A Novel Multi Hidden Layer Convolutional Neural Network for Content Based Image Retrieval
K. Ramanjaneyulu1, K. Veera Swamy2, Ch. Srinivasa Rao3
1K. Ramanjaneyulu*, Research scholar, JNTUK, Associate Professor, Department of ECE, QISIT, Andhra Pradesh, India.
2K. Veera Swamy, Professor, Department of ECE, Vasavi College of Engineering, Hyderabad, India.
3Ch. Srinivasa Rao, Professor, Department of ECE, JNTUKUCEV, Vizianagaram.,Andhra Pradesh, India.
Manuscript received on February 01, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 30, 2020. | PP: 365-370 | Volume-9 Issue-3, February, 2020. | Retrieval Number: C4771029320/2020©BEIESP | DOI: 10.35940/ijeat.C4771.029320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The applications of a content-based image retrieval system in fields such as multimedia, security, medicine, and entertainment, have been implemented on a huge real-time database by using a convolutional neural network architecture. In general, thus far, content-based image retrieval systems have been implemented with machine learning algorithms. A machine learning algorithm is applicable to a limited database because of the few feature extraction hidden layers between the input and the output layers. The proposed convolutional neural network architecture was successfully implemented using 128 convolutional layers, pooling layers, rectifier linear unit (ReLu), and fully connected layers. A convolutional neural network architecture yields better results of its ability to extract features from an image. The Euclidean distance metric is used for calculating the similarity between the query image and the database images. It is implemented using the COREL database. The proposed system is successfully evaluated using precision, recall, and F-score. The performance of the proposed method is evaluated using the precision and recall.
Keywords: Convolutional neural network, Euclidean distance and performance measures.