Computer graphics processing and selective visual display system – Computer graphics processing – Graphic manipulation
Reexamination Certificate
1998-04-17
2002-02-26
Vo, Cliff N. (Department: 2671)
Computer graphics processing and selective visual display system
Computer graphics processing
Graphic manipulation
Reexamination Certificate
active
06351269
ABSTRACT:
BACKGROUND
One type of special effect in computer graphics is known as morphing. The morphing operation changes one picture to another by creating a smooth transitional link between the two pictures. The process preserves features associated with each image by mapping the features from a source image to corresponding features in a destination image. Although the user interface may vary in the morphing software, the internal handling of data is similar. In one version of the conventional morphing process, given two pictures, key points defining correspondences between the pictures can be identified by selecting a first point in a first picture and a corresponding point on a second picture. The process is then repeated for the remaining key points for the two pictures. The key points on the first picture are then connected together to form a fine mesh which may be small triangles or quadrilaterals. The same mesh appears on the other picture, but deformed in accordance with one or more functions to produce a “warped” or “deformed” image.
SUMMARY
A computer-implemented method for morphing among multiple images is provided. The invention uses as inputs a predetermined set of coefficients and a plurality of warping functions. Each image defined by a plurality of points in a first space and each point has a color. The method generates a derived warping function, determines an inverse of the derived warping function, warps each image to the first image, blends the colors using the predetermined set of coefficients, applies the inverse of the derived warping function to points in the first space to generate a warped image, and applies the blended color to the warped image.
Implementations of the invention include the following. Each warping function is defined by meshes. The number of images may be n, where n is greater than
2
. The predetermined set of coefficients sum up to one and further, may be functions. Change vectors may be generated for pairs of images and applied to another image by using predetermined weights. The change vectors may be used to automatically generate movies. Moreover, a new character may be generated from an existing character in a movie by applying the change vector. The invention may also be used to transport gestures and facial expressions from an image of one person to another. Further, the invention can convert black-and-white pictures to colored pictures using the change vector.
Advantages of the invention include the following. The n-image morphing allows a user to achieve precise control over the final results by appropriately selecting the n pictures and coefficients.
REFERENCES:
T.Georgiev et al., “Morphing Between Multiple Images,” S.Illinois Univ. at Cardbondale dept. of Comp. Science, Technical Report, p. 17, Apr. 17, 1997.
T.Georgiev, “Morphing Between Multiple Images: Theory and Applications,” Thesis, S.Illinois Univ. at Cardbondale Dept. of Comp. Science, p. 45, Jun. 1997.
Seungyong Lee et al., “Polymorph: Morphing Among Multiple Images,” IEEE, 60-73, 1998.
Todor Georgiev, “Movie Compression and Motion Editing by Multi-Image Morphing,” 20 pgs. 1997.
Jain et al., “Algorithms for Clustering Data,” Prentice hall, Englewood Cliffs, NJ, 24-36, 1988.
Turk et al., “Eigenfaces for Recognition,” Massachusetts Institute of Technology, Journal of Cognitive Neuroscience vol. 3,No.1, 72-86, 1991.
Devijver et al., “Pattern Recognition: a Statistical Approach,” Prentice Hall International, 301-341, 1982.
George Wolberg, “Digital Image Warping,” IEEE Computer Society, 41-65, 1990.
Klaus et al., “Robot Vision,” The MIT Electrical Engineering and Computer Science Series, 279-95, 1986.
Johnson et al., “Applied Multivariate Statistical Analysis,” University of Wisconsin-Madison, Prentice-Hall, Inc., 361-388, 1982.
Beymer et al., “Example Based Image Analysis, and Synthesis” Massachusetts Institute of Technology Artificial Intelligence Laboratory, Memo No. 1431, Paper No. 80, 21 pgs., Nov. 1993.
Seitz et al., “View Mrophing,” Department of Computer Sciences University of Wisconsin-Madison, 10 pgs., 1986.
“Motion Field & Optical Flow,” Motion Field 12, 279-295.
Wolberg, “Spatial Transformations,” Chapter 3, 41-65, 1990.
Adobe Systems Incorporated
Fish & Richardson P.C.
Vo Cliff N.
LandOfFree
Multiple image morphing does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Multiple image morphing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multiple image morphing will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2950179