Watching pattern distribution via massive character recognition

Seiichi Uchida, Wenjie Cai, Akira Yoshida, Yaokai Feng

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

抄録

The purpose of this paper is to analyze how image patterns distribute inside their feature space. For this purpose, 832,612 manually ground-truthed handwritten digit patterns are used. Use of character patterns instead of general visual object patterns is very essential for our purpose. First, since there are only 10 classes for digits, it is possible to have an enough number of patterns per class. Second, since the feature space of small binary character images is rather compact, it is easier to observe the precise pattern distribution with a fixed number of patterns. Third, the classes of character patterns can be defined far more clearly than visual objects. Through nearest neighbor analysis on 832, 612 patterns, their distribution in the 32 x 32 binary feature space is observed quantitatively and qualitatively. For example, the visual similarity of nearest neighbors and the existence of outliers, which are surrounded by patterns from different classes, are observed.

本文言語英語
ホスト出版物のタイトル2011 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2011
DOI
出版ステータス出版済み - 2011
イベント21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011 - Beijing, 中国
継続期間: 9 18 20119 21 2011

出版物シリーズ

名前IEEE International Workshop on Machine Learning for Signal Processing

その他

その他21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011
国/地域中国
CityBeijing
Period9/18/119/21/11

All Science Journal Classification (ASJC) codes

  • 人間とコンピュータの相互作用
  • 信号処理

フィンガープリント

「Watching pattern distribution via massive character recognition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル