Title: Content-based fabric image retrieval system by exploiting dictionary learning approach

Authors: T. Jasperline; D. Gnanadurai

Addresses: Dr. G.U. Pope College of Engineering, Pope Nagar, Sawyerpuram, Thoothukudi 628251, India ' St. Joseph University, Virgin Town, Ikishe Model Village, Dimapur, Nagaland-797115, India

Abstract: Owing to the skyrocketing growth of the image utilisation, it is necessary to organise the images by some means. CBIR is the system that matches the query image with the image database and fetches the relevant images with respect to the query image. This makes the image search process easier and it has found many applications in almost all domains. The main issues of a CBIR system are the accuracy and time consumption. This work presents a content-based fabric image retrieval system (CBFIR) which relies on the extraction of colour and texture features. The initial clusters are built by the fuzzy C-means (FCM) algorithm and the dictionaries are constructed for every cluster. The clusters of each dictionary are updated by simultaneous orthogonal matching pursuit (SOMP) algorithm. The proposed approach compares the test image with the constructed dictionaries, so as to detect the dictionary with sparsest representation. The performance of the proposed approach is observed to be satisfactory in terms of accuracy, precision and recall rates.

Keywords: fabric image retrieval; image clustering; feature extraction; dictionary learning.

DOI: 10.1504/IJAIP.2024.140094

International Journal of Advanced Intelligence Paradigms, 2024 Vol.28 No.3/4, pp.327 - 339

Received: 08 Jun 2018
Accepted: 17 Nov 2018
Published online: 24 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article