原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
normalized to be zero mean and unit norm) and the local image patch, p, centered at that location and with the same size as the kernel, normalized to be unit norm. This can be implemented with the following steps: First, we normalize the kernel h. The normalized kernel is the result of making the kernel h zero mean and unit norm. Then, the normalized cross-correlation
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c015b.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8