Generative Adversarial Classifier for Handwriting Characters Super-Resolution
This addresses the challenge of generating super-resolved images suitable for classification in handwriting character recognition, offering a domain-specific improvement.
The paper tackles the problem of low-resolution handwriting character recognition by proposing a Generative Adversarial Classifier (GAC) that integrates a classifier into GAN training to improve super-resolution for classification, achieving approximately 10% and 20% higher performance than state-of-the-art methods on CASIA-HWDB1.1 and MNIST datasets for 8x super-resolution.
Generative Adversarial Networks (GAN) receive great attentions recently due to its excellent performance in image generation, transformation, and super-resolution. However, GAN has rarely been studied and trained for classification, leading that the generated images may not be appropriate for classification. In this paper, we propose a novel Generative Adversarial Classifier (GAC) particularly for low-resolution Handwriting Character Recognition. Specifically, involving additionally a classifier in the training process of normal GANs, GAC is calibrated for learning suitable structures and restored characters images that benefits the classification. Experimental results show that our proposed method can achieve remarkable performance in handwriting characters 8x super-resolution, approximately 10% and 20% higher than the present state-of-the-art methods respectively on benchmark data CASIA-HWDB1.1 and MNIST.