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.NQ44232


Hardeep Singh, Dr. Vijay Dhir, Dr.Jagdeep Kaur


Improvements in current digital storage media, especially in image capturing devices such as webcams, digital cameras, and the exponential growthin the Internet generates a millions of images per day. This requires an efficient retrieval system to extract useful information from these images. For an example visual information of images is required in different fields such as healthcare, architecture drawing, academic, crime prevention, etc. To this end, many image retrieval systems have been developed. Content-Based Image Retrieval (CBIR) systems as it are now a big demand in society. It is a method of retrieving similar image from the massive dataset. A number of approaches are used to develop an efficient CBIR system, out of which Scale Invariant Feature Transform (SIFT) is very popular. In this paper, we designed a novel CBIR system for massive dataset by taking the advantage of SIFT as feature extraction algorithm. To obtained high quality images, the image features are optimized using Artificial Bee Colony Algorithm (ABC). Then for training and classification Artificial neural Network (ANN) is used. Results are tested by uploading different images in terms of precision, recall, and F-measure. The experiment results show satisfied results compared to past work.


Content-Based Image Retrieval, Scale Invariant Feature Transform, Artificial Bee Colony Algorithm, Artificial neural Network.

Full Text