Proceedings of SPIE - the International Society for Optical Engineering
We used the discrete wavelet transform to approximate an image at a lower resolution in preparation for object recognition using correlation techniques. We cross- correlated the low-resolution image with a similarly processed image containing an object of interest. Then, we synthesized the cross-correlation result to the resolution of original image. Using this approach, we avoided cross- correlating an image multiple times and passing information between levels of an image representation such as an image pyramid. We satisfactorily identified objects at 1/4 resolution using the wavelet representation and binary phase-only filters. We chose wavelets based on their impulse response and found that different wavelet filters gave significantly different autocorrelation peak, and SNR values.
Kozaitis, S. P. (1996). Multiresolution wavelet processing for binary phase-only filters. Paper presented at the Proceedings of SPIE - the International Society for Optical Engineering, , 2749 165-174.