手書き数字認識におけるデータベースの大規模化の効果

Translated title of the contribution: An Experimental Study toward Massive Character Recognition

吉田 晃, 蔡 文傑, ヤオカイ フォン, 内田 誠一

Research output: Contribution to journalArticlepeer-review

Abstract

In pattern recognition, to increase the number of prototypes is a simple method to improve accuracy. In this paper, we use over 830,000 manually labeled handwriting patterns, and we examine an effect of the number of prototypes on the handwriting numeral recognition. The analysis result showed the error rate decreases about 40% by increasing the number of prototypes 10 times. Other analysis results showed the changing situation of feature space when the number of prototypes increased.
Translated title of the contributionAn Experimental Study toward Massive Character Recognition
Original languageJapanese
Pages (from-to)119-124
Number of pages6
JournalIEICE technical report
Volume110
Issue number330
Publication statusPublished - Dec 2 2010

Fingerprint

Dive into the research topics of 'An Experimental Study toward Massive Character Recognition'. Together they form a unique fingerprint.

Cite this