可见光与红外灰度融合图像感知对比度客观评价

如何客观有效地评价融合图像质量，是融合技术发展与装备应用面临的一个关键问题.图像对比度是衡量双波段灰度融合质量的一项重要的评价指标.针对目前的图像对比度客观计算模型没有充分反映人眼视觉特性，从而影响模型计算结果与人眼视觉感受的一致性的问题.在各向同性局部对比度计算模型基础上，引入人眼视觉的亮度掩盖特性，提出图像感知对比度客观评价模型.使用模拟灰度图像以及人眼主观评价实验得到的15组不同真实场景融合图像的对比度评价数据来验证客观计算模型.结果表明，相比于4种经典的对比度客观评价模型，建立的图像感知对比度模型评价结果更符合人眼视觉感受，可以有效实现双波段灰度融合图像感知对比度的客观评价. 

Perceptual Contrast Metric for Visible and Infrared Gray Fusion Images

To evaluate the fusion image quality scientifically for fusion technology research and equipment applications, image contrast was taken as an important quality metric of dual-band gray fusion images. To solve the problem in the existing contrast metrics, unconsidering human visual system and affecting coherence between the predictions and the human perceptions, an objective perceptual contrast metric was proposed based on isotropic local contrast model as well as the introduction of the human luminance masking effect. The simulated gray images and the observer evaluation scores for 15 groups of real scene gray fusion images were used to test the proposed model. Experimental results show that the proposed perceptual contrast metric is more closely matched to the human vision perception than existing methods and can evaluate the dual-band gray fusion image perceptual contrast effectively.