Deep Networks for Degraded Document Image Binarization through Pyramid Reconstruction

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 遥感图像处理团队

	Deep Networks for Degraded Document Image Binarization through Pyramid Reconstruction
	Gaofeng Meng; Kun Yuan; Ying Wu; Shiming Xiang; Chunhong Pan
	2017
会议日期	November 13-15, 2017
会议地点	Kyoto, Japan
页码	727-732
英文摘要	Binarization of document images is an important processing step for document images analysis and recognition. However, this problem is quite challenging in some cases because of the quality degradation of document images, such as varying illumination, complicated backgrounds, image noises due to ink spots, water stains or document creases. In this paper, we propose a framework based on deep convolutional neural-network (DCNN) for adaptive binarization of degraded document images. The basic idea of our method is to decompose a degraded document image into a spatial pyramid structure by using DCNN, with each layer at different scale. Then the foreground image is sequentially reconstructed from these layers in a coarse-to-fine manner by using deconvolutional network. Such kind of decomposition is quite beneficial, since multiresolution supervision information can be directly introduced into network learning.We also define several loss functions about label consistency and foregrounds smoothing to further regularize the training of the network. Experimental results demonstrate the effectiveness of the proposed method.
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/15339]
专题	自动化研究所_模式识别国家重点实验室_遥感图像处理团队
推荐引用方式 GB/T 7714	Gaofeng Meng,Kun Yuan,Ying Wu,et al. Deep Networks for Degraded Document Image Binarization through Pyramid Reconstruction[C]. 见:. Kyoto, Japan. November 13-15, 2017.