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.NQ44408

CONTENT BASED IMAGE RETRIEVAL USING CONVOLUTIONAL NEURAL NETWORK AND EXTREME LEARNING MACHINE IN COREL DATASET

AntoAMicheal, N Vadivelan, KBhargavi

Abstract

The evolution of multimedia technology and rapidly increasing image collections on the Internet has attracted significant research efforts in image retrieval. Difficulties faced by text-based image retrieval motivated the researchers to develop new solutions for representation and indexing of visual information. This paper proposes a content-based image retrieval using the significant use of Convolutional Neural Network (CNN) and Extreme Learning Machine (ELM) This proposed approach extracts various features and forms as feature vectors. Apart from these extracted features, CNN is used to extract the additional features and the ELM classifies the intermediate results. The proposed approach is experimented on COREL dataset and its performance is calculated using statistical parameters such as, the precision and recall. The statistical results show that the accuracy of the proposed system is 93.58%. The experiments result shows that the proposed method outperforms the existing methods by exhibiting significant performance improvement in terms of accuracy and efficiency.

Keywords

Content Based Image Retrieval, Corel Dataset, Convolutional Neural Network (CNN), Extreme Learning Machine (ELM), Hybrid Classification Structure.

Full Text

PDF

References

?>