Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Online hand-written chemical symbol identification method based on Hidden Markov model

A chemical symbol and recognition method technology, applied in character and pattern recognition, computer components, instruments, etc., can solve problems such as large-scale chemical symbol collection, deformation of handwritten samples, and uneven quality of strokes, so as to avoid interference and reduce Performance consumption, the effect of accurate identification

Inactive Publication Date: 2017-05-10
NANKAI UNIV
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The difficulties in conducting related research include: (1) the set of chemical symbols is relatively large, and there are many similar structures in it; (2) the size and position of the symbols imply certain chemical meanings, which need to be analyzed and transmitted after the symbols are recognized. Concealed information; (3) The handwritten sample is seriously deformed and the stroke quality is uneven
Therefore, accurate recognition of handwritten chemical symbols is a challenging task

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Online hand-written chemical symbol identification method based on Hidden Markov model
  • Online hand-written chemical symbol identification method based on Hidden Markov model
  • Online hand-written chemical symbol identification method based on Hidden Markov model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] The specific implementation process is as follows:

[0058] Step 1: Collect chemical symbol samples and preprocess them

[0059] Organize 20 users to use HP Tablet PC for sample collection. This work was carried out using the collection software HCSC under the Windows Vista operating system, and a total of 12444 valid symbol samples were collected. Taking the 102 complete symbols written by each user as a set, the longest writing time is 22 minutes, the shortest writing time is 6 minutes, and the average writing time is 11 minutes; the average writing time of a single sample is 2.58 seconds, of which 1.753 seconds for writing, Pen 1.85 seconds.

[0060] The five-step preprocessing operations of deduplication, interpolation, detection of sharp points, dehooking, and smoothing are performed on the samples in sequence. The hook structure generally occurs when starting or writing, with small length and large angle change, which has a serious impact on the recognition accu...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An online hand-written chemical symbol identification method based on the Hidden Markov model solves the problem of the online identification of chemical symbol written by any one writer on any one device. The method constructs a processing framework of identification of the online written chemical symbol, and employs a hierachical processing and step-by-step optimization strategy. The method based on a support vector machine selects grid features and peripheral contour features to distinguish organic ring symbols and non-ring symbols, and the classification error rate is controlled under 0.2%. The method based on the Hidden Markov model to identify concrete symbols, and the accuracy is more than 90%. In order to improve the precision design, a set of preprocessing flow is designed, and the post-processing measures such as candidate result reliability, chemical symbol adjacent matrixes and the atom element conservation detection are employed. The method has the universal meaning, systematicness and completeness through the experimental proof of the data source such as the input of a Tablet PC, a digital panel and a mouse simulation pen, and can be used for the online hand-written chemical symbol identification field.

Description

[0001] 【Technical field】 [0002] The invention belongs to the field of pattern recognition and human-computer interaction, and in particular relates to an online handwritten chemical symbol recognition method based on a hidden Markov model. [0003] 【Background technique】 [0004] A chemical formula (chemical equation) is a formula that expresses the law of a chemical reaction, and is the most important form of expression of chemistry and chemical activities. A chemical formula, like a mathematical formula, is a very widely used expression in the field of natural science. With the development of information society, more and more chemistry-related work is transferred to electronic equipment. However, how to quickly and efficiently enter chemical knowledge, especially chemical formulas, into the computer is still a difficult problem. At present, chemical formulas are mainly entered by professional software. The common disadvantages of this type of software include complex int...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/46
CPCG06V30/2276G06V10/457
Inventor 杨巨峰王恺许静陈丽怡
Owner NANKAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products