A ground-truthing tool for making a database of online handwritten mathematical expressions

نویسندگان

  • Anh Duc LE
  • Masaki NAKAGAWA
چکیده

This paper presents a tool for labeling online handwritten mathematical expressions with ground truth automatically. We apply symbol hypotheses for segmentation and spatial relationship for matching between a template expression and a sequence of input strokes. By using this tool, we experimentally made a ground-truthed database contains 1,407 mathematical expressions and over 12000 symbols. Statistical features extracted from the ground-truthed database are to be used to determine spatial relationship in matching process. Keyword Recognition of Handwritten Mathematical Expressions, Mathematical Expression Database, Ground Truthing Online Mathematical Expression, Spatial Relationship Classification

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Transcript mapping for handwritten Chinese documents by integrating character recognition model and geometric context

Creating document image datasets with ground-truths of regions, text lines and characters is a prerequisite for document analysis research. However, ground-truthing large datasets is not only laborious and time consuming but also prone to errors due to the difficulty of character segmentation and the large variability of character shape, size and position. This paper describes an effective reco...

متن کامل

Online Handwritten Mathematical Expressions Recognition System Using Fuzzy Neural Network

The paper is devoted to the development of the new online handwritten mathematical expressions recognition system. The paper presents the recognition method to the handwritten symbols using fussy neural network NEFCLASS as a means for classification.

متن کامل

Recognition of Online Handwritten Mathematical Expressions Using Convolutional Neural Networks

We further investigate the problem of recognizing handwritten mathematical expressions, which we also chose for our CS221 final project [3]. Being able to change handwritten expressions into LATEX has applications for consumers and academics. While large amounts of work have been done for digit and character recognition [2] [10], much less progress has been made surrounding handwritten expressi...

متن کامل

Persian Handwritten Digit Recognition Using Particle Swarm Probabilistic Neural Network

Handwritten digit recognition can be categorized as a classification problem. Probabilistic Neural Network (PNN) is one of the most effective and useful classifiers, which works based on Bayesian rule. In this paper, in order to recognize Persian (Farsi) handwritten digit recognition, a combination of intelligent clustering method and PNN has been utilized. Hoda database, which includes 80000 P...

متن کامل

A hybrid classifier for handwritten mathematical expression recognition

In this paper we propose a hybrid symbol classifier within a global framework for online handwritten mathematical expression recognition. The proposed architecture aims at handling mathematical expression recognition as a simultaneous optimization of symbol segmentation, symbol recognition, and 2D structure recognition under the restriction of a mathematical expression grammar. To improve the c...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014