Human Oriented Content Based Image Retrieval using Clustering and Interactive Genetic Algorithm

Vaishali Namdevrav Pahune; Nikita Umare

CALL FOR PAPERS : Feb-2026

Submission Last Date

25-Feb-26

Submit Manuscript Online

FOR AUTHORS

FOR REVIEWERS

ARCHIEVES

DOWNLOADS

Open Access

Human Oriented Content Based Image Retrieval using Clustering and Interactive Genetic Algorithm

Author(s):

Vaishali Namdevrav Pahune , Abha Gaikwad College of Engg,Nagpur; Nikita Umare, Abha Gaikwad College of Engg,Nagpur

Keywords:

Image retrieval, Interactive genetic algorithm (IGA), K-means, Visual features

Abstract:

Digital image libraries and other multimedia databases have been dramatically extended in recent years. The development of a content based image retrieval (CBIR) system is an important research topic which aims to retrieve the desired images effectively and precisely from a large image database. The proposed human oriented CBIR system that uses the interactive genetic algorithm (IGA) with K-means algorithm to infer which images in the databases would be of most interest to the user. Color, texture, and edge, of an image which are three image features are utilized in this approach. An interactive mechanism by IGA provides to better capture user’s intention. Here different features are considered which are as follows: from the hue, saturation, value (HSV) color space low-level image features color features, as well as texture and edge descriptors, are used in this approach the query-by-example strategy has been adopted as a search technique.(i.e. the user provides an image query). In addition, the hybrid of user’s subjective evaluation and essential characteristics of the images in the image matching against only considering human judgment is taken. The IGA (Interactive Genetic Algorithm) is employed to reduce the gap between the retrieval results and the users’ expectation which help the users to identify the images that are most satisfied to user’s needs. A clustering algorithm, definitely the k-means, is used to cluster the database into classes. Images with similar features are clustered to one class. From the experimental results, it is evident that the proposed system surpassed its counterpart, other existing systems, in terms of precision, recall and retrieval time.