Characteristics information extraction method and device for static image target

A technology of static images and feature information, applied in the field of pattern recognition, can solve the problem of the lack of generality and speed of the selection and retrieval method of image target feature information, and achieve the effect of improving the memory effect.

Active Publication Date: 2012-01-04
NEW FOUNDER HLDG DEV LLC +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problems existing in the prior art, the object of the present invention is to provide a feature information extraction method of a static image target, which is used to solve the problem that the prior art has no universality in selecting and obtaining the feature information of the image target and the existing The problem of slow speed caused by obtaining feature information through complex calculation process

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
  • Characteristics information extraction method and device for static image target
  • Characteristics information extraction method and device for static image target
  • Characteristics information extraction method and device for static image target

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In daily life, through vision, memorizing image information is a basic behavior that we take for granted. However, if you want to express the information you remember, you find that you only remember very little information. Even so, it does not affect your memory and recognition of daily image information. This is the basic characteristic of image thinking. It is the core idea of ​​the present invention to simulate image thinking and construct a method for extracting feature information of static image objects. The memory of the main features of the image target is realized through a small amount of information.

[0031] The embodiment of the present invention provides a method for extracting feature information of a static image target. By searching the boundary points of the static image target, the area information of the static image target is obtained, and the feature elements in the neighborhood of the boundary point are obtained through the value factor evalua...

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 and a device for extracting still image target characteristic information, which belong to the technical field of pattern recognition, and are invented for solving the problems in the prior art that a characteristic information calculation method is complex, has no versatility, and the calculation speed is slower. The method comprises searching an image target boundary point, obtaining image target zone information, respectively evaluating value factors of the image target boundary point and peripheral neighborhood picture elements, obtaining a characteristic element, and further forming characteristic information of static image targets. The device comprises a boundary point obtaining unit and a target characteristic element obtaining unit and the like. The method and the device for extracting still image target characteristic information can radically and directly obtain target characteristic information of static images, which are convenient for rapidly memorizing and identifying image targets.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a method and device for extracting feature information of static image objects. Background technique [0002] In the problem of image target recognition, feature information extraction is the most critical technology. However, there is no general theoretical guidance at present, and we can only decide which feature information to select by analyzing the specific identification objects. The extraction methods of feature information are also designed for the characteristics of selecting feature information, and have no universality. [0003] In the prior art, in addition to the image and image information of the image target, the selected feature information includes feature information based on logical thinking, which can only be obtained through image information processing, mathematical transformation, deductive reasoning, and statistical calculation. The target re...

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 Patents(China)
IPC IPC(8): G06K9/46G06K9/32
Inventor 曾培祥
Owner NEW FOUNDER HLDG DEV LLC
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
Try Eureka
PatSnap group products