Comparative Analysis of Different Methods for Classifying Polychromatic Sketches
This addresses image classification in a domain where humans are not accustomed, with incremental improvements over existing methods.
The paper tackled the problem of classifying hand-drawn doodles into 170 categories, achieving a best model accuracy of 47.5%, which surpasses human performance of 41%.
Image classification is a significant challenge in computer vision, particularly in domains humans are not accustomed to. As machine learning and artificial intelligence become more prominent, it is crucial these algorithms develop a sense of sight that is on par with or exceeds human ability. For this reason, we have collected, cleaned, and parsed a large dataset of hand-drawn doodles and compared multiple machine learning solutions to classify these images into 170 distinct categories. The best model we found achieved a Top-1 accuracy of 47.5%, significantly surpassing human performance on the dataset, which stands at 41%.