The extraction of the contours of objects in images is an integral function of systems for processing and recognition of numbers presented in the form of images. The paper considers a class of algorithms focused on the formation of a set of pixels separating objects of interest from the background, and which is resistant to certain types of noise. The main idea of the proposed algorithms is the construction and analysis of fuzzy increments in the extraction of contours. The rules for calculating fuzzy increments for the considered pixel in an arbitrary direction are described. The algorithm has been tested and shown to be effective in solving the problems of recognizing car numbers. The practical significance of the obtained results lies in the fact that the proposed algorithms can be used to create a software module for preliminary image processing in image processing and recognition systems.
Contour Extraction When Recognizing Numbers Presented as Images
Lect. Notes in Networks, Syst.
International School on Neural Networks, Initiated by IIASS and EMFCSC ; 2022 ; St.Petersburg, Russia February 08, 2022 - February 10, 2022
Networked Control Systems for Connected and Automated Vehicles ; Chapter : 123 ; 1209-1218
2022-11-16
10 pages
Article/Chapter (Book)
Electronic Resource
English
Application of Neural Networks for the Contour Extraction in Images
British Library Online Contents | 2005
|Clustering by contour extraction
British Library Online Contents | 1994
|Recognizing occluded objects in SAR images
Tema Archive | 2001
|Recognizing occluded objects in SAR images
IEEE | 2001
|Hierarchical contour matching in medical images
British Library Online Contents | 1996
|