A High Speed Contour Fill Method for Character Image Generation (Special Issue on Document Analysis and Recognition)
スポンサーリンク
概要
- 論文の詳細を見る
This paper proposes a new, high-speed method of filling in the contours of alpha-numeric characters to produce correct binary image patterns. We call this method the improved edge-fill method because it improves on a previously developed edge-fill method. Ambiguity of the conventional edge-fill method on binary images are eliminated by selecting fill pixels from combinations of Freeman's chain code, which expresses contour lines. Consequently, the areas inside the contour lines are filled in rapidly and correctly. With the new method, the processing time for character image generation is reduced by ten to twenty percent over the conventional method. The effectiveness of the new method is examined in experiments using both Arabic numerals and letters from the Roman alphabet. Results show that this fill method is able to produce correct image patterns and that it can be applied to alpha-numeric-character contour filling.
- 社団法人電子情報通信学会の論文
- 1994-07-25
著者
-
Koga Masashi
Central Research Laboratory Hitachi Ltd.
-
Nakano Yasuaki
Faculty Of Engineering Shinshu University
-
Nakashima Kazuki
Central Research Laboratory Hitachi Ltd.
-
Marukawa Katsumi
Central Research Laboratory, Hitachi, Ltd.
-
Shima Yoshihiro
Central Research Laboratory, Hitachi, Ltd.
-
Marukawa Katsumi
Central Research Laboratory Hitachi Ltd.
-
Shima Yoshihiro
Central Research Laboratory Hitachi Ltd.
関連論文
- Segmentation of Handwritten Kanji Numerals Integrating Features by Bayesian Rule
- Note Symbol Extraction for Printed Piano Scores Using Neural Networks (Special Issue on Character Recognition and Document Understanding)
- A High Speed Contour Fill Method for Character Image Generation (Special Issue on Document Analysis and Recognition)
- Cursive Handwritten Word Recognition Using Multiple Segmentation Determined by Contour Analysis (Special Issue on Character Recognition and Document Understanding)