Abstract
Nowadays, there are many studies on microbiologic diagnosis literature. In this study, the Multi-entropy and Artificial Neural Network (ME-ANN) system is presented for automatic detection of RNA virus images. This system consists of four stages. They are respectively pre-processing, feature extraction, classification and test of correct detection ratio of this ME-ANN method. In pre-processing stage, it is used the center - edge changing method. In this method, Euclidian distances are calculated the from center pixells of an object on image to edges of this object. Therefore, the distance vector has been obtained. This calculating is repeated for each of RNA virus images used in this study. In feature extraction stage, the norm, the logarithmic energy and threshold entropy values are calculated as feature vector. The obtained these features are invariant from rotation and scale of these RNA virus images. In classification stage, these obtained feature vector is given to the ANN classifier. Finally the test stage is performed for evaluation the correct detection ratio of ME-ANN algorithm for RNA virus images. The correct detection ratio of the proposed system is 94.02%.
Sign-in/Register to access full text options 
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 callDisclaimer: 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.
