Shipping labels are widely used in logistics. It is important to ensure label quality and to verify the shipping label on the package in the logistics. We developed a verification and recognition method for various types of shipping labels by using deep neural networks. The experimental results showed 96% recognition accuracy and the method is rotation-invariant. Also, we introduce Google Maps API for validating the address which can reduce the cost for returning packages due to the invalid address. To train and evaluate the method, we have generated and collected 25 different types of the shipping label dataset. We plan to release the dataset on our website.

Paper

• LINK