ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
We propose further improvement of a handwriting recognition method that avoids segmentation while able to recognize words that were never seen before in handwritten form. This met...
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
In this paper we propose to define a measure of visual similarity to compare different pages in a corpus. This measure is based on the analysis of the visual layout saliency of th...
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
This paper summarises the achievements of a multidisciplinary Bioinformatics project which has the objective of providing a general mechanism for efficient computerisation of type...
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
The increasing availability of high performance, low priced, portable digital imaging devices has created a tremendous opportunity for supplementing traditional scanning for docum...
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
This paper presents a new technique to improve the combination of classification decisions obtained from local analysis of patterns. Specifically, a genetic algorithm is used to d...
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
In this paper I will try to explain the nature of document understanding in all of its dimensions. Therefore I will first describe the characteristics of data, knowledge, and info...
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
Existing skeletonization methods operate directly on the binary image ignoring the gray-level information. In this paper we propose a new method for the skeletonization of handwri...
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
With an aim to high-level understanding of the mathematical contents in a document image the requirement of math-zone extraction and recognition technique is obvious. In this pape...
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
In this paper, we propose a new character generation method from on-line handwriting recognizers based on Bayesian networks. On-line handwriting recognizers are trained with handw...
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
In this paper, we propose a Bayesian network framework for explicitly modeling components and their relationships of Korean Hangul characters. A Hangul character is modeled with h...