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

String-kernel-based hand-drawn sketch recognition method

A technology for sketch recognition and character strings, which is applied in the field of hand-drawn sketch recognition, can solve the problems of graphic complexity, information loss, retention, etc., and achieve high recognition accuracy and simple realization

Inactive Publication Date: 2011-09-14
TIANJIN UNIV
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Usually, it needs to divide different graphic geometric features in a certain way. The extraction of stroke information is essentially to reduce the dimension of stroke information. However, due to the complexity of graphics, it is difficult to retain the complete information of strokes with fixed-dimensional geometric features. Part of the information is in Lost during dimensionality reduction
Therefore, the accuracy of geometric feature recognition is not high. The geometric feature representations of some visually dissimilar graphics may be similar.

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
  • String-kernel-based hand-drawn sketch recognition method
  • String-kernel-based hand-drawn sketch recognition method
  • String-kernel-based hand-drawn sketch recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Firstly, based on the idea of ​​area filling, the hand-drawn sketches are mapped to feature strings, and secondly, the training samples are trained by the Support Vector Machine (SVM) based on the String Kernelho to obtain a classifier, and then the obtained The classifier classifies and recognizes the sketches to be recognized, and maps fuzzy, irregular hand-drawn sketches to precise geometric shapes.

[0049] The system of the present invention operates under the visual C++6.0 environment, is based on the libsvm software package, and is developed using C++ language.

[0050] First, build a single-document view project in visual C++6.0; transplant the libsvm software package with String Kernel into the built project, and write the code of the characteristic string mapping module. Prepare training data: 1150 samples were collected, 1000 samples were used as training data and 150 samples were used as test data, and the sketches were mapped to feature strings, and the obt...

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

The invention discloses a support-vector-machine-based kernel matrix approximating method. The method comprises the following steps of: firstly, mapping a hand-drawn sketch into a feature string on the basis of a region-filling concept; secondly, training a training sample by using a support vector machine (SVM) on the basis of a string kernel to obtain a classifier; and finally, classifying and recognizing the sketch to be recognized by using the classifier obtained through training, and mapping the blurred and irregular hand-drawn sketch into a precise geometrical shape. Compared with the prior art, the method has the advantages that: the method is unrelated to the position, the size and the drawing way of the sketch and a user is allowed to draw the sketch in an individual habitual way; and by the string-kernel-based hand-drawn sketch recognition method, the recognition accuracy is relatively high and the method is easy to implement.

Description

technical field [0001] The present invention relates to hand-drawn sketch recognition based on kernel method. Background technique [0002] The background technology involved in the present invention comprises the following three aspects: [0003] 1. Hand-drawn sketch recognition [0004] Hand-drawn sketch recognition is to map the fuzzy sketch expression obtained by pen-based interaction to precise graphic expression, that is, to mine the sketch shape constraints from the sketch information that is constantly increasing in the process of human-computer interaction, and to understand the original intention of the user. Small, irregular sketches are recognized as regular, precise geometric shapes. [0005] At present, there are mainly three types of graphic recognition methods, that is, the method based on stroke representation; the method based on the representation of primitives such as straight lines, arcs, and curves; and the graphic recognition method based on geometri...

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): G06K9/20G06K9/62
Inventor 廖士中段孟华
Owner TIANJIN 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com