Review the latest experiments using a computer-vision-based methodology for automatic image-based classification of 2042 training images and 284 unseen (test) images divided into 68 categories of gemstones.
Join Bona Hiu Yan Chow and Constantino Carlos Reyes-Aldasoro as they share research in a paper published in MDPI Open Access Journals.
Included in the paper is a review of how a series of feature extraction techniques (33 including colour histograms in the RGB, HSV and CIELAB space, local binary pattern, Haralick texture and grey-level co-occurrence matrix properties) were used in combination with different machine-learning algorithms (Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbour, Decision Tree, Random Forest, Naive Bayes and Support Vector Machine); how deep-learning classification with ResNet-18 and ResNet-50 was also investigated.; and how the optimal combination was provided by a Random Forest algorithm with the RGB eight-bin colour histogram and local binary pattern features, with an accuracy of 69.4% on unseen images; the algorithms required 0.0165 s to process the 284 test images.
Also included, most importantly, how the results compared against three expert gemologists who participated in the experiments.
Read the complete paper here.
Disclaimer: The views, opinions or examples included in linked article are those of the author and do not necessarily reflect an official policy or position of ASA or its members.