Automated Video Monitor Screen Extraction using Semantic Segmentation and CNN
| Autor: | Caio F.S. Cruz, Eddie Filho, Lucas Coimbra, Ricardo G. Paula, Ruan J.S. Belem, Anderson S. Jesus, Osmar R.A. Silva, André Lucirton Costa, Wilson Salgado Júnior, Agemilson Pimentel |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Visual inspection
Reduction (complexity) business.industry Computer science 0202 electrical engineering electronic engineering information engineering 020206 networking & telecommunications 020201 artificial intelligence & image processing Pattern recognition Segmentation 02 engineering and technology Artificial intelligence business Convolutional neural network |
| Zdroj: | ICCE-TW |
| Popis: | In production lines for monitors and displays, some validation tests are based on visual inspection, whose preliminary step usually consists in detecting the area corresponding to a monitor's screen, which is then followed by evaluation procedures. Nonetheless, depending on the chosen technique, such a detection may consume much of a given test's total time. The present paper addresses the mentioned problem and presents an approach that uses semantic segmentation and convolutional neural networks for screen segmentation, which allows a reduction on elapsed test times about 27.77%, without compromising the accuracy already obtained with traditional approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|