Document Annotation and Retrieval Systems
A. Balasubramanian
Digital documents are now omnipresent. Techniques and algorithms to process and understand these documents are still evolving. This thesis focuses on the non-textual documents of textual content. Example of this category are online handwritten documents and scanned printed books. Algorithms for accessing such documents at the content-level are still missing, specially for Indian Languages. This thesis addresses two fundamental problems in this area: Annotation and Retrieval. Annotated datasets of handwriting are a prerequisite for the design and training of hand- writing recognition algorithms. Retrieval from annotated data sets is relatively straightforward. However retrieval from unannotated datasets is still an open problem. We explore algorithms which make these two tasks possible. Annotation of large datasets is a tedious and expensive process. The problem becomes compounded for handwritten documents, where the characters correspond to one or more strokes. We have developed a versatile, robust annotation tool for online handwriting data. This tool is aimed at supporting the emerging UPX/hwDataset schema, a promising successor of the UNIPEN. We provide easy-to-use interface for the annotation tool. However, still the annotation is highly manual. We then propose a novel, automated method for annotation of online handwriting data at the character level, given a parallel corpus of online handwritten data and typed text. The method employs a model-based handwriting synthesis unit to map the two corpora to the same space. Annotation is then propagated to the word level and finally to the individual characters using elastic matching. The initial results of annotation are used to improve the handwriting synthesis model for the user under consideration, which in turn refine the annotation. The method takes care of errors in the handwriting such as spurious and missing strokes and characters. The output is stored in the UPX format. (more...)
| Year of completion: | 2006 |
| Advisor : |
Related Publications
Anand Kumar, A. Balasubramanian, Anoop M. Namboodiri and C.V. Jawahar - Model-Based Annotation of Online Handwritten Datasets, International Workshop on Frontiers in Handwriting Recognition(IWFHR'06), October 23-26, 2006, La Baule, Centre de Congreee Atlantia, France. [PDF]
C. V. Jawahar and A. Balasubramanian - Synthesis of Online Handwriting in Indian Languages, International Workshop on Frontiers in Handwriting Recognition(IWFHR'06), October 23-26, 2006, La Baule, Centre de Congree Atlantia, France. [PDF]
A. Balasubramanian, Million Meshesha and C. V. Jawahar - Retrieval from Document Image Collections, Proceedings of Seventh IAPR Workshop on Document Analysis Systems, 2006 (LNCS 3872), pp 1-12. [PDF]
Sachin Rawat, K. S. Sesh Kumar, Million Meshesha, Indineel Deb Sikdar, A. Balasubramanian and C. V. Jawahar - A Semi-Automatic Adaptive OCR for Digital Libraries, Proceedings of Seventh IAPR Workshop on Document Analysis Systems, 2006 (LNCS 3872), pp 13-24. [PDF]
C. V. Jawahar, Million Meshesha and A. Balasubramanian, Searching in Document Images, Proceedings of the Indian Conference on Vision, Graphics and Image Processing(ICVGIP), Dec. 2004, Calcutta, India, pp. 622--627. [PDF]
A. Bhaskarbhatla, S. Madhavanath, M. Pavan Kumar, A. Balasubramanian, and C. V. Jawahar - Representation and Annotation of Online Handwritten Data, Proceedings of the International Workshop on Frontiers in Handwriting Recognition(IWFHR), Oct. 2004, Tokyo, Japan, pp. 136--141. [PDF]
C. V. Jawahar, A. Balasubramanian and Million Meshesha, Word-Level Access to Document Image Datasets, Proceedings of the Workshop on Computer Vision, Graphics and Image Processing(WCVGIP), Feb. 2004, Gwalior, India, pp. 73--76. [PDF]
Downloads
