Open AccessMedical Image Retrieval Using Convolution Neural Networks
Author(s) -
N. Kalaivani,
Dr.T.Arumuga Maria Devi,
S. Sophia,
Natraj Manimaran,
P Kowsalya
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/994/1/012038
Subject(s) - computer science , image retrieval , artificial intelligence , convolution (computer science) , convolutional neural network , image (mathematics) , matching (statistics) , matlab , pattern recognition (psychology) , dicom , class (philosophy) , artificial neural network , deep learning , automatic image annotation , computer vision , image processing , mathematics , statistics , operating system
In this paper, medical image retrieval is done in an effective manner by using convolution neural network (CNN). This proposed system locates reference tags and classes the DICOM images using image processing techniques and retrieval of images are done by using GUI panel. First, the deep learning technique is used to extract powerful features of the image for tag description. Conversely, this technique performs tag matching directly by passing suitable parameters which recognizes the classes as queries. The comparison features are able to capture the general form of the input image and its class based on image tags. Here, we have used a collection of 22 classes of database to demonstrate the efficiency of our system. The experimental results show the classification of images by deep learning algorithm which is used to gain the rate of retrieval accuracy by using MATLAB.