A Novel Unified Deep Neural Networks Methodology Foruse Bydate Recognition In Retail Food Package Image

There exist various types of information on retail food packages, includinguse bydate, food product name and so on. The correct coding ofuse bydates on food packages is vitally important for avoiding potential health risks to customers caused by erroneous mislabelling ofuse bydates. It is extremely tedious and laborious to check theuse bydates coding manually by a human operator, which is prone to generate errors thus an automatic system for validating the correctness of the coding ofuse bydates is needed. In order to construct such a system, firstly it needs to correctly automatic recognizeuse bydates on food packages. In this work, we propose a novel dual deep neural networks-based methodology for automatic recognition ofuse bydates in food package photographs recorded by a camera, which is a combination of two networks: a fully convolutional network foruse bydate ROI detection and a convolutional recurrent neuron network for date character recognition. The proposed methodology is the first attempt to apply deep learning for automaticuse bydate recognition. From comprehensive experimental evaluations, it is shown that the proposed method can achieve high accuracies inuse bydate recognition (more than 95% on our testing dataset), given food package images with varying lighting conditions, poor printing quality and varied textual/pictorial contents collected from multiple real retailer sites.