A Hand-Held

1
A Hand-Held Scanner forLarge-Format Images
Steps Towards

• COMP 256
• Adrian Ilie

2
Previous Work Panoramas

• Feature extracting use SIFT, since they are
  scale-invariant and partially invariant to affine
  illumination changes - done
• Feature matching approximate nearest neighbor -
  done
• Image matching probabilistic model using RANSAC
  inliers/outliers - N/A
• Bundle adjustment add images one by one and
  iterate using Levenberg-Marquardt - N/A
• Blending multi-band - not done

3
Extracting the Features

• Use SIFT features
• Location peaks in DoG pyramids
• Descriptors gradient orientation histograms

4
Matching Features

• Look for closest 2 descriptors in a k-d tree
  (logarithmic speed)
• If distance(descriptor, 1st closest) lt
  0.36distance(descriptor, 2nd closest),
  descriptor is a good match

5
Computing the Homography

• MLESAC

6
Warping the Images

• Use bilinear interpolation

7
Algorithm

• Take an overview image
• Extract its features and build a k-d tree
• Take N detail images
• For each image i
• Extract the features
• Match the features against the ones in the k-d
  tree
• Use MLESAC to compute the homography
• Warp the image
• Blend the image into the current estimate
• Update the k-d tree

8
Blending the Warped Images

• Detail image has higher resolution!
• Resample the current estimate so that the area
  corresponding to the warped image is equal to the
  area of the unwarped image
• Can blend using some weights, or just use the
  detail image pixel (since it is of higher quality)

9
Results
10
Scanning My Favorite Poster )
11
Scanning My Favorite Poster )
12
Scanning My Favorite Poster )
13
Scanning My Favorite Poster )
14
Issues and Future Work

• Issues
• Radial distortion in the overview image
• Numerical instability of the homography
  computation
• Illumination changes across images
• Future work
• Super-resolution would be nice to have
• It would be nice to have a nice viewer that would
  take images and homographies as input, then blend
  and render them at the appropriate level of
  detail, depending on the zoom level