External defects and severity level evaluation of potato using single and multispectral imaging in near infrared region

• Published in: Information processing in agriculture Vol. 11; no. 1; pp. 80 - 90
• Main Authors: Al Riza, Dimas Firmanda, Widodo, Slamet, Yamamoto, Kazuya, Ninomiya, Kazunori, Suzuki, Tetsuhito, Ogawa, Yuichi, Kondo, Naoshi
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.03.2024; Elsevier
• Subjects: Common scab; External defects; Multispectral imaging; Near infrared; Pseudo-color; Common scab; Multispectral imaging; External defects; Pseudo-color; Near infrared
• ISSN: 2214-3173; 2214-3173
• DOI: 10.1016/j.inpa.2022.09.001

•Potato defects severity level has been assessed using NIR image.•Defect area and soil deposits could be identified in NIR region.•Single channel image and multispectral images has been compared for defects segmentation.•Single channel image on 1 600 nm shows good results of defects. Non-invasive potato defects detection has been demanded for sorting and grading purpose. Researches on the classification of the defects has been available, however, investigation on the severity level calculation is limited. For the detection of the common scab, it has been found that imaging in the infrared region provide an interesting characteristic that could distinguish defected area to normal area. Thus, investigations on this wavelength range is interesting to add more knowledge and for applications. In this research, the multispectral image has been obtained and investigated especially at three wavelengths (950, 1 150, 1 600 nm). Image pre-processing and pseudo-color conversion techniques were explored to enhance the contrast between defects, normal background skin area and soil deposits. Results show that external defects, such as common scab and some mechanical damage types, appear brighter in the near infrared region, especially at 1 600 nm against the normal skin background. It has been found that pseudo-color images conversion provides more information regarding type if surface characteristics compared to grayscale single imaging. Image segmentation using pseudo-color images after multiplication operation pre-processing could be used for common scab and mechanical damage detection excluding soil deposits with a Dice Sorensen coefficient of 0.64. In addition, image segmentation using single image at 1 600 nm shown relatively better results with Dice Sorensen coefficient of 0.72 with note that thick soil deposits will also be segmented. Defect severity level evaluation had an R2 correlation of 0.84 against standard measurements of severity.