Tablet images are significance vehicles for ancient culture heritage. However, due to natural or artificial destruction, there usually exists a large amounts of noises or scratches in the ancient tablet images, and this makes the recognition of interesting objects carved in the ancient very difficult. To deal with this problem, a method based on transfer learning of DnCNN De-noiser Prior was proposed in this paper. Firstly all parameters of all layers of a DnCNN pre-trained in natural images are transferred to our target networks. The initial trained CNN filter weights were then fine tuned with noised Chinese tablet calligraphy images by back-propagation so that they better reflected the noise modalities of tablet image, where Chinese tablet calligraphy structures are concerned to remove isolated small scratches by combing the connected region technique with DnCNN transfer denoising. Experiments on real noised tablet images demonstrate that the proposed method is effective both in image noise removal and image detail preserve compared with existing image denoising methods.
This paper proposed an integration de-noising method based on self-adaptive manifold filtering and text contour for ancient Chinese calligraphy tablet image. It consists of two main operations in sequence: image smoothing with a non-local means (NL-means) based self-adaptive manifold filter and isolated blocks removal based on text contour. Experiments demonstrate that the proposed method is superior to several recent published stele image de-noising techniques in terms of preserving the character structures.
The Euler number of a binary image is an important topological property for pattern recognition, image analysis, and computer vision. In the proposed algorithm, only three comparisons need to be completed for processing a bit-quad in the given image. Moreover, the proposed algorithm processes three rows simultaneously in the scanning which will reduce the number of checked pixels from 4 to 1.5 for processing each bit-quad, which will lead to an efficient processing. Experimental results demonstrated that the performance of the proposed algorithm significantly overpasses conventional Euler number computing algorithms.