Development of multistage algorithm for text objects recognition in images

The relevance of this study is stipulated by the necessity of designing algorithms allowing to improve the efficiency of characters recognition on images with complex backgrounds subjected to noise, affine and projective transformations. Purpose: Development of algorithms and software system allowin...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE International Siberian Conference on Control and Communications. Online) s. 1 - 5
Hlavní autori: Cherneta, D.S., Druki, A.A., Spitsyn, V.G.
Médium: Konferenčný príspevok.. Journal Article
Jazyk:English
Vydavateľské údaje: IEEE 01.05.2016
Predmet:
Algorithm design and analysis
Algorithms
artificial neural networks
Background noise
Character recognition
Classification algorithms
Hough transform
Image processing
Image recognition
Image segmentation
Neural networks
Neurons
Noise
Object recognition
Training
Transformations
Viola-Jones algorithm
ISSN:2380-6516
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The relevance of this study is stipulated by the necessity of designing algorithms allowing to improve the efficiency of characters recognition on images with complex backgrounds subjected to noise, affine and projective transformations. Purpose: Development of algorithms and software system allowing to improve the efficiency of characters recognition on images with complex backgrounds subjected to noise, affine and projective transformations. Experimental research to be carried out into the efficiency of developed algorithms and their comparison to their existing analogs. Findings: Viola-Jones object detection algorithm is suggested to detect the area of character location on images with complex background. The image normalization includes the following operations: boundary identification, Hough transformation, search for closed loops, image leveling. The structure of convolutional neural network (CNN) is suggested for characters recognition. The implementation of the developed algorithms is presented by characters recognition on images of vehicle number plates.
Bibliografia:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:2380-6516
DOI:10.1109/SIBCON.2016.7491714