Content Based Image Retrieval using Statistical Parameters of a Medical Image
M. Thilagam1, K. Arunesh2
1Ms M. Thilagam, Department of Computer Science, Sri S Ramasamy Naidu Memorial College, Sattur, Virudhunagar, Tamilnadu, India.
2Dr. K. Arunesh, Department of Computer Science, Sri S Ramasamy Naidu Memorial College, Sattur, Virudhunagar, Tamilnadu, India.
Manuscript received on 05 August 2019. | Revised Manuscript received on 14 August 2019. | Manuscript published on 30 September 2019. | PP: 3653-3649 | Volume-8 Issue-3 September 2019 | Retrieval Number: C5348098319/2019©BEIESP | DOI: 10.35940/ijrte.C5348.098319
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: We present a framework that permits in classifying medical images so as to recognize conceivable diseases that affected. This is done by Image retrieval from the collection of dataset by inputting the query image. Content based Image retrieval (CBIR) is the way toward seeking comparable pictures from a picture database dependent on the visual substance of the given query image. Even though some studies present general method in image extraction, there are no efficient methods in medical image retrieval with accuracy. To overcome and to eliminate these flaws our proposed CBIR method examined with the accurate and efficient way for feature extraction from medical images. The images used are grey scale image. The dataset holds the n number of images related to medical particularly brain tumor images. To retrieve the related images from the dataset and get the corresponding details, image is given as an input i.e., query image. Initially, the query image is analyzed by shape, texture and histogram and the result obtained from this is compared with the similar images in dataset. The similarities between the images are found by implementing the Matching Score algorithm. This algorithm provides accuracy in matching the image that helps greatly at the time of classification. The results of computation is said to be the features for the given image. Also the cost for processing the image is comparatively low. The technique has been examined on standard image dataset and satisfactory results have been achieved.
Index Terms: CBIR, Histogram, Matching Score, Brain Tumor, Image Retrieval.
Scope of the Article: Biomedical Computing