Rotation Distortion Invariant Image Recognition Based on Fractional Correlation

2012 ◽  
Vol 220-223 ◽  
pp. 2899-2902
Author(s):  
Hong Xia Wang ◽  
Pan Shi Li ◽  
Zhan Rong Zhou ◽  
You Zhang Zhu
Keyword(s):  
Fourier Transform ◽  
Numerical Calculation ◽  
Fractional Order ◽  
Image Recognition ◽  
Fast Algorithm ◽  
Fractional Fourier Transform ◽  
Correlation Peak

In this paper, a fast algorithm for fractional Fourier transform was proposed based on the theory of fractional Fourier transform, the fast numerical calculation of the fractional Fourier transform and fractional correlation was realized using MATLAB language. The characteristics of rotation distortion invariant image recognition based on fractional correlation were analyzed and compared with the traditional correlation. The results show that the quality of the fractional correlation peak is obviously improved. When fractional order P = 0.7, the fractional correlator can realize rotation distortion invariant image recognition within the scope of 15°.

Fractional Fourier Transform for Digital Image Recognition

2020 ◽  
Vol 34 (10) ◽  
pp. 2054025
Author(s):  
Luis Felipe López-Ávila ◽  
Josué Álvarez-Borrego
Keyword(s):  
Fourier Transform ◽  
Image Recognition ◽  
Gaussian Noise ◽  
Fractional Fourier Transform ◽  
Correlation Energy ◽  
Classical Correlation ◽  
Correlation Peak ◽  
Output Plane ◽  
Performance Metric ◽  
Salt And Pepper

In the image recognition field, there are several techniques that allow identifying patterns in digital images, correlation being one of them. In a correlation, you have to obtain an output plane that is as clean as possible. To measure the sharpness of the correlation peak and the cleanliness of the output plane, a performance metric called Peak to Correlation Energy (PCE) is used. In this paper, the fractional correlation is applied to recognize real phytoplankton images. This fractional correlation guarantees a higher PCE compared to the conventional correlation. The results of PCE are two-orders of magnitude higher than those obtained with the conventional correlation and manage to identify 91.23% of the images, while the conventional correlation only manages to identify 87.42% of them. This methodology was tested using images in salt and pepper or Gaussian noise, and the fractional correlation output plane always is cleaner and generates a better-defined correlation peak when compared with the classical correlation.

scholarly journals Discrete Pseudo-Fractional Fourier Transform and Its Fast Algorithm

Electronics ◽  
2021 ◽  
Vol 10 (17) ◽  
pp. 2145
Author(s):  
Dorota Majorkowska-Mech ◽  
Aleksandr Cariow
Keyword(s):  
Fourier Transform ◽  
Fast Algorithm ◽  
Fourier Transforms ◽  
Fractional Fourier Transform ◽  
Composite Number ◽  
Fractional Fourier Transforms ◽  
Fractional Transform

In this article, we introduce a new discrete fractional transform for data sequences whose size is a composite number. The main kernels of the introduced transform are small-size discrete fractional Fourier transforms. Since the introduced transformation is not, in the generally known sense, a classical discrete fractional transform, we call it discrete pseudo-fractional Fourier transform. We also provide a generalization of this new transform, which depends on many fractional parameters. A fast algorithm for computing the introduced transform is developed and described.

A feasibility study on elbow erosion monitoring using active sensing approach and fractional Fourier transform

2020 ◽  
pp. 1045389X2096317
Author(s):  
Ning Li ◽  
Furui Wang ◽  
Gangbing Song
Keyword(s):  
Fourier Transform ◽  
Fractional Order ◽  
Stress Wave ◽  
Fractional Fourier Transform ◽  
Damage Index ◽  
Active Sensing ◽  
Thickness Gauge ◽  
Order Energy ◽  
Energy Peak ◽  
Elbow Erosion

Elbow erosion monitoring is of great significance to the safety of pipeline systems and maintenance personnel. This paper proposes a new elbow erosion monitoring method, which combines the PZT (lead zirconate titanate) enabled active sensing with the fractional Fourier transform (FrRT), and takes the fractional-order energy peak of the stress wave signal as the damage index. Three 90°-elbows and three 90°-elbow assemblies were used in the experimental studies. Under different erosion degrees, the mass reduction of the three separate elbows was measured by high-precision electronic scale and the residual thickness of the three elbow assemblies was detected by ultrasonic thickness gauge. Two pieces of PZT patches were respectively used to excite and receive the signals in the active sensing. FrFT was used to distinguish the linear sweep signal components of stress wave signals from the energy of other interference or noise signals, and the fractional-order energy peak was used as the damage index. The results show that there is a one-to-one relationship between mass of erosion loss and damage index. Compared with the traditional time domain signal energy method, the new method has the advantage of eliminating the saturation phenomenon. The proposed method and damage index proposed in this paper will be a promising tool for real-time monitoring of elbow erosion.

Sign in / Sign up

Export Citation Format

Share Document