Abstract
In the field of computer vision, large-scale image classification tasks are both important and highly challenging. With the ongoing advances in deep learning and optical character recognition (OCR) technologies, neural networks designed to perform large-scale classification play an essential role in facilitating OCR systems. In this study, we developed an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters by using deep learning neural networks and fine-tuning techniques. The proposed framework comprises four components, including training dataset synthesis and background simulation, image preprocessing and data augmentation, the process of training the model, and transfer learning. The training data synthesis procedure is composed of a character font generation step and a background simulation process. Three background models are proposed to simulate the factors of the background noise patterns on ID cards. To expand the diversity of the synthesized training dataset, rotation and zooming data augmentation are applied. A massive dataset comprising more than 19.6 million images was thus created to accommodate the variations in the input images and improve the learning capacity of the CNN model. Subsequently, we modified the GoogLeNet neural architecture by replacing the fully connected layer with a global average pooling layer to avoid overfitting caused by a massive amount of training data. Consequently, the number of model parameters was reduced. Finally, we employed the transfer learning technique to further refine the CNN model using a small number of real data samples. Experimental results show that the overall recognition performance of the proposed approach is significantly better than that of prior methods and thus demonstrate the effectiveness of proposed framework, which exhibited a recognition accuracy as high as 99.39% on the constructed real ID card dataset.
Highlights
Image classification has always been one of the prominent topics in deep learning, and Chinese character recognition is one application of it
Using the different font generation, background simulation, and data augmentation processes illustrated in Sections 3.1 and 3.2, we expanded the dataset to generate a sufficient amount of training data, using up to more than 19.6 million images to accommodate the diversity of input image variations and strengthen the recognition capability of the convolutional neural network (CNN) model
We developed an automatic optical character recognition (OCR) system for identifying up to 13,070 large-scale printed Chinese characters by using deep learning neural networks and fine-tuning techniques
Summary
Image classification has always been one of the prominent topics in deep learning, and Chinese character recognition is one application of it. These challenges motivated us to study the problem of a large-scale classification model for ID card character recognition. We developed an automatic OCR system to identify up to 13,070 large-scale printed Chinese characters using deep learning neural networks and fine-tuning techniques. (1) Training dataset synthesis is used to generate a synthesized training set of character images with different Chinese character fonts and simulated. (4) we collected several samples of real Chinese characters on ID cards and performed data augmentation and balancing processing for further transfer learning; the recognition results were obtained as the output. We developed a large-scale OCR system to identify printed Chinese characters using a deep learning neural network. The resultant character image was blurred with a Gaussian filter to smooth the appearance of the generated character image
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
