An application of image analysis to dehydration of apple discs

This paper presents a method based on computer vision to analyze the effect of drying on shrinkage, color and image texture of apple discs. A standardized image acquisition system consisting of a digital camera, illumination, computer hardware and software was developed to capture and process the images. All parameters related to shape (area, perimeter, Fourier energy, etc.) decreased with drying time. With regard to sample color, lightness (L*) remained almost constant while the chromatic co-ordinates (a* and b*) increased steadily as drying proceeded. Parameters related to the texture of the image and calculated from the color co-ordinates represented well the complexity and non-homogeneity of the visual appearance of samples. Apple discs were classified into classes depending on external image features at different stages of drying by an Euclidean distance classifier with an accuracy of 95%. This approach has the advantages over conventional methods of inspection of being versatile, quantitative and non-intrusive. (C) 2004 Elsevier Ltd. All rights reserved.