Abstract
Abstract
In order to improve the accuracy and stability of metal stamping character (MSC) automatic recognition technology, a metal stamping character enhancement algorithm based on conditional Generative Adversarial Networks (cGAN) is proposed. We identify character regions manually through region labeling and Unsharpen Mask (USM) sharpening algorithm, and make the cGAN learn the most effective loss function in the adversarial training process to guide the generated model and distinguish character features and interference features, so as to achieve contrast enhancement between character and non-character regions. Qualitative and quantitative analyses show that the generated results have satisfactory image quality, and that the maximum character recognition rate of the recognition network ASTER is improved by 11.03%.
Subject
General Physics and Astronomy
Reference20 articles.
1. Real-time scene text detection with differentiable binarization;Liao,2020
2. Efficient and accurate arbitrary-shaped text detection with pixel aggregation network;Wang,2019
3. Aster: An attentional scene text recognizer with flexible rectification;Shi;IEEE Trans. Pattern Anal. Mach. Intell.,2018
4. Moran: A multi-object rectified attention network for scene text recognition;Luo;Pattern Recogn,2019
5. AdOtsu: An adaptive and parameterless generalization of Otsu’s method for document image binarization;Moghaddam;Pattern Recogn,2012