A Medical Knowledge Based Postprocessing Approach for Doctor's Handwriting Recognition

  title={A Medical Knowledge Based Postprocessing Approach for Doctor's Handwriting Recognition},
  author={Qi Chen and Tianxia Gong and Linlin Li and Chew Lim Tan and Boon Chuan Pang},
  journal={2010 12th International Conference on Frontiers in Handwriting Recognition},
  • Qi Chen, T. Gong, B. Pang
  • Published 16 November 2010
  • Computer Science
  • 2010 12th International Conference on Frontiers in Handwriting Recognition
In this paper, we propose a novel post processing approach for on-line handwriting recognition. Differing from the existing linguistic knowledge-based methods, we make use of domain specific knowledge to improve the performance of recognition. Our system recognizes doctor’s handwriting which often poses great challenges in readability, and then enhances the quality of recognized text by analyzing and restoring the text with a medical knowledge model. We show experiments with this approach on a… 

Figures from this paper

A New Approach to Information Retrieval based on Keyword Spotting from Handwritten Medical Prescriptions

This paper proposes a document retrieval approach based on word spotting for medical prescriptions that involves extracting the domain specific knowledge of doctors by recognising printed text on letterhead part of the prescription in order to narrow down the search operation for word spotting in handwritten portion of the prescriptions.

Towards an On-line Handwriting Recognition Interface for Health Service Providers using Electronic Medical Records

A handwriting recognition interface for EMR data entry that is user-friendly and is unobstructive to the patient-physician relationship is described.



Handwriting recognition using semantic information

This paper describes the development of techniques that use existing sources of semantic information, such as machine-readable dictionaries and text corpora, to improve the performance of handwriting recognition systems.

Integration of lexical and syntactical knowledge in a handwriting-recognition system

The integration of linguistic information to correct words not recognized by a handwritingrecognition system is shown to be an effective approach, and one that might be worth pursuing.

Shape Encoded Post Processing of Gurmukhi OCR

A method for detection and correction of errors in recognition results of handwritten and machine printed Gurmukhi OCR and suggestions are made based on the similarity of the source word with the words of the same code present in dictionary.

Automatic bankcheck processing

Automatic bankcheck processing - a new engineered system, G. Dimauro et al a prototype for Brazilian bankcheck recognition, and an evolutionary approach to the use of neural networks in the segmentation of handwritten numerals.

Handwritten Address Interpretation: A Task of Many Pattern Recognition Problems

  • S. Srihari
  • Computer Science
    Int. J. Pattern Recognit. Artif. Intell.
  • 2000
A gradation of pattern discrimination problems is encountered in interpreting handwritten postal addresses and the performances of each of the subsystems in a handwritten address interpretation system developed at CEDAR are described.

LipiTk: a generic toolkit for online handwriting recognition

The first version of the Lipi Toolkit, a generic toolkit whose aim is to facilitate development of online handwriting recognition engines for new scripts, and simplify integration of the resulting engines into real-world application contexts is described.

Degraded text recognition using visual and linguistic context

This thesis addresses problems in degraded text recognition and discusses potential solutions through passage-level postprocessing, to develop a postprocessing methodology from a broader perspective.

Experiments in Text Recognition with Binary n-Gram and Viterbi Algorithms

  • J. HullS. Srihari
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1982
This correspondence describes the underlying theory of each approach in unified terminology, and presents new implementation algorithms for each approach, including a storage efficient data structure for the binary n-gram algorithm and a recursive formulation for the Viterbi algorithm.

A Contextual Postprocessing System for Error Correction Using Binary n-Grams

Various algorithms utilizing context are considered, from a dictionary algorithm which has available the maximum amount of information, to a set of contextual algorithms utilizing positional binary n-gram statistics.

The Viterbi algorithm as an aid in text recognition (Corresp.)

  • D. Neuhoff
  • Computer Science
    IEEE Trans. Inf. Theory
  • 1975
English is modeled as a Markov source and the Viterbi algorithm is used to do maximum a posteriori sequence estimation on the output of an optical character reader (OCR).