Automatic classification of medical images for Content Based Image Retrieval Systems (CBIR)

2008 ◽  
Author(s):  
Epaphrodite Uwimana ◽  
Miguel E. Ruiz
Keyword(s):  
Image Retrieval ◽  
Medical Images ◽  
Automatic Classification ◽  
Content Based Image Retrieval ◽  
Retrieval Systems

scholarly journals CLASSIFICATION OF BIOMEDICAL IMAGES USING CONTENT BASED IMAGE RETRIEVAL SYSTEMS

2020 ◽  
Vol 5 (2) ◽  
pp. 181-189
Author(s):  
Yinghui Zhang ◽  
Fengyuan Zhang ◽  
Yantong Cui ◽  
Ruoci Ning
Keyword(s):  
Image Retrieval ◽  
Input Image ◽  
The Body ◽  
Content Based Image Retrieval ◽  
Main Task ◽  
Area Of Interest ◽  
Retrieval Systems ◽  
Complete Series ◽  
Occurrence Matrix

Because of the numerous application of Content-based image retrieval (CBIR) system in various areas, it has always remained a topic of keen interest by the researchers. Fetching of the most similar image from the complete repository by comparing it to the input image in the minimum span of time is the main task of the CBIR. The purpose of the CBIR can vary from different types of requirements like a diagnosis of the illness by the physician, crime investigation, product recommendation by the e-commerce companies, etc. In the present work, CBIR is used for finding the similar patients having Breast cancer. Gray-Level Co-Occurrence Matrix along with histogram and correlation coefficient is used for creating CBIR system. Comparing the images of the area of interest of a present patient with the complete series of the image of a past patient can help in early diagnosis of the disease. CBIR is so much effective that even when the symptoms are not shown by the body the disease can be diagnosed from the sample images.

AUTOMATIC CLASSIFICATION OF DIGITAL PHOTOGRAPHS BASED ON DECISION FORESTS

2004 ◽  
Vol 18 (05) ◽  
pp. 819-845 ◽  
Author(s):  
RAIMONDO SCHETTINI ◽  
CARLA BRAMBILLA ◽  
CLAUDIO CUSANO ◽  
GIANLUIGI CIOCCA
Keyword(s):  
Image Processing ◽  
Image Retrieval ◽  
Automatic Classification ◽  
Experimental Results ◽  
Content Based Image Retrieval ◽  
Test Set ◽  
Digital Photographs ◽  
Low Level

Annotating photographs with broad semantic labels can be useful in both image processing and content-based image retrieval. We show here how low-level features can be related to semantic photo categories, such as indoor, outdoor and close-up, using decision forests consisting of trees constructed according to CART methodology. We also show how the results can be improved by introducing a rejection option in the classification process. Experimental results on a test set of 4,500 photographs are reported and discussed.

scholarly journals A new approach for content-based image retrieval for medical applications using low-level image descriptors

2020 ◽  
Vol 10 (4) ◽  
pp. 4363
Author(s):  
Mohammed Qassim Shatnawi ◽  
Mohammad Alrousan ◽  
Suzan Amareen
Keyword(s):  
Image Retrieval ◽  
Medical Images ◽  
Image Similarity ◽  
Content Based Image Retrieval ◽  
Great Success ◽  
Similarity Matching ◽  
Low Level ◽  
Image Descriptors ◽  
Retrieval Systems ◽  
Imaging Research

<p>Content based image retrieval (CBIR) has become an important factor in medical imaging research and is obtaining a great success. More applications still need to be developed to get more powerful systems for better image similarity matching, and as a result getting better image retrieval systems. This research focuses on implementing low-level descriptors to maximize the quality of the retrieval of medical images. Such a research is supposed to set a better result in terms of image similarity matching. In this research a system that uses low-level descriptors is introduced. Three descriptors have been developed and applied in an attempt to increase the accuracy of image matching. The final results showed a qualified system in medical images retrieval specially that the low-level image descriptors have not been used yet in the image similarity matching in the medical field.</p>

Sign in / Sign up

Export Citation Format

Share Document