Classification of Burrs Using Contour Features of Image in Milling Workpieces

  1. Virginia Riego del Castillo 1
  2. Lidia Sánchez-González 1
  3. Claudia Álvarez-Aparicio 1
  1. 1 Universidad de León
    info

    Universidad de León

    León, España

    ROR https://ror.org/02tzt0b78

Libro:
Hybrid Artificial Intelligent Systems: 16th International Conference, HAIS 2021. Bilbao, Spain. September 22–24, 2021. Proceedings
  1. Hugo Sanjurjo González (coord.)
  2. Iker Pastor López (coord.)
  3. Pablo García Bringas (coord.)
  4. Héctor Quintián (coord.)
  5. Emilio Corchado (coord.)

Editorial: Springer International Publishing AG

ISBN: 978-3-030-86271-8 978-3-030-86270-1

Año de publicación: 2021

Páginas: 209-218

Congreso: Hybrid Artificial Intelligent Systems (HAIS) (16. 2021. Bilbao)

Tipo: Aportación congreso

Resumen

Fulfilment of quality standards in manufacturing processes is an essential task and often increases production costs. Specifically, the appropriate edge finishing of machine workpieces is one of the requirements so as to avoid the presence of burrs. In this paper, a vision-based system that employs contour features is proposed to detect and classify images of edge workpieces. In the first stage, we locate the region of the image that contains the edge of the part and in the second one, more precised operations provide detailed information in order to detect the edge type of the machined part. Calculated feature vector feeds supervised classifiers to determine the best approach to this dataset. Random Forest Classifier yields the best results obtaining a 90% of precision, recall and F1-score in the test dataset, which satisfies the experts demand to these processes.