Automatic Classification of Optical Defects of Mirrors from Ronchigram Images Using Bag of Visual Words and Support Vector Machines

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10657)


The Ronchi test is known as a procedure that is able to generate visual patterns called ronchigrams. These patterns could be used to determine optical characteristics on the surface of mirrors, particularly to quantify and qualify optical aberrations and deformations. This paper presents an automatic method to detect these optical errors of mirrors using the Ronchi test by classifying ronchigram images using bag of visual words (BoVWs) for image representation and support vector machines (SVM) for ronchigrams classification. The ronchigram image data set was obtained from the optical manufacture laboratory of lenses and mirrors at Universidad de los Llanos. The BoVWs approach used was based on Scale-Invariant Feature Transform (SIFT) as visual words and a Linear SVM was trained for automatic classification of ronchigrams into optical defects. The classification performance achieved was 0.69% in terms of accuracy measure. These results shows that our proposed approach can be used to detect optical defects of mirrors with high precision in a real scenario of ronchigrams obtained from mirrors during the manufacture process of a optical laboratory.


Bag of visual words Image processing Machine learning Optical defects Mirrors Ronchi test Support Vector Machine 


  1. 1.
    Arenas, G., Doria, O., Narvaéz, A., Nunez, M.: Prueba de ronchi para un espejo cóncavo. Rev. Colomb. de Física 38(2), 601–604 (2006)Google Scholar
  2. 2.
    Cordero, A., González, J.: Surface evaluation with Ronchi test by using Malacara formula, genetic algorithms, and cubic splines. In: IODC. SPIE (2010)Google Scholar
  3. 3.
    Cordero, A., González, J., Robledo, C.I., Leal, I.: Local and global surface errors evaluation using ronchi test, without both approximation and integration. Appl. Opt. 50(24), 4817–4823 (2011)CrossRefGoogle Scholar
  4. 4.
    González, M.M., Ochoa, N.A.: The Ronchi test with an LCD grating. Opt. Commun. 191(3), 203–207 (2001)CrossRefGoogle Scholar
  5. 5.
    Hidalgo, S.: Random forests para detección de fraude en medios de pago. Master’s thesis, Univ. Autónoma de Madrid, Escuela Politécnica Superior, Dpto. Ingeniería Informática (2014)Google Scholar
  6. 6.
    Jiménez, J., Dávila, A.: Ronchi test visibility as a function of illumination source size and duty cycle of the Ronchi ruling. Optica pura y aplicada 46(1), 29–32 (2013)CrossRefGoogle Scholar
  7. 7.
    López, A.J., Pelayo, M.P., Forero, Á.R.: Enseñanza del procesamiento de imágenes en ingeniería usando Python (2015)Google Scholar
  8. 8.
    Malacara, D.: Optical Shop Testing, vol. 59. Wiley, Hoboken (2007)CrossRefGoogle Scholar
  9. 9.
    Prieto, M., Forero, A.: Diseño e implementación de un sistema asistido por computador de la prueba de ronchi en el taller de óptica de la universidad de los llanos (2015)Google Scholar
  10. 10.
    Sánchez, J., Silva, G., Castro, J., Sasian, J.: 1\(\lambda \) Ronchi tester to obtain the wave front aberration in converging optical systems using phase shifting interferometry. Opt. Pura Apl. 45(4), 461–473 (2012)CrossRefGoogle Scholar
  11. 11.
    Scikit-learn developers: an introduction to machine learning with scikit-learn. An introduction to machine learning with scikit-learn (2010–2016)Google Scholar
  12. 12.
    Valveny, E., González, J.B.R.: Clasificación de imágenes: cómo reconocer el contenido de una imagen? (2010)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Dynamic Systems and GITECX Research GroupsUniversidad de los LlanosVillavicencioColombia
  2. 2.GITECX Research GroupUniversidad de los LlanosVillavicencioColombia
  3. 3.Dynamic Systems Research GroupUniversidad de los LlanosVillavicencioColombia
  4. 4.UN-Robot Research GroupUniversidad Nacional de ColombiaBogotáColombia

Personalised recommendations