With the development of domestic express business in China, there is a potential and huge need for automatic information extraction from express mail images, which however is challenging due to the skewness/folds of the captured express mail images. This paper presents a robust approach to text extraction from camera captured express mail images. Firstly, the proposed approach use a deep direct regression neural network to predict both the express bill region and type; then the form frame lines and corners are detected, with which the Coherent Point Drift (CPD) based point matching is adopted to obtain the mapping between the template and the input image. Finally, based on the mapping, accurate writing fields can be extracted. The Experiments on realistic express mail images demonstrate the effectiveness of the proposed approach.
This paper describes an new method for online handwriting signatures verification. The algorithm is based on "Siamese" deep neural network. This network consists of two identical sub-networks joined at their outputs. During verification the two sub-networks extract features from two signatures, while the joining fully-connected network measures the distance between the two feature vectors to determine whether the signature is genuine. The most remarkable advantage of the system is that it can be trained end-to-end without any handcraft feature extraction except some necessary preprocessing. Experiments on the publicly dataset yielded the performance of 4.5% equal error rate (ERR).