Object Verification via Mining Visual Patterns
-
- TARASHIMA Shuhei
- NTT Media Intelligence Laboratories, NTT Corporation
-
- HOSONO Takashi
- NTT Media Intelligence Laboratories, NTT Corporation
-
- WATANABE Yukito
- NTT Media Intelligence Laboratories, NTT Corporation
-
- KUROZUMI Takayuki
- NTT DATA Corporation
-
- SHIMAMURA Jun
- NTT Media Intelligence Laboratories, NTT Corporation
-
- KINEBUCHI Tetsuya
- NTT Media Intelligence Laboratories, NTT Corporation
Bibliographic Information
- Other Title
-
- 局所ビジュアルパターンの抽出に基づく物体の変形に頑健な同一性判定
Description
In this paper we propose a novel object verification method based on mining local visual patterns lying in a image pair. Our method is robust to object deformation because (i) any number of local visual patterns can be mined independently of their locations and (ii) each pattern is extracted via clustering of the correspondence graph that embeds geometric similarities of keypoint quadruplets. We validate our approach in an experiment of detecting deformed planar objects in a noisy image collection.
Journal
-
- PROCEEDINGS OF THE ITE WINTER ANNUAL CONVENTION
-
PROCEEDINGS OF THE ITE WINTER ANNUAL CONVENTION 2017 (0), 15B-7-, 2017
The Institute of Image Information and Television Engineers
- Tweet
Details 詳細情報について
-
- CRID
- 1390856815735561216
-
- ISSN
- 24242306
- 13434357
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Disallowed
