A design of a preprocessing framework for large database of historical documents
Proceedings of the 2011 Workshop on Historical Document Imaging and Processing
Shape based local thresholding for binarization of document images
Pattern Recognition Letters
Efficient illumination compensation techniques for text images
Digital Signal Processing
Support value based stent-graft marker detection
Pattern Recognition
A learning framework for the optimization and automation of document binarization methods
Computer Vision and Image Understanding
Historical document image restoration using multispectral imaging system
Pattern Recognition
Historical document binarization based on phase information of images
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume 2
An optimization for binarization methods by removing binary artifacts
Pattern Recognition Letters
A combined approach for the binarization of handwritten document images
Pattern Recognition Letters
Hi-index | 0.00 |
Document images often suffer from different types of degradation that renders the document image binarization a challenging task. This paper presents a document image binarization technique that segments the text from badly degraded document images accurately. The proposed technique is based on the observations that the text documents usually have a document background of the uniform color and texture and the document text within it has a different intensity level compared with the surrounding document background. Given a document image, the proposed technique first estimates a document background surface through an iterative polynomial smoothing procedure. Different types of document degradation are then compensated by using the estimated document background surface. The text stroke edge is further detected from the compensated document image by using L1-norm image gradient. Finally, the document text is segmented by a local threshold that is estimated based on the detected text stroke edges. The proposed technique was submitted to the recent document image binarization contest (DIBCO) held under the framework of ICDAR 2009 and has achieved the top performance among 43 algorithms that are submitted from 35 international research groups.