TLC Image Processing as a New Way for Substances Identification

Authors

  • MSc. Francisco J. Silva-Mata Centro de Aplicaciones de Tecnologías de Avanzada (CENATAV), La Habana
  • Ing. Dania Porro-Muñoz Centro de Aplicaciones de Tecnologías de Avanzada (CENATAV), La Habana
  • Dra. Isneri Talavera-Bustamante Centro de Aplicaciones de Tecnologías de Avanzada (CENATAV), La Habana
  • Dra. Noslen Hernández-González Centro de Aplicaciones de Tecnologías de Avanzada (CENATAV), La Habana
  • MSc. René Antonio Vázquez-Vallejo Centro de Aplicaciones de Tecnologías de Avanzada (CENATAV), La Habana
  • Lic. Yenisel Pérez-Pérez Centro de Aplicaciones de Tecnologías de Avanzada (CENATAV), La Habana

Abstract

The Thin-layer chromatographic analytical technique is one of the most currently used for the analysis of substances. This work is focused on the automatic analysis of such plate’s images using image processing methods and pattern recognition methods. The proposed method consists of several steps as capture, detection, automatic cropping and automatic rotation of the mentioned images. Afterwards, a number of filters are applied to improve the image such that the stains of the substances of interest be correctly detected. Finally, from that image automatically extracting descriptors of shape and color, and Rf value determination is performed to identify the substance by calculating the similarity with the patterns substances previously stored. The presented method is evaluated in a drugs identification problem. Good results were obtained for identifying 44 abuse drugs.
Keywords: Chromatography, Thin Layer Chromatography, automatic.

Published

2016-01-07

How to Cite

J. Silva-Mata, M. F., Porro-Muñoz, I. D., Talavera-Bustamante, D. I., Hernández-González, D. N., Vázquez-Vallejo, M. R. A., & Pérez-Pérez, L. Y. (2016). TLC Image Processing as a New Way for Substances Identification. Revista Cubana De Química, 25(3), 295–306. Retrieved from https://cubanaquimica.uo.edu.cu/index.php/cq/article/view/624

Issue

Section

Artículos

Most read articles by the same author(s)