Computer vision system in real-time for color determination on flat surface food

• Autores: Saldaña, Erick, Siche, Raul, Huamán, Rosmer, Luján, Mariano, Castro, Wilson, Quevedo, Roberto
• Formato: artículo
• Fecha de Publicación: 2013
• Institución: Universidad Nacional de Trujillo
• Repositorio: Revista UNITRU - Scientia Agropecuaria
• Lenguaje: inglés
• OAI Identifier: oai:ojs.revistas.unitru.edu.pe:article/98
• Enlace del recurso: http://revistas.unitru.edu.pe/index.php/scientiaagrop/article/view/98
• Nivel de acceso: acceso abierto
• Materia: Computer Vision; RGB model; CIELab model; food quality control; Matlab

Artificial vision systems also known as computer vision are potent quality inspection tools, which can be applied in pattern recognition for fruits and vegetables analysis. The aim of this research was to design, implement and calibrate a new computer vision system (CVS) in real-time for the color measurement on flat surface food. For this purpose was designed and implemented a device capable of performing this task (software and hardware), which consisted of two phases: a) image acquisition and b) image processing and analysis. Both the algorithm and the graphical interface (GUI) were developed in Matlab. The CVS calibration was performed using a conventional colorimeter (Model CIEL* a* b*), where were estimated the errors of the color parameters: eL* = 5.001%, and ea* = 2.287%, and eb* = 4.314 % which ensure adequate and efficient automation application in industrial processes in the quality control in the food industry sector.