Fractional Fourier Transform for Digital Image Recognition

Abstract

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.