Presentation | 2013-12-12 Automatic Fruit Grading system based on Bi-pigment Model Kasumi ITO, Wataru OHYAMA, Tetsushi WAKABAYASHI, Fumitaka KIMURA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose an algorithm for automatic grading of fruits based on a model which utilizes the characteristics of fruit color. Establishment of automatic sorting and grading techniques are expected to contribute improving food security by introducing objective grading based on quantitative criteria. For this purpose, image-based techniques that adopt visible pericarp color of fruit as feature values have been proposed. However, these techniques were also required to combine the visible feature values and invisible physical sensor values due to low performance of color-based grading. In this research, we confirmed that the color distribution of normal fruit constructs a plane in color space. The plane is obtained from each image and established as Bi-pigment Model. Our grading method classifies an input image containing one fruit into normal or abnormal classes using the value of distance from the Bi-pigment Model on the assumption that the pixel included in the region of an abnormality exists the area. The results of evaluation experiment show that our proposed method having a high degree of usability for fruit grading and a difference between variance covariance matrix and autocorrelation matrix for generating Bi-pigment Model. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Grading / Fruit / Bi-pigment Model / Principal component analysis |
Paper # | PRMU2013-80 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2013/12/5(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Automatic Fruit Grading system based on Bi-pigment Model |
Sub Title (in English) | |
Keyword(1) | Grading |
Keyword(2) | Fruit |
Keyword(3) | Bi-pigment Model |
Keyword(4) | Principal component analysis |
1st Author's Name | Kasumi ITO |
1st Author's Affiliation | Information and Computer Science, Graduate School of Engineering, Mie University() |
2nd Author's Name | Wataru OHYAMA |
2nd Author's Affiliation | Information and Computer Science, Graduate School of Engineering, Mie University |
3rd Author's Name | Tetsushi WAKABAYASHI |
3rd Author's Affiliation | Information and Computer Science, Graduate School of Engineering, Mie University |
4th Author's Name | Fumitaka KIMURA |
4th Author's Affiliation | Information and Computer Science, Graduate School of Engineering, Mie University |
Date | 2013-12-12 |
Paper # | PRMU2013-80 |
Volume (vol) | vol.113 |
Number (no) | 346 |
Page | pp.pp.- |
#Pages | 5 |
Date of Issue |