For a raw picture data set in either binary or gray-scaled digital form, we can first apply a pixel-quantization method to condense the picture to a much smaller file. Then we can use a math-graphic program such as Mi...
详细信息
ISBN:
(纸本)0819439835
For a raw picture data set in either binary or gray-scaled digital form, we can first apply a pixel-quantization method to condense the picture to a much smaller file. Then we can use a math-graphic program such as Microsoft Visual Basic to compute its center of mass (CM). From this CM, we can then construct a polar coordinate with M sectors and N rings. If we apply a normalized Magnitude Fourier Transform (MFT) to these M sectors and a normalized Hankel transform (HT) to these N rings, we will obtain two numerical series truncated at P and Q terms (e.g., P=Q=16). We can then construct a P+Q (or 32) dimension ANALOG vectors. This vector may be used as the pre-processed image vectors for feeding to any neuralnetwork (including the noniterative neuralnetworks we presented in the last 8 years) for training and learning.
暂无评论