Title
Color Sectors and Edge Features for Content-Based Image Retrieval
Abstract
We provide a new image retrieval model which integrates the spatial distributing information of colors and the shape features. The color features are represented by an amelioration of HSV color model: color sector. To describe the relative position and orientation of objects within the image, hue edges in the image, computed using Canny approach, are processed by Hough transform to generate the spatial histogram which is used as shape representation. To address matching of image, we define two global distance measures based on the accumulative distance and vector-based distance to compare the similarity of two images. Experimental results indicate that our approach provides higher retrieval rate than that of single feature (color), is a better tradeoff between high efficiency and reasonable precision. Key words: image retrieval; retrieval model; color model; Hough transform.
Year
DOI
Venue
2007
10.1109/FSKD.2007.220
FSKD (3)
Keywords
Field
DocType
color feature,color model,higher retrieval rate,color sector,accumulative distance,edge features,image retrieval,color sectors,global distance,hsv color model,retrieval model,new image retrieval model,content-based image,edge detection,feature extraction,hough transform
Computer vision,Image gradient,Pattern recognition,Color histogram,Image texture,Computer science,Color balance,Artificial intelligence,Color normalization,Content-based image retrieval,Color quantization,Color image
Conference
ISBN
Citations 
PageRank 
0-7695-2874-0
0
0.34
References 
Authors
3
4
Name
Order
Citations
PageRank
Taijun Li151.54
Qiuli Wu200.34
Jiafu Yi300.34
Cheng Chang444054.17