Mahidol University Logo
Faculty of ICT, Mahidol University
 

Admissions

Printable Version

 

COLOR HARMONY-BASED IMAGE RETRIEVAL SYSTEM

AnawatBoonchabuppajarn5088009ITCS/B
ThreerasoonChansuroj5088019ITCS/B
PurisChalermpug5088055ITCS/B

B.Sc.(INFORMATION AND COMMUNICATION TECHNOLOGY)

Project Advisor: Dr.Rawesak Tanawongsuwan

Abstract

This senior project topic is the image retrieval system using color characteristics in the image as main features. Existing popular search engines offer image search feature as part of their search services. Besides the normal search based on text query, other features that enhance the search results are also being incorporated into the search options. Color characteristics in the image is one interesting feature that researchers have analyzed recently. Our work analyzes color harmony and a set of color tones in an image and uses them as features in the search process. These features are calculated from the hue channel (HSV color space). For the color harmony feature, we retrieve images based on the harmony scores that calculated from harmonic templates on the hue color wheel. For the color tone feature, we discretize the hue component into 12 tone ranges. We implement a prototype of the image retrieval system that can take advantages of both of these features. Our results show that these color features allow us to retrieve interesting images that may not be easy to obtain from the simple text query search. Moreover, our system can rate the harmony scores to user’s images such as webpage, photo, or design work to by uploading to our system.

 

KEYWORDS: IMAGE RETRIEVAL / COLOR / COLOR TONE / COLOR HARMONY / CBIR

 

Go to Top

 

ICT Building, Mahidol University, 999 Phuttamonthon 4 Road, Salaya, Nakhonpathom 73170 Tel. +66 02 441-0909 Fax. +66 02 849-6099
Mahidol University Computing Center, The Faculty of ICT, Mahidol University , Rama 6 Road, Rajathevi, Bangkok 10400 Tel. +66 02 354-4333 Fax. +66 02 354-7333