Search

This paper presents an algorithm for the segmentation of Blood Vessels from x-ray angiography of coronary artery images using Matched filters and Otsu thresholding. Identifying these arteries is a difficult process because of the vessel overlapping, and superimposition with various anatomical structures such as the ribs, the spine and the heart chambers. Firstly, the 3D Fourier and 2D Wavelet transforms are first used to eliminate the background and reduce noise in the images. Afterwards, a set of matched filters was applied to enhance the coronary arteries in the images. Finally with Otsu thresholding and 8-connected neighborhood pixels the segmented vessel was obtained. [ABSTRACT FROM AUTHOR]

One of the most important stages in Character Recognition Systems is "Segmentation", because any mistake will affect to all other tasks, especially to character recognition. This operation is more complex in Persian/Arabic writing than other Latin writing like English, and there has been an ongoing research on it. Other algorithms, that has been used as base as proposed algorithm, show 85% accuracy. In this paper, a new improved method has been presented by analyzing the visual features of the Persian/Arabic language. The proposed algorithm is able to segment existing fonts up to 98.5% accuracy or even 100% on some cases. The remaining error could be refined by applying a good character recognition technique and a precise vocabulary. [ABSTRACT FROM AUTHOR]

This paper present a simple watermarking approach based on the rotation of low frequency components of image blocks. The rotation process is performed with less distortion by projection of the samples on specific lines according to message bit. To have optimal detection Maximum Likelihood criteria has been used. Thus by computing the distribution of rotated noisy samples the optimum decoder is presented and its performance is analytically investigated. The privilege of this proposed algorithm is its inherent robustness against gain attack as well as its simplicity. Experimental results confirm the validity of the analytical derivations and also high robustness against common attacks. [ABSTRACT FROM AUTHOR]