Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Image Feature Selection in Machine Vision for Determining Sunagoke Moss Water Content (Bio-inspired Approaches

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2010 Pittsburgh, Pennsylvania, June 20 - June 23, 2010  1008582.(doi:10.13031/2013.29661)
Authors:   Yusuf Hendrawan, Haruhiko Murase
Keywords:   bio-inspired algorithms, feature selection, machine vision, Sunagoke moss, water content.

One of the primary determinants of Sunagoke moss Rachomitrium japonicum growth is water availability. There is need to develop non-destructive method for sensing water content of cultured Sunagoke moss to realize automation and precision irrigation in a close bio-production systems. Machine vision can be utilized as non-destructive sensing to recognize changes in some kind of features that describe the water conditions from the appearance of wilting Sunagoke moss. The goal of this study is to propose and investigate bio-inspired algorithms i.e. Neural-Ant Colony Optimization, Neural-Simulated Annealing and Neural-Genetic Algorithms to find the most significant sets of image features suitable for predicting water content of cultured Sunagoke moss. Image features consist of 8 color features, three morphological features and 90 textural features (gray level co-occurrence matrix, RGB, HSV and HSL color co-occurrence matrix textural features). Textural features consist of energy, entropy, contrast, homogeneity, inverse difference moment, correlation, sum mean, variance, cluster tendency and maximum probability. The specificity of this problem is that we are not looking for single image feature but several associations of image features that may be involved in determining water content of Sunagoke moss. Neural-Ant Colony Optimization had the best performance as a feature selection technique. The minimum average testing prediction mean square error achieved was 1.75x10-3. There is significant improvement between method using feature selection and method without feature selection.

(Download PDF)    (Export to EndNotes)