基于加权的可见光与红外光图像融合算法

Fusion Algorithm of Infrared Images and Visible Images Based on Weighting

红外图像所含边缘等细节偏少、可见光又容易受外部环境干扰,融合图像可以提供更全面的信息,符合人或机器的视觉特性,为图像进一步分析、识别等提供基础。提出一种比值与梯度加权的可见光与红外光图像融合算法,结合小波变换在图像分解中的特性及信号集中的特点,将小波变换应用于红外光和可见光图像融合中可以提高融合信息的理解能力。针对分解获得的低频系数主要反映图像细节信息的特点,对低频系数采用比值加权分析融合规则;针对分解获得的高频系数主要反映图像边缘信息特征的特点,对高频系数采用改进边缘检测算子梯度加权的融合规则。选取多组图像进行了不同融合规则实验对比分析,通过客观评价指标进行评价,改进的融合算法可以获得较清晰的融合图像,可以增加图像的互补信息,并能较好地提高融合图像的清晰度。

The infrared images contains less information such as edge feature, but the visible images are affected by various light change. Fusion image is to fuse a completely clear image with a set of images of the same scene and under the same imaging conditions which are with different points. The new image is reconstructed by image fusion,which provides richer visual information than the original images. The re- sult shows that retrieval results fit more closely with human perception and computer vision. In order to get a clear image that contains all relevant objects in an area, the image fusion algorithm is proposed based on wavelet transform. Among them, for the low frequency and high frequency coefficients, we present a fusion rule based on the weighted ratios and the weighted gradient with the improved edge detection operator. Different fusion rules based on wavelet transformation were analyzed. The fusion results were analyzed and compared with the objective evaluation. Compare the new fusion method with other classical fusion algo- rithm to confirm the advantages of the new method. The experimental results illustrate that the proposed algorithm is effective for retaining the detailed images. The images ratios weighting and gradient weighting fusion algorithm is proposed based on wavelet transformation. The simulation result on three groups of the images indicated that the algorithm is able to obtain fused images of higher clarity and complementary information compared with traditional methods.