Comparative study of segmentation in monochrome facial images: snake pedals and template matching (パターン認識・メディア理解)
スポンサーリンク
概要
- 論文の詳細を見る
The snake pedal model is a rather new active contour algorithm used for segmentation in 2D and 3D digital images, and has been employed with good results in medical imaging. However, its use on other typical images, like facial images, has not been studied deeply. In this paper we evaluate the snake pedal model applied to face segmentation, and more specifically, to parameter extraction, i.e., face aspect ratio, face area and position. We compare its results with the ones of a template matching method. Results indicate that the snake pedal model outperforms the template matching model in face area estimation.
- 社団法人電子情報通信学会の論文
- 2007-08-27
著者
-
OHYA Jun
Waseda University, GITS Faculty
-
Ohya Jun
Waseda Univ.
-
Ohya Jun
Waseda University
-
Perez Claudio
Universidad De Chile
-
Ramirez Carolina
Waseda University
関連論文
- Parallel forward projection of large voxel-volumes on the GPU (放送技術)
- Parallel forward projection of large voxel-volumes on the GPU (オーディオビジュアル複合情報処理)
- Parallel forward projection of large voxel-volumes on the GPU (通信方式)
- Parallel forward projection of large voxel-volumes on the GPU (画像工学)
- Stakeholder system and analysis of extended producer responsibility based on game theory (情報システムと社会環境)
- H-024 Validation of the Snake Pedal Model applied to Face Segmentation in Monochromatic Images
- Study of different image features used for recognizing unknown person's activity based on tensor decomposition approach (コンピュータビジョンとイメージメディア)
- Study of different image features used for recognizing unknown person's activity based on tensor decomposition approach (ヒューマン情報処理)
- Study of different image features used for recognizing unknown person's activity based on tensor decomposition approach (パターン認識・メディア理解)
- J-024 Tensor Decomposition Framework For Recognizing an Unknown Person's Action From A Video Sequence Using Image Features
- D-12-122 Implementation of a Video Sequence Based System for Recognizing an Unknown Person's Gesture by a Tensor Decomposition Based Approach
- Comparative study of segmentation in monochrome facial images: snake pedals and template matching (コンピュータビジョンとイメージメディア)
- Comparative study of segmentation in monochrome facial images: snake pedals and template matching (ヒューマン情報処理)
- Comparative study of segmentation in monochrome facial images: snake pedals and template matching (パターン認識・メディア理解)
- A modified RANSAC based method for extracting primitive shapes from image (コンピュータビジョンとイメージメディア)
- Staff removal for square musical notation manuscripts OCR: an experiment on the binarization and staff detection stage (パターン認識・メディア理解)
- D-4-6 Analysis-based Participant Selection Scheme in Workflow Management System(D-4. データ工学, 情報・システム1)
- D-12-49 Local Adaptive Thresholding Study for Early Musical Manuscripts OMR
- A Modified RANSAC mechanism : Multiple models extraction algorithm
- A Modified RANSAC mechanism : Multiple models extraction algorithm
- G-013 Incorporating Zoom Motion Estimation in Video Compression : A More General Approach for Motion Compensated Predictive Coding