Content Based Image Retrieval Using Local Color Histogram
Journal: International Journal of Engineering Research (IJER) (Vol.3, No. 8)Publication Date: 2014-08-01
Authors : Metty Mustikasari; Sarifuddin Madenda; Eri Prasetyo; Djati Kerami; Suryadi Harmanto;
Page : 507-511
Keywords : AVRR; City block distance; Content-based image retrieval (CBIR); Euclidean distance; IAVRR; Local color histogram; precision; recall.;
Abstract
This paper proposes a technique to retrieve images based on color feature using local histogram. The image is divided into nine sub blocks of equal size. The color of each sub-block is extracted by quantifying the HSV color space into 12x6x6 histogram. In this retrieval system Euclidean distance and City block distance are used to measure similarity of images. This algorithm is tested by using Corel image database. The performance of retrieval system is measured in terms of its recall and precision. The effectiveness of retrieval system is also measured based on AVRR (Average Rank of Relevant Images) and IAVRR (Ideal Average Rank of Relevant Images) which is proposed by Faloutsos. The experimental results show that the retrieval system has a good performance and the evaluation results of city block has achieved higher retrieval performance than the evaluation results of the Euclidean distance.
Other Latest Articles
- Waste Marble Utilization from Residue Marble Industry as a Substitution of Cement and Sand within Concrete Rooftile Production
- CPW fed Inverted U-Shape Microstrip Patch Antenna for WLAN/WiMAX Applications
- Analysis of lubrication properties of zinc-dialkyl-dithio-phosphate (ZDDP) additive on Karanja oil (Pongamia pinnatta) as a green lubricant
- Performance Evaluation of a Ricemill Developed in NCRI
- Hydrochemical Analysis and Evaluation of Groundwater Quality in Part of Krishna District, Andhra Pradesh ? Using Remotesensing and GIS Techniques
Last modified: 2014-08-05 18:05:13