论文部分内容阅读
图像融合是获取完整足迹图像的关键,是后续足迹识别的基础。将足迹图像进行小波分解,得到低频近似图像和各级水平、垂直、对角高频细节图像,对低频图像和高频图像分别采用不同的融合规则,将融合后的各级小波系数进行小波逆变换,得到效果较好的融合图像。详细讨论不同小波滤波器、融合规则对足迹图像融合效果的影响,并对小波域融合算法与最大值法、平均法进行了比较。
Image fusion is the key to obtain complete footprint image and is the basis of subsequent footprints recognition. The footprint image is decomposed by wavelet to get the low-frequency approximation image and horizontal, vertical and diagonal high-frequency detail images at all levels. Different fusion rules are applied to the low-frequency and high-frequency images respectively. Transform, get a better fusion image. The effects of different wavelet filters and fusion rules on the image fusion of the footprints are discussed in detail. The fusion methods of the wavelet domain and the maximum and average methods are compared.