Abstract :
It is very significant to know the different minority costumes which are vanishing now a day which is used for minority culture protection and inheritance. To get the exact results for image retrieval there is need of a novel image feature representation method which is used to show the rich information of minority costume image. In this implementation first image is divided into image sub blocks and then from that image calculate both color histogram as well as edge orientation histogram separately. The final feature used for minority costume image retrieval is fusion or integration of both color histogram and edge orientation histogram. At last improved Canberra distance is calculated for the input query image and retrieved output image. For the performance analysis there is use of self build minority costume image dataset. MATLAB analysis results show that integrated technique of image retrieval will give outperforming results for characteristics such as color, texture, shape and spatial information, in comparison to existing technique proposed work will give higher and stable retrieval accuracy. S Shivakumar | S Mallesh "Image Retrieval for Minority Costume by using Color Histogram and Edge orientation (EO) Histogram Technique" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-4 , June 2018, URL: https://www.ijtsrd.com/papers/ijtsrd14445.pdf Paper URL: http://www.ijtsrd.com/engineering/electronics-and-communication-engineering/14445/image-retrieval-for-minority-costume-by-using-color-histogram-and-edge-orientation-eo-histogram-technique/s-shivakumar
Keyword :
Edge Orientation Histogram, Color Histogram, Minority Culture, Image Sub-blocks, Canberra Distance.