Least-squares method and deep learning in the identification and analysis of name-plates of power equipment
- Autores: Yerong Zhong, Guohong Luan, Ehab Abozinadah, Jiming Jiang
- Localización: Applied Mathematics and Nonlinear Sciences, ISSN-e 2444-8656, Vol. 7, Nº. 1, 2022, págs. 103-112
- Idioma: inglés
- Enlaces
-
Resumen
This article proposes a nameplate recognition method based on the least-squares method and deep learning algorithmcharacter feature fusion. This method extracts the histogram of the edge direction of the character and constructs thehistogram feature vector based on the wavelet transform deep learning algorithm. We use classifier training for the textrecognition of the nameplate to segment the text into individual characters. Then, we extract the character features to builda template. Experiments prove that the algorithm meets the practical application needs of nameplate identification of powerequipment and achieves the design goals.
¿Es nuevo? Regístrese
Ventajas de registrarse
