Proposed is an industrialized
system (1) and method for
rice grain recognition. An
optical image (123) is taken by a user (5) and transmitted to a digital platform (11), wherein the
system (1) segments the
optical image (123) and extracts and / or measures appropriate grain features (41) from the image (123) describing different aspects of the grain (4). The image (123) is processed by the
system (1), comprising a selector (1122) selecting different
machine learning structures (11211,...,1121i), applying the different
machine learning structures (11211,...,1121i) to the extracted features (41) for
rice grain (4) recognition, and selecting the best of the applied
machine learning structures (11211,...,1121i) by a random sampling process. The selected best of the applied
machine learning structures (11211,...,1121i) is further optimized by varying an appropriate threshold (11231) by a threshold trigger (1123) based on a
confusion matrix comprising (11221). An active learning structure (113) based on the
confusion matrix comprising (11221) the values of True Positive (TP), False Negative (FN), False Positive (FP) and True Negative (TN) for the classified rice grains, providing a
feedback loop to the user or human expert (5), wherein the system (1) is retrained based on the feedback parameters of the
feedback loop (1132).