Color space analysis using KNN for lettuce crop stages identification in smart farm setup

• Main Authors: Loresco, Pocholo James M., Valenzuela, Ira C., Dadios, Elmer P.
• Format: text
• Published: Animo Repository 2019
• Subjects: Lettuce—Growth; Computer vision; Image segmentation; Image processing; Nearest neighbor analysis (Statistics); Electrical and Computer Engineering; Electrical and Electronics
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/2931
• Institution: De La Salle University

Advancing technologies are being done in improvement and enhancement of the smart farming all over the world. The growth of the plants is being monitored through the vision system and image processing is done to identify their growth stages. This is important since the amount of light, temperature and water varies at each stage. One of the challenges in the image processing is the selection of the color space that will be appropriate for a particular setup. In this study, K-nearest neighboring is used in the image segmentation for the RGB, HSV, CIELab, and YCbCr color spaces. The specificity and sensitivity of each color spaces were computed and compared. Based on the result obtained, CIELab color space is the best color space to be used in the identification of the growth stage of the lettuce. © 2018 IEEE.