Relative color polygons for object detection and recognition

Authors:
Thi Thi Zin;Sung Shik Koh;Hiromitsu Hama
Affiliations:
Graduate School of Engineering, Osaka City University, Osaka-shi, Japan;Graduate School of Engineering, Osaka City University, Osaka-shi, Japan;Graduate School of Engineering, Osaka City University, Osaka-shi, Japan
Venue:
RSCTC'06 Proceedings of the 5th international conference on Rough Sets and Current Trends in Computing
Year:
2006

Citing 8
Cited 0

Color indexing

International Journal of Computer Vision
Color Constant Color Indexing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detection of Norwegian Speed Limit Signs

Proceedings of the 16th European Simulation Multiconference on Modelling and Simulation 2002
Indexing Colored Surfaces in Images

ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
Road Signs Recognition Using a Dynamic Pixel Aggregation Technique in the HSV Color Space

ICIAP '01 Proceedings of the 11th International Conference on Image Analysis and Processing
Color Recognition in Outdoor Images

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Linear color segmentation and its implementation

Computer Vision and Image Understanding - Special issue on color for image indexing and retrieval
Color-contrast landmark detection and encoding in outdoor images

CAIP'05 Proceedings of the 11th international conference on Computer Analysis of Images and Patterns

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new framework of the color model for outdoor scene image detection and recognition. This model enables us to manipulate easily the color of an image. Here, the concept of ‘relative color polygon’ for an object composed of uniform color regions is introduced on a 2D color space (XY space). Then the color similarity is defined using three kinds of parameters of the polygon: length and slope of every side and angle of adjacent sides. This paper addresses how to decide the color similarity by using the facts about color shifting on the XY space. The feasibility of the proposed framework has been confirmed through the experimental results using outdoor scene images taken under a great variety of various illumination conditions.