3-D Image Analysis via Jacobi Moments with GPU-Accelerated Algorithms

This research has developed a parallel algorithm to compute 3-Dimensional Jacobi moments with high efficiency and accuracy. The algorithm was implemented in CUDA C. Our developing progress was in the order of Legendre moments, Gegenbauer moments, and Jacobi moments investigated on the 2-D image. Then, we extended research from 2-D to 3-D image. To verify the algorithm’s performance, we have implemented image reconstruction from higher orders up to 500 on testing image sized at 512×512×512. The experiment was deployed on Nvidia Tesla V100, which restrained computational time within 400 milliseconds, and the PSNR value of reconstructed image reached up to 53.6382.

Classification of Mammogram Abnormalities Using Legendre Moments

In this paper, the issue of classifying mammogram abnormalities using images from an mammogram image analysis society (MIAS) database is discussed. We compare a feature extractor based on Legendre moments (LMs) with six other feature extractors. To determine the best feature extractor, the performance of each was compared in terms of classification accuracy rate and extraction time using a [Formula: see text]-nearest neighbors ([Formula: see text]-NN) classifier. This study shows that feature extraction using LMs performed best with an accuracy rate over 84% and requiring relatively little time for feature extraction, on average only 1[Formula: see text]s.

Fast Legendre Moments in Securing Digital Image

Moments are set of values used to describe the information contained in the image. In this paper the content of the image is represented with the help of fast legendre moments. Legendre moments has the advantage that these moments are calculated exactly without any loss in information while other moments like geometric moments, zernike moments etc suffer from approximation errors and geometric error when applied to digital images. Legendre moments are also more suitable for image reconstruction. Experimental results show that the proposed system is very efficient in computing moments at much faster time than the Zernike moments since fast legendre moments calculates the moments as two ID function rather as a 2D function of a digital image and the results of reconstruction in case of tampering is also shown