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 and anti-counterfeiting 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 FC 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.

This study investigated the inhibitory effect of Siegesbeckia orientalis ethanolic extract (SOE) on growth and metastasis of hepatic tumors in C57BL/6JNarl mice, which is the model of tumor-igenesis induced by subcutaneous injection of Hepa1-6 murine hepatoma cells on the back of mice. Feeding 25 mg SOE/kg BW daily for 14 days effectively reduced the hepatoma weight in tu-mor-bearing mice by 59.7%. SOE intervention reduced the expression of anti-apoptotic Bcl-2 gene in tumor tissue by 48.5% and down-regulated the antioxidant system, by reducing the gene ex-pression of catalase (48.0%), glutathione peroxidase (46.3%), and superoxide dismutase (32.0%). In addition, SOE intervention increased the production of ROS by 21.4%, and the gene expression of pro-inflammatory cytokines TNF-α, IL-1β, and IL-6 by 135.3%, 179.3% and 91.7%, respectively, indicating that SOE intervention promoted the acute inflammatory response. Results of H&E staining analysis showed that SOE had the ability to inhibit angiogenesis in tumor tissue. Fur-thermore, SOE treatment inhibited the expression of migration-related genes, such as MMP-2, MMP-7, MMP-9 and β-catenin, and the inhibition rates were 24.8%, 27.4%, 10.4% and 21.9%, respectively. These results imply that SOE had the ability to suppress tumor metastasis. On the other hand, SOE intervention decreased the serum contents of inflammatory cytokines, such as TNF-α, IL-1β and IL-6 by 27.4%, 30.4%, and 30.7%, respectively, indicating that SOE intervention has an anti-inflammatory effect on normal tissues of mice. Since SOE intervention had no signif-icant effect on liver and kidney weights, and no mice died throughout the experiment, it shows that it is safe to feed SOE under this experimental condition. Based on the above results, SOE has a great potential to be used in the treatment of hepatoma.