Image-based classification and segmentation of healthy and defective mangoes

Maria Jeseca C. Baculo, Conrado Ruiz

Producció científica: Capítol de llibreContribució a congrés/conferènciaAvaluat per experts

1 Citació (Scopus)

Resum

The use of image processing and classification for agricultural applications has been widely studied and has led to work such as the automatic grading of fruit and vegetables, yield approximation and defect detection. Image segmentation is one of the first steps to identify the region of interest within an image. This paper presents an approach to automatic segmentation and classification of healthy and defective Carabao mangoes. K-means, range filtering and color-channel segmentation were utilized so that the varying texture and color of mangoes due to the surface defects can be considered. Results show that the proposed technique performs better than the classical K-means segmentation. The performance of segmentation step has a considerable influence on the precision of the classification model. Segmented and not segmented images were trained using KNN, SVM, MLP and CNN. The experiments showed that the models performed better when trained with segmented images.

Idioma originalAnglès
Títol de la publicacióEleventh International Conference on Machine Vision, ICMV 2018
EditorsAntanas Verikas, Dmitry P. Nikolaev, Jianhong Zhou, Petia Radeva
EditorSPIE
ISBN (electrònic)9781510627482
DOIs
Estat de la publicacióPublicada - 2019
Publicat externament
Esdeveniment11th International Conference on Machine Vision, ICMV 2018 - Munich, Germany
Durada: 1 de nov. 20183 de nov. 2018

Sèrie de publicacions

NomProceedings of SPIE - The International Society for Optical Engineering
Volum11041
ISSN (imprès)0277-786X
ISSN (electrònic)1996-756X

Conferència

Conferència11th International Conference on Machine Vision, ICMV 2018
País/TerritoriGermany
CiutatMunich
Període1/11/183/11/18

Fingerprint

Navegar pels temes de recerca de 'Image-based classification and segmentation of healthy and defective mangoes'. Junts formen un fingerprint únic.

Com citar-ho