A research for Comic Image Analysis and Character Detection Methods
| Project/Area Number |
24700100
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | Waseda University |
|---|
Principal Investigator |
ISHII Daisuke 早稲田大学, 理工学術院, 助手 (40581525)
|
|---|
| Project Period (FY) |
2012-04-01 – 2014-03-31
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2013: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2012: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | 画像解析 / マンガ / 画像特徴量 / メタデータ / 2値画像 / 細線化 / 機械学習 / マンガ解析処理 / 人物識別 / 人物検出 |
|---|
| Research Abstract |
Manga (Japanese style Comics) is one of an important content of Japan. For simplicity to use information of contents/stories of comics, it is important to analyze comic components. In this research, we studied image analysis methods for comic character detection and identification. We discussed about the detection method that use EYE-FACE cascade classifier consisted by HOG feature for character face detection from comic images. Then, through analysis examinations, we confirmed that the classifier with HOG can be obtained high accuracy ratio than Haar-like for face detection from comic images. Also character initialization and detection is constructed same method. Moreover, we discussed image analysis method for binary thinned comic images to increase comic analysis accuracy.
|
Report
(3 results)
Research Products
(13 results)
