Study on Image Processing for Quality Estimation of Strawberries. (Part 1). Detection of Bruises on Fruit by Color Image Processing
| Autor: | Bim Prasad Shrestha, Yoshinori Gejima, Masateru Nagata |
|---|---|
| Rok vydání: | 2001 |
| Předmět: | |
| Zdroj: | Shokubutsu Kojo Gakkaishi. 13:115-122 |
| ISSN: | 1880-3555 0918-6638 |
| DOI: | 10.2525/jshita.13.115 |
| Popis: | This paper addresses the problem of detecting bruises on strawberry fruit surface. Bruises were caused in a controlled manner on the freshly harvested fruits. The intensity level of reflection from the bruised and non-bruised surfaces were measured and analyzed by using a spectrometer within the range of 600 to 1000 nm. The particular wavelengths critical for bruise detection were determined and spectral images were acquired with suitable filters. The effective wavelength with the constant differences between bruised and non-bruised areas was selected as 945 to 975 nm.The image subtraction was carried out between bruised and non-bruised strawberries acquired with 960 nm and 860 nm filters respectively. Two methods of image subtraction are proposed, first between the images of the same samples for recognizing the possibility of bruise detection and, second between test and standard strawberry images for online sorting.The former method has confirmed the possibility of bruise detection by using NIR image processing. The judgment result from the latter method has agreed with the visual judgment for online sorting of strawberries. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|