Tagging Products using Image Classification

Associating labels with online products can be a laborintensive task. We study the extent to which a standard “bag of visual words” image classifier can be used to tag products with useful information, such as whether a sneaker has laces or velcro straps. Using Scale Invariant Feature Transform (SIFT) image descriptors at random keypoints, a hierarchical visual vocabulary, and a variant of nearestneighbor classification, we achieve accuracies between 66% and 98% on 2and 3-class classification tasks. We show that we can improve performance over standard k-nearest neighbor (k-NN) by modifying it to consider all other images while giving the most weight to the closest ones. We also increase accuracy by combining information from multiple views of the same product.