【摘要】 为提高单板节子图像的对比度、细节清晰度和颜色保真性，综合考虑单板活节和死节图像的特征，提出一种将自适应校正和非锐化掩模相结合的单板节子图像增强算法。在可分离颜色信息的HSV空间提取亮度分量、饱和度分量，分别进行加权分布的自适应Gamma校正和自适应非线性拉伸处理，用于改善单板节子图像对比度和保持色彩自然，最后利用非锐化掩模技术增强节子细节区域。试验结果表明，该算法能够有效地改善单板节子图像的对比度和细节清晰度，图像颜色更为自然；突出节子缺陷部位，保留了较多节子细节信息；在均方差、峰值信噪比和结构相似性指数上，比AGC-Quantile和直方图均衡化算法均有提升。更多还原

【Abstract】 In order to improve image qualities of veneer knots, including the contrast, detail sharpness,and color fidelity, an image enhancement algorithm combining adaptive correction and unsharpening mask technology was proposed. The brightness(V) component and saturation(S) component were extracted from the HSV space of separable color information. The weighted distribution adaptive gamma correction and adaptive nonlinear stretching processing were used to improve the contrast and keep the color natural. Finally, unsharpened mask technique was used to enhance the sub-detail area around knots.Experiment results showed that this algorithm could effectively improve the contrast and detail definition of the veneer images, and the image color was more natural. The defects of knots were more prominent and more details of knots were retained. Compared with AGC-Quantile and histogram equalization algorithms, these algorithms have better mean square error, peak signal to noise ratio, and structural similarity index.更多还原