图像的边缘信息和对比度是影响人体视觉的最主要因素。提出一种能够同时保持边缘特征和增强对比度的图像缩放新方法。通过边缘检测算法、边缘梯度增强以及梯度图的低通滤波算法,得到新的梯度图,再通过求解泊松方程得到重建的图像。由于对图像边缘作了特殊处理,从而避免在图像缩放过程中丢失边缘信息。该方法可以同时保持特征以及增加图像的对比度,从而更好地展现图像的细节。实验结果表明,本文方法能应用于一般图像和医学图像的缩放和增强等应用中。

Humans are sensitive to edges and the contrast of images.We propose a novel image zooming method which preserves the edges and enhances the contrast of an image synchronously. In our system, images are reconstructed by solving a Poisson equation after Canny edges detection, gradients scaling and smoothing on edges. The gradients along the image edges are scaled, which preserves the edges for image scaling. Our method not only preserves the image edges, but also enhances the image contrast which reveals more image details. This method is easy to implement, and can be applied to several areas such as image scaling and contrast enhancement.