A Pattern Recognition Method Based on Ufir Moment Invariants
A moment invariant, pattern recognition technology, applied in special data processing applications, instruments, electrical and digital data processing, etc., can solve problems such as calculation errors and errors, and achieve the effect of good invariance
Active Publication Date: 2018-08-17
HARBIN ENG UNIV
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, since the two orthogonal moments are continuous in the domain of definition, there are some obvious problems in their practical application
First of all, due to the continuity of the definition domain, it is necessary to establish a coordinate mapping relationship between the image and the polynomial before application, and errors will occur during coordinate conversion
Secondly, it is necessary to perform integral operations on continuous orthogonal moments, which will also cause calculation errors
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] The present invention will be further described below in conjunction with accompanying drawing:
[0027] The concrete realization method of the present invention is as follows:
[0028] (1) The original image is transformed, and each pixel is multiplied by a transformation factor;
[0029] (2) calculate the UFIR moment function of the transformed image;
[0030] (3) The UFIR moment function of the transformed image can be expressed as a linear sum of a series of geometric moments;
[0031] (4) We replace the geometric moment in the obtained expression with the corresponding geometric moment invariant, thus obtaining the UFIR moment invariant of the original image;
[0032] (5) In the pattern recognition experiment, we selected five different objects with similar shapes as standard images, and calculated their UFIR moment invariants respectively;
[0033] (6) We process the result, calculate its |μ| and δ, and use the ratio of δ to |μ| as a measure;
[0034] (7) We a...
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
Login to View More Abstract
The invention relates to the field of digital image processing, in particular to an UFIR moment invariants based pattern recognition method. The pattern recognition method includes: transforming an original image and multiplying each pixel by a transformation factor; calculating UFIR moment function of the transformed image; formulating the calculated UFIR moment function as the form of linear sum of geometric moment; substituting the geometric moment in a formula with geometric moment invariants to acquire the UFIR moment invariants of the original image; selecting five objects identical in shape as standard images, and respectively calculating the UFIR moment invariants of the standard images; processing results and calculating absolute averages and the sum of the absolute averages after subtracting the averages from individual measured values; selecting one images as the standard image, performing translation, zoom and rotation transformation respectively, and calculating the UFIR moment invariants of the transformed image. By the method, better invariance of the UFIR moment invariants for image transformation can be achieved.
Description
technical field [0001] The invention relates to the field of digital image processing, in particular to a pattern recognition method based on UFIR moment invariants. Background technique [0002] Since Hu's moments and their invariants were discovered, moment features have been a research hotspot in the fields of pattern recognition, image analysis, edge detection and texture analysis. Compared with other features, the moment feature has the following advantages: (1) The moment feature can reflect the gray distribution characteristics of the entire image area, and can reflect the original characteristics of the target information; (2) It has nothing to do with the target position and placement direction, and is not affected by the target The influence of image acquisition conditions and environment; (3) It is easy to construct invariant features with multiple invariant characteristics. [0003] The basis of the orthogonal moment is a series of mutually orthogonal polynomial...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/50
Inventor 卞红雨张志刚张健宋子奇刘琨
Owner HARBIN ENG UNIV