Object detection in images with cluttered background by using local features and their configuration (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
In computer vision object detection is dealing with the problem to find certain objects in an image. Under controlled conditions the results of current systems are reliable. The absence of background clutter is such a condition. Problems arise if these conditions do not hold. In this paper we propose a method for overcoming the problem of background clutter by using a sensitive voting for objects and taking into account the position of local features. In an evaluation our proposed method clearly outperforms a naive object voting, by returning for 64% of the images the correct object compared to 4%.
- 2009-08-24
著者
-
Dengel Andreas
German Research Center for Artificial Intelligence(DFKI)
-
KLINKIGT Martin
Department of Computer Science and Intelligent Systems, Osaka Prefecture University
-
KISE Koichi
Department of Computer Science and Intelligent Systems, Osaka Prefecture University
-
Maus Heiko
German Research Center For Artificial Intelligence
-
Kise Koichi
Department Of Computer Science And Intelligent Systems Osaka Prefecture University
-
Kise Koichi
Department Of Computer Science And Intelligent Systems Graduate School Of Engineering Osaka Prefectu
-
Dengel Andreas
German Research Center For Artificial Intelligence
-
Klinkigt Martin
Department Of Computer Science And Intelligent Systems Osaka Prefecture University
-
Klinkigt Martin
Department Of Computer Science And Intelligent Systems Graduate School Of Engineering Osaka Prefecture University
関連論文
- ドイツ人工知能研究センター(DFKI)の20年 : 成功への道筋とそれを可能とした人々
- An Attempt of CUDA Implementation of PCA-SIFT(Internationa Session 6)
- Position detection for a camera pen using LLAH and dot patterns (パターン認識・メディア理解)
- Object detection in images with cluttered background by using local features and their configuration (パターン認識・メディア理解)
- Position detection for a camera pen using LLAH and dot patterns (ヒューマン情報処理)
- Is quantity better than quality?: a study case on a simple classifier applied to digit character recognition (パターン認識・メディア理解)
- Is quantity better than quality?: a study case on a simple classifier applied to digit character recognition (情報論的学習理論と機械学習)
- Copyright Protection of Images Based on Large-Scale Image Recognition(International Session 1)
- Document Image Retrieval for QA Systems Based on the Density Distributions of Successive Terms(Document Image Retrieval, Document Image Understanding and Digital Documents)
- Effectiveness of Passage-Based Document Retrieval for Short Queries(Special Issue on Text Processing for Information Access)
- Better Decision Boundary for Pattern Recognition with Supplementary Information(Pattem Recognition)
- Object recognition with less requirements (特集 電気関係学会関西連合大会)
- Object recognition with less requirements (特集 電気関係学会関西連合大会)
- Automatic Word Ground Truth Generation for Camera Captured Documents