Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for constructing cascade classifier, method and device for recognizing object

A technology of cascaded classifiers and classifiers, applied in the field of pattern recognition, can solve the problems of slow operation speed, high complexity of classifier operation and high construction cost, and achieve the effect of simple method, fast classification speed and high precision

Inactive Publication Date: 2011-02-02
FUJITSU LTD
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The above-mentioned classifiers in the prior art have high computational complexity, high construction cost, and slow computational speed

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
  • Method for constructing cascade classifier, method and device for recognizing object
  • Method for constructing cascade classifier, method and device for recognizing object
  • Method for constructing cascade classifier, method and device for recognizing object

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] Embodiments of the present invention will be described below with reference to the drawings. It should be noted that representation and description of components and processes that are not related to the present invention and known to those of ordinary skill in the art are omitted from the drawings and descriptions for the purpose of clarity.

[0019] Currently, the Chinese character set included in GBK Level 1 includes 3755 characters. The English character set includes 62 characters, including: 26 uppercase English characters, 26 lowercase English characters and 10 numbers. Most Chinese characters (such as those shown in Table 1) are quite different from English characters. However, some Chinese characters (such as those shown in Table 2) are structurally similar to English characters.

[0020] Table 1:

[0021]

[0022] Table 2:

[0023]

[0024] These structurally similar characters may overlap in the feature space, resulting in recognition difficulties an...

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 method for constructing a cascade classifier, a method and a device for recognizing an object. The method for constructing the cascade classifier comprises the steps of: constructing a first-stage node classifier to be used as a temporary cascade classifier based on a first-stage sample set, circularly executing the following steps of: constructing a next-stage node classifier based on a next-stage sample set, wherein the next-stage sample set is a set of samples aiming at the condition that the last-stage recognition fraction of a last-stage node classifier is less than the sum of the last-state recognition threshold corresponding to the last-stage node classifier and recognition fraction threshold deviator which is not less than 0; cascading the next-stage nodeclassifier with the temporary cascade classifier to construct a new temporary cascade classifier; comparing recognition precision of the temporary cascade classifier before and behind being additionally provided with the next-stage node classifier; and if the next-stage node classifier is additionally provided, keeping the recognition unchangeable or reduced, determining the temporary cascade classifier after the next-stage node classifier is deleted as the final cascade classifier and terminating the circulation, and if not, continuing constructing the next next-stage node classifier.

Description

technical field [0001] The present invention relates generally to the field of pattern recognition, and more particularly to cascaded classifiers. Background technique [0002] With the development of computer technology, image processing technology has also made great progress. At present, people have been able to use Optical Character Recognition (OCR) technology to recognize text in a document image, avoiding heavy labor of manual keyboard entry. [0003] It is well known that character language type recognition technology helps to improve the performance of OCR. The text unit of most existing character language type recognition technologies is the entire document image, text line or word, which requires the assumption of language identity within the text unit, so it has certain limitations in use. [0004] However, in reality, there are multilingual mixed documents, which include two or more languages ​​and characters, and the languages ​​and characters are mixed and a...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
Inventor 朱远平孙俊皆川明洋堀田悦伸直井聪于浩
Owner FUJITSU LTD