Method for recognizing outline shape of digital image

A digital image and recognition method technology, which is applied in character and pattern recognition, image analysis, image data processing, etc., can solve the problems of inapplicable eigenvalues, low precision of solving short axis, strict size requirements, etc., and reduce the computational complexity , reduce operations and comparisons, and ensure accuracy

Inactive Publication Date: 2007-12-26
SUZHOU UNIV
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] When using image recognition technology to sort objects, this method can be used for wheat and grain classification and quality inspection, because the classification and quality inspection of wheat and grain focus on saturation, and only need to know the size of the geometric size, It is not necessary to judge the shape of each particle; similarly, it can also be used for sorting of screws and grain quality inspection, because screws are regular objects with strict size indicators. However, for flat particles (su

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 recognizing outline shape of digital image
  • Method for recognizing outline shape of digital image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Using a CCD digital camera, using the image acquisition system to obtain the image of the detected object, and input it into the computer, using the threshold construction method to separate the basic outline of the target object from the background, and then using the outline extraction algorithm to further refine the outline of the object to ensure its Continuous and single-pixel.

[0029] Referring to attached drawing 1, the center point O inside the image contour is approximated as the origin, and 8 points are sequentially intercepted on the image contour, respectively k 1 、k 2 、k 3 …k 8 , and the angle between any two adjacent points and the origin is 45 degrees, that is, ∠k 1 OK 2 =∠k 2 OK 3 ...=∠k 7 OK 8 = 45°;

[0030] See accompanying drawing 2, with k 1 is the starting endpoint, which is sequentially connected with each point k on the contour 2 、k 3 …k 8 connect to get k 1 k 2 、k 1 k 3 …k 1 k 8 7 line segments, obtain the length of each lin...

Embodiment 2

[0036] In this embodiment, a method for calculating and processing the major axis and the minor axis is provided for the convenience of computer software programming.

[0037] Referring to accompanying drawing 4, after inputting the digital image of the contour of the measured object obtained into the computer, the center point O inside the contour of the image is approximately obtained, and a Cartesian coordinate system is established with it as the origin, and the positions of all pixels on the contour of the image in the new coordinate system are recalculated. coordinates, and simultaneously calculate the coordinates of the pixels located on the coordinate axes of the new coordinate system and the straight lines y=x and y=-x. If no pixel point is located in one of these eight directions, you can choose any point in this direction whose coordinates conform to the equation ||y|-|x||=1 to replace, and place these 8 points in a clockwise direction Write it down as 1, 2, 3, ... ...

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

A method for identifying outline form of digital image utilizes long axis length, left-short axis length, right-short axis length, distance between left and right short axis as well as absolute value of left-right short axis length difference as five identification feature values of digital image outline form then inputs said identification feature values into computer for finalizing identification of digital image outline form. The method for obtaining said feature values is also disclosed.

Description

technical field [0001] The invention relates to a method for recognizing the outline form of a digital image, which belongs to the technical field of computer pattern recognition. Background technique [0002] Image recognition is widely used in various fields, and is increasingly used in the identification, sorting and grading of tiny objects, such as the appearance sorting of screws, resistors, and capacitors in industry; the quality inspection of wheat and grain in agriculture Wait. The application of image recognition in the field of object sorting has greatly reduced labor costs while improving the sorting efficiency exponentially and minimizing the misselection rate. However, due to processing technology reasons, there are no related reports at home and abroad on the sorting research on flat granular objects, especially objects with certain requirements on shape and outline. [0003] It is generally believed that the length of the major axis, the length of the minor ...

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): G06K9/48G06T7/60
Inventor 孙涌崔志明管淼
Owner SUZHOU 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
Try Eureka
PatSnap group products