Title
Avocado visual selection with convolutional neural networks based on Peruvian standards
Date Issued
01 January 2022
Access level
metadata only access
Resource Type
conference paper
Publisher(s)
Institute of Electrical and Electronics Engineers Inc.
Abstract
This research article proposes an artificial vision system (AVS) for the selection of avocado in order to reduce product losses, be efficient, in the shortest time and with greater precision. Based on a systematic review, the correct techniques was selected according the comparison of the results and the process. In the case study, it uses 4,000 avocado images. First, the ripening stages of avocados will be analyzed by Red Green Blue (RGB) layers. Secondly, the segmentation is carried out, which consists of binarizing the image, then applying the filter operation to obtain a uniform image without any distortion, with this result, the size analysis is determined with the area of the size of the avocado in pixels to later determine the quality analysis based on the Peruvian Technical Standard called INACAL. Thirdly, the avocado is classified according to its state of maturation, size and quality. Programming codes will run in MATLAB software.
Language
English
OCDE Knowledge area
Ingeniería, Tecnología
Scopus EID
2-s2.0-85138760702
ISBN of the container
978-166548636-1
Conference
Conference Proceedings: Proceedings of the 2022 IEEE 29th International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2022
Sources of information: Directorio de Producción Científica Scopus