• Corpus ID: 3163538

Classification of Chinese Characters Using Pseudo Skeleton Features

@article{Wen2004ClassificationOC,
  title={Classification of Chinese Characters Using Pseudo Skeleton Features},
  author={Ming-Gang Wen and Kuo-Chin Fan and Chin-Chuan Han},
  journal={J. Inf. Sci. Eng.},
  year={2004},
  volume={20},
  pages={903-922},
  url={https://api.semanticscholar.org/CorpusID:3163538}
}
A novel method to classify machine printed Chinese characters by matching the code strings generated from pseudo skeleton features using a single-font reference database is presented.
View Paper
iis.sinica.edu.tw
6 Citations
Background Citations
2
Methods Citations
2

Figures and Tables from this paper

6 Citations

Using Skeletonization and Shortest Skeleton Path Approach for Chinese Character Representation

This paper adopts skeletonization approach to represent Chinese character and uses the resulting written strokes for optimized matching and uses shortest path method considering end nodes and junction nodes as matching strategy.

Real-time Online Chinese Character Recognition

This system will determine a Chinese character while user is drawing/writing, and two different types of neural networks will be used in the system: multi-layer neural network and convolutional neural network.

Fall 12-20-2016 Real-time Online Chinese Character Recognition

This system will determine a Chinese character while user is drawing/writing, and two different types of neural networks will be used in the system: multi-layer neural network and convolutional neural network.

A pseudo-skeletonization algorithm for static handwritten scripts

A skeletonization approach that has desirable characteristics for the analysis of static handwritten scripts that is particularly useful as a pre-processing step for algorithms that estimate the pen trajectories of static signatures and can be applied to other static handwriting recognition techniques.

An interactive grading and learning system for chinese calligraphy

An interactive calligraphic guiding system is first proposed to grade the score of written characters by using the image processing and the fuzzy inference techniques to learn and practice Chinese calligraphy at home.

Building Handwriting Recognizers by Leveraging Skeletons of Both Offline and Online Samples

A handwriting recognizer based on Deep Bidirectional Long Short-Term Memory and Hidden Markov Model is built by using IAM benchmark databases of offline and online English handwritings plus an internal online handwriting corpus, which outperforms the recognizers built from either offline or online handwriting samples only.

14 References

Coarse classification of Chinese characters via stroke clustering method

Feature extraction methods for character recognition-A survey

Combining statistical and structural approaches for handwritten character description

A structural/statistical feature based vector for handwritten character recognition

Skeletonization of binary images with nonuniform width via block decomposition and contour vector matching

Character preclassification based on genetic programming

Learning String-Edit Distance

The stochastic model allows us to learn a string-edit distance function from a corpus of examples and is applicable to any string classification problem that may be solved using a similarity function against a database of labeled prototypes.

At the frontiers of OCR

It is argued that it is time for a major change of approach to optical character recognition (OCR) research, and new OCR systems should take advantage of the typographic uniformity of paragraphs or other layout components.

The String-to-String Correction Problem

An algorithm is presented which solves the string-to-string correction problem in time proportional to the product of the lengths of the two strings.

A thinning algorithm for discrete binary images