 - 316

← 1 2 3 4 5 →