Localization and Segmentation of A 2D High Capacity Color Barcode

A 2D color barcode can hold much more information than a binary barcode. Barcodes are often intended for consumer use where using a cellphone, a consumer can take an image of a barcode on a product, and retrieve relevant information about the product. The barcode must be read using computer vision techniques. While a color barcode can hold more information, it makes this vision task in consumer scenarios unusually challenging. We present our approach to the localization and segmentation of a 2D color barcode in such challenging scenarios, along with its evaluation on a diverse collection of images of Microsoft's recently launched high capacity color barcode (HCCB). We exploit the unique trait of barcode reading: the barcode decoder can give the vision algorithm feedback, and develop a progressive strategy to achieve both - high accuracy in diverse scenarios as well as computational efficiency.