Apple mealiness detection using fluorescence and self-organising maps |
| |
Authors: | Dimitrios Moshou Stijn Wahlen Reto Strasser Ann Schenk Herman Ramon |
| |
Institution: | a K.U. Leuven, Laboratory for Bio-Mechatronics and Processing, Department of Agro-Engineering and Economics, Kasteelpark Arenberg, 30, B-3001, Heverlee, Belgium;b Laboratory of Bioenergetics, Department of Plant Biology, Université de Genève, Chemin des Embrouchis, 10, CH 1254, Jussy/Lullier, Genéve, Switzerland;c VCBT, Flanders Centre for Postharvest Technology, Willem De Croylaan 42, B-3001, Heverlee, Belgium |
| |
Abstract: | The chlorophyll fluorescence kinetics of ‘Jonagold’ and ‘Cox’ apples, stored under different conditions to induce mealiness, were measured. Three different storage conditions were considered causing three mealiness levels: not mealy, moderately and strongly mealy. Also destructive measurements of the texture (firmness, hardness, juice content and soluble solids content) were done. Classification into different mealiness levels based on the fluorescence measurements was more performant than a classification based on the destructive measurements. To estimate the mealiness level in a non-destructive way from the fluorescence features, a number of different classifiers were constructed. Quadratic discriminants and supervised and unsupervised neural networks were tested and compared. The self-organising map gives promising results when compared with the multi-layer perceptrons and quadratic discriminant analysis. The different advantages of the constructed classifiers suggest that fluorescence can be used in an automatic sorting line to assess certain types of mealiness. |
| |
Keywords: | Neural networks Self-organising systems Classification Agriculture Pattern recognition Quality control Mealiness |
本文献已被 ScienceDirect 等数据库收录! |
|