Application of fuzzy C-Means clustering for seed discrimination by artificial vision
DOI: 10.1016/S0169-7439(97)00045-2
Title: Application of fuzzy C-Means clustering for seed discrimination by artificial vision
Journal Title: Chemometrics and Intelligent Laboratory Systems
Volume: 38
Issue: 1
Publication Date: August 1997
Start Page: 75
End Page: 87
Published online: online 21 April 1998
ISSN: 0169-7439
Affiliations:

  • a Institut National de la Recherche Agronomique, Laboratoire de Technologie Appliquée à la Nutrition, B.P. 71627, Rue de la Géraudière, F-44316 Nantes Cedex 03, France

  • b Institut de Recherche et d'Enseignement Supérieur aux Techniques de l'Electronique, Laboratoire des Systèmes Electroniques et Informatiques, La Chantrerie, C.P. 3003, 44087 Nantes Cedex 03, France

  • c Station National d'Essais de Semences, Rue Georges Morel, 49071 Beaucouzé Cedex, France
  • Abstract: y C-Means Algorithm (FCMA) was applied for the discrimination between seed species by artificial vision. Colour images of seeds belonging to 4 species were acquired with a CCD camera. In order to characterise the morphology of the seeds, a set of quantitative features were extracted from the images. The aim of this study was to cluster, by FCMA, the measured learning and test data into 4 groups. The FCMA process was improved by the introduction of a non-random initialisation of the cluster centres. In addition, the Mahalanobis distance was used, instead of the Euclidean distance, as a measure of the proximity of a pattern to a cluster. Furthermore, a classification approach with a reject option was investigated for increasing the classification performances. This was achieved by assigning the seeds which were lying in the fuzzy boundaries between the available classes to a reject class. The proposed initialisation method outperformed the random initialisation both in terms of the computation time and the percentage of correct recognition. With the Mahalanobis distance, the error of classification was 5.32% and 6% for the training and test sets. In comparison to the Euclidean distance, the Mahalanobis distance allowed a decrease of the classification errors by 1.12% and 1% for the training and test sets, respectively. The main advantage of the Mahalanobis distance is that it takes into account the real underlying shapes of the clusters. The Application of FCMA with a reject option showed that the classification errors dropped to 3.38% and 5% when 7.43% of the learning seeds were rejected.
    Accepted: 17 April 1997
    Received: 5 February 1997
    Tel: +33-240675000
    Fax: +33-240675012
    Email: chtioui@nantes.inra.fr

    Please Share this Paper with friends:
    Comment
    No.
    Comment Content
    User Name
    Date
    Post new Comment
    UserName
    Post to Facebook
    ×
    Search Full Text