Abstract

In this paper algorithm for search the tumour cells images in a database is developed. This algorithm based on shape and colour image features.

Highlights

  • Today every biomedical research includes the processing of a big amount of textual and image data

  • There are two main approaches for image searching, either in local database or internet: classification defined by expert and the content based image retrieval

  • Image segmentation considerably improves speed of image search in the case when it contains the group of objects

Read more

Summary

INTRODUCTION

Today every biomedical research includes the processing of a big amount of textual and image data. For storing and retrieval of medical data researchers uses various databases. There are two main approaches for image searching, either in local database or internet: classification defined by expert and the content based image retrieval. The first approach means that images are classified on some categories: disease, organ, tissue type, magnification etc. The second approach means that images are segmented into homogeneous regions, based on some rules, and their different features are calculated. Image segmentation considerably improves speed of image search in the case when it contains the group of objects. During segmentation the features of each region are calculated and stored in database. The goal of this paper is the determination of edge and colour features of tumour cells images and developing the algorithm for search of these images in a database

OBJECTS SELECTION ALGORITHM AND DETERMINATION OF SHAPE FEATURE
COLOUR FEATURE REPRESENTATION
Findings
WORK ALGORITHM AND EXPERIMENTAL RESULTS
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.