Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ44087

An Efficient Content Based Image Retrieval using Block Truncation Coding

R.Sahaya Jeya Sutha, D.S. Mahendran, S.John Peter


Content based image retrieval (CBIR) systems used to retrieve the related images from a large image database according to the query image. Existing methods for CBIR usually suffer from the limitations of retrieval time and high length feature vector. This paper presents CBIR using global features for Block Truncation Coding (BTC) compressed images. BTC is a compression technique, which is also suitable for indexing the images in database for image retrieval. The features extracted directly from the BTC compressed image without decompressing it, reduces retrieval time. To achieve an image retrieval from a large database, texture and color attributes integrated in this work. HSV Color Histogram extracts color information, while Gray Level Co-occurrence Matrix (GLCM) of BTC codeextracts the texture information. The experimental results prove that the proposed method is able to achieve higher performance as compared to traditional retrieval scheme using BTC. The proposed method tested on Wang image database having 1000 images across 10 categories with 100 images in each category of RGB color space. To compare the performance precision and recall computed, and they showed our approach is outperformed.


Block truncation coding (BTC), Content based image retrieval (CBIR), global feature descriptors, HSV Color Histogram, Gray Level Co-occurrence Matrix (GLCM)

Full Text