Evolutionary computation based optimization of image Zernike moments shape feature vector

Abstract

The image shape feature can be described by the image Zernike moments. In this paper, we points out the problem that the high dimension image Zernike moments shape feature vector can describe more detail of the original image but has too many elements making trouble for the next image analysis phases. Then the low dimension image Zernike moments shape feature vector should be improved and optimized to describe more detail of the original image. So the optimization algorithm based on evolutionary computation is designed and implemented in this paper to solve this problem. The experimental results demonstrate the feasibility of the optimization algorithm.

Airplane extraction and identification by improved PCNN with wavelet transform and modified Zernike moments

“…From Table 1, it illustrates that the moments in Ref. 16 have the good rotating invariance, but their scaling invariance is not good; the moments in Ref. 17 have the good scaling invariance, but their rotating invariance is not good; while the moments in this paper have the property of both the rotation invariance and the scaling invariance.…”

“…Nowadays, they have been adapted for image processing in shape recognition schemes. [16][17][18][19][20] The orthogonal properties of the Zernike moments suit for shape recognition well because unlike geometric moments, their invariants can be computed independently to arbitrary high orders without having to re-compute low order invariants. These orthogonal properties also allow one to evaluate up to what order to calculate the Zernike moments to obtain a good descriptor for a given database.…”

“…Based on Zernike's work, Teague firstly proposed Zernike moments' definition of twodimensional function f(x,y) in 1980. 16 Let f(x,y) be an image intensity function, and the two-dimensional Zernike moment of order m with repetition n is defined as: 12…”