Crop Images Segmentation using Adaptive Morphologic Descriptors

This research is focused on the segmentation improvement of crop images by using adaptive morphologic descriptors instead of classic algorithms like K-means and the top-hat operator using predefined shapes like disk or diamond. Obtained results shows that using an adaptive morphologic descriptor improves the segmentation performance against the classic shapes like disc and diamond. In order to measure the process a set of 60 crop images was used including their respective ground-truth images. The images were segmented using the K-Means algorithm and the top-hat operator with the disk and diamond shapes at different sizes into a range to validate their performance. In order to generate the adaptive morphologic descriptor, the Univariated Marginal Distribution Algorithm was used with no constraints by exploring a range of different sizes. Also, performance metrics like receiver operating characteristic and accuracy rate were applied to the generated data in order to assess the results.