Automatic Classification of Tahitian Pearls - Archive ouverte HAL
Conference Papers Year : 2015

Automatic Classification of Tahitian Pearls

Martin Loesdau
  • Function : Author
  • PersonId : 1003510
Sébastien Chabrier
Alban Gabillon

Abstract

Tahitian pearls are currently classified manually by pearl experts. This process is time consuming and furthermore subjective for some of the quality parameters such as colour, form or lustre. In this paper we present our ongoing work to implement an automatic classification of Tahitian pearls out of images. An automatic classification can help to accelerate the quality evaluation process as well as to minimize the subjective influence of the human classification. For this purpose different image segmentation and machine learning methods are used. In the following sections we explain our methodology, show first results for several sub-steps and give new ideas for greylevel edge detection and colour classification.
Fichier principal
Vignette du fichier
Loesdau, Chabrier, Gabillon - 2015 - Automatic Classification of Tahitian Pearls.pdf (1.02 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01711245 , version 1 (05-02-2021)

Identifiers

  • HAL Id : hal-01711245 , version 1

Cite

Martin Loesdau, Sébastien Chabrier, Alban Gabillon. Automatic Classification of Tahitian Pearls. 6th International Conference on Image Processing & Communications (IPC 2014), Sep 2014, Bydgoszcz, Poland. ⟨hal-01711245⟩

Collections

UPF
47 View
69 Download

Share

More