Flattening curved documents in images
read more
Citations
Triggering applications based on a captured text in a mixed media environment
System And Methods For Creation And Use Of A Mixed Media Environment
Visibly-perceptible hot spots in documents
Geometric Rectification of Camera-Captured Document Images
Dynamic presentation of targeted information in a mixed media reality recognition system
References
Evaluation of binarization methods for document images
Metric rectification for perspective images of planes
Global and local document degradation models
Image restoration of arbitrarily warped documents
Structure of Applicable Surfaces from Single Views
Related Papers (5)
Frequently Asked Questions (16)
Q2. What are the future works in "Flattening curved documents in images" ?
Subsequent experiments are being conducted to test the system ’ s performance on large scale data, and the results will be reported in a future publication.
Q3. What is the method used to extract texture flow from textual content?
The authors use an edge detector to find pixels with strong gradient, and apply an open operator to expand those pixels into textual area.
Q4. What is the first part of their work on camera-captured document processing?
The restoration of a frontal planar view of a warped document from a single picture is the first part of their planed work on camera-captured document processing.
Q5. What is the measure of continuity in the unfolded plane?
In the unfolded plane, the authors expect the text lines to be continuous, parallel, straight, and orthogonal to the vertical character stroke direction.
Q6. Why have digital cameras proliferated in recent years?
Digital cameras have proliferated rapidly in recent years due to their small size, ease of use, fast response, rich set of features, and dropping price.
Q7. Why are synthetic images better than real images?
The reason that results obtained from synthetic images are better than from real images is because synthetic images have better quality in terms of focus, noise and contrast.
Q8. What is the common convergence point of the major texture flow field EM?
The common convergence point of the major texture flow field EM is the horizontal vanishing point of the plane, while Em gives the vertical vanishing point.
Q9. What is the way to measure the smoothness of the planar strips?
The group of strips {Pi}n+1i=1 is globally smooth, that is, the change between the normals of two adjacent planar strips is not abrupt.
Q10. What is the way to describe a developable surface?
It is well known in elementary differential geometry that given sufficient differentiability a developable surface is either a plane, a cylinder, a cone, the collection of the tangents of a curve in space, or a composition of these types.
Q11. What is the score of the candidate l(, x, y)?
The score of the candidate l(θ, x, y) is s(θ) = ∑ni=2 d(Ei−1, Ei) n(1)where d(Ei−1, Ei) measures the difference between two sub-fields, which in their implementation is the sum of squared differences2.
Q12. How do the authors extract texture flow fields from the textual area in the projected image?
More specifically, the authors extract two texture flow fields from the textual area in the projected image, which represent the local orientations of projected text lines and vertical character strokes respectively.
Q13. Why do the authors need to use small blocks of texture flow field to detect rulings?
due to the errors in estimated EM and Em, the authors have found that texture flow at individual pixels has too much noise for this direct method to work well.
Q14. What is the restriction on the pose of the page cylinder?
Apart from the cylinder shape assumption, they also have a restriction on the pose that requires the image plane to be parallel to the generatrix of the page cylinder.
Q15. What is the procedure for calculating the major texture flow directions?
the authors remove the major texture flow directions from the local skew candidates, reset confidences for the remaining candidates, and apply the relaxation again.
Q16. What is the way to recover the 2D plane of the page?
One way of dealing with these 3D factors is to use special equipments such as structured light to measure the 3D range data of the document, and recover the 2D plane of the page [1, 12].