Contributions to OCR for unreadable characters in printed circuit boards by means of pattern matching and machine learning techniques [recurso electrónico] / Carlos Fábian Nava Dueñas; director, Félix Fernando González Navarro
Tipo de material:
TextoDetalles de publicación: Mexicali, Baja California, 2019Descripción: 1 recurso en línea,149 p. ; il. colTema(s): Circuitos impresos -- Tesis y disertaciones académicas -- Diseño y construcciónClasificación LoC:TK7868 .P7 | N39 2019Recursos en línea: Tesis Digital
Nota de disertación: Tesis (Doctorado)--Universidad Autónoma de Baja California, Instituto de Ingeniería, Mexicali, 2019. Resumen: In the last few decades, new computer vision technologies and image
processing techniques have been very important in the improvement
and automation of manual processes in many technical areas, e.g.,
in the semiconductor industry. In this thesis, we propose and com-
pare several techniques in the areas of pattern matching and machine
learning to have optical character recognition (OCR) of damaged or
unreadable numerical digit characters from images on printed circuit
boards (PCBs). We describe how the best machine learning algo-
rithms are applied to extract the principal characteristics and fea-
tures to compute, classify and find the correct numerical character
that corresponds to those features. We also present our work in the
improvement of the image quality in the pre-processing stage to make
pattern matching a good option over some specific conditions of PCBs
damage.
| Tipo de ítem | Biblioteca actual | Colección | Signatura | Copia número | Estado | Fecha de vencimiento | Código de barras |
|---|---|---|---|---|---|---|---|
| Tesis | Biblioteca Central Mexicali | Colección de Tesis | TK7868 .P7 N39 2019 (Browse shelf(Abre debajo)) | 1 | Disponible | MXL122270 |
Maestría y Doctorado en Ciencias e Ingeniería
Tesis (Doctorado)--Universidad Autónoma de Baja California, Instituto de Ingeniería, Mexicali, 2019.
In the last few decades, new computer vision technologies and image
processing techniques have been very important in the improvement
and automation of manual processes in many technical areas, e.g.,
in the semiconductor industry. In this thesis, we propose and com-
pare several techniques in the areas of pattern matching and machine
learning to have optical character recognition (OCR) of damaged or
unreadable numerical digit characters from images on printed circuit
boards (PCBs). We describe how the best machine learning algo-
rithms are applied to extract the principal characteristics and fea-
tures to compute, classify and find the correct numerical character
that corresponds to those features. We also present our work in the
improvement of the image quality in the pre-processing stage to make
pattern matching a good option over some specific conditions of PCBs
damage.
