This paper presents an efficient method for query-adaptive image retrieval using feature extraction and hashing method low level. Low-level features mainly consist of color, shape, and texture features. For color feature extraction, color moments, color histogram and color correlogram method were implemented and for texture feature extraction, wavelet moment method was implemented. been used. Hashing methods are used to integrate high-dimensional image features into the Hamming space, where the search can be performed in real time based on the Hamming distance of the compact hash codes. Based on the minimum Hamming distance, it returns the image similar to the query image. Index Terms: Hash Code, Hamming Distance, HammingSpace.I. INTRODUCTIONWEB data, including documents, images, and videos, is growing rapidly. Consider the website Flickr, which is primarily used for photo sharing and includes over 5 billion images. To find relevant images from such large databases, we need a simple method. Additionally, search engines like Google and Bing are based on text input; Content-based image retrieval (CBIR) has attracted considerable attention over the past decade. Instead of taking textual keywords as input, CBIR techniques directly take a visual query image Q and attempt to return images that are closer to the query image from a given database predefined feature space and distance measure. Generally, a large-scale image retrieval system consists of two key elements “an efficient representation of image features and an efficient retrieval mechanism”. Basically, the quality of image search results strongly depends on the representation power of image features [1]. The efficient search mechanism is essential when the existing image features are mainly large and current image ...... middle of paper ...... th HashCodes » IEEE Transactions On Multimedia, Vol. 15, No. 2, February 2013[2] Jun Wang, Sanjiv Kumar, and Shih-Fu Chang “Semi-supervised Hashing for Large-Scale Search” IEEE TransactionsOn Pattern Analysis And Machine Intelligence, Vol. 34, No. 12, December 2012[3] Chenxia Wu, Jianke Zhu, Deng Cai, Member, Chun Chen, and Jiajun Bu, “Semi-supervised Nonlinear Hashing Using Bootstrap Sequential Projection Learning” IEEE Transactions OnKnowledge And Data Engineering , Flight. 25, No. 6, June 2013[4] Archana B. Waghmare “Low-level feature extraction for content-based image retrieval” International Journal of Advances in Computing and Information Researches ISSN: 2277-4068, Volume 1 – No.2, April 2012[5] Dr. HB Kekre, M. Dhirendra Mishra “Image retrieval using image hashing” Techno-Path: Journal of Science, Engineering & Technology Management, Vol. October 1st No. 32009