Tasks:
- Hybrid image
- Image pyramid
- Colorizing the Russian Empire
127
1. Hybrid image
Overview
A hybrid image is the sum of a low-pass filtered version of the one image and a high-pass filtered version of a second image. There is a free parameter, which can be tuned for each image pair, which controls how much high frequency to remove from the first image and how much low frequency to leave in the second image. This is called the “cutoff frequency”.
Hybrid image
Low-pass filter
High-pass filter
Image refer to: http://cvcl.mit.edu/hybrid/OlivaTorralb_Hybrid_Siggraph06.pdf
129
2. Image pyramid
Overview
134
1. Hybrid image
Low pass filter
Ideal low pass filter
Gaussian low pass filter
D0: cutoff frequency D(u,v) = (u2 + v2)1/2
Image refer to: Digital Image Processing, 3rd Ed., Rafael C. Gonzalez and Richard E. Woods
130
1. Hybrid image
High pass filter
Ideal high pass filter
D0: cutoff frequency D(u,v) = (u2 + v2)1/2
Gaussian high pass filter
Image refer to: Digital Image Processing, 3rd Ed., Rafael C. Gonzalez and Richard E. Woods
131
1. Hybrid image
Procedure
- Multiply the input image by (-1)x+y to center the transform.
- Compute Fourier transformation of input image, i.e. F(u,v).
- Multiply F(u,v) by a filter function H(u,v).
- Compute the inverse Fourier transformation of the result in (3).
- Obtain the real part of the result in (4).
- Multiply the result in (5) by (-1)x+y.
132
2. Image pyramid
Overview
An image Pyramid is a collection of representations of an image.
Refer to: http://cs.haifa.ac.il/hagit/courses/ip/Lectures/Ip11_MultiscaleRepx4.pdf
133
2. Image pyramid
Gaussian image pyramid
The Gaussian pyramid
High resolution Low resolution
135
2. Image pyramid
Procedure
Set the finest scale layer to the image
For each layer, going from next to finest to coarsest
Obtain this layer by smoothing the next finest layer with a Gaussian, and then subsampling it.
End
136
3. Colorizing the Russian Empire
Overview
Goal: automatically produce a color image from the digitized Prokudin- Gorskii glass plate images with as few visual artifacts as possible.
The glass plate images record three exposures of every scene onto a glass plate using a red, a green, and a blue filter. In order to do this, extract the three color channels from the glass plate, then place and align one above the other so that the combination forms a single RGB color image.
Assume that a simple x,y translation model is sufficient for proper alignment. However, the full-size glass plate images are very large, the alignment procedure will need to be fast and efficient.
Refer data: http://www.cs.cmu.edu/afs/cs.cmu.edu/academic/class/15463-s10/www/proj1/www/ abarnat/images/standard/
137
3. Colorizing the Russian Empire
Procedure
Divide the original image into three images with same size.
Blue
Green
Red
Input: glass plate images
Auto align the G and R channels to the B channel.
138
Output: one color image
