Image analysis – Learning systems
Reexamination Certificate
2005-02-22
2005-02-22
Chang, Jon (Department: 2623)
Image analysis
Learning systems
C382S190000, C382S283000
Reexamination Certificate
active
06859550
ABSTRACT:
Noise or outliers corrupt image non-contact measurement of a geometric structure or geometric entity. A weight image is created prior to fitting whose pixel value indicates certainty of image information or feature signal strength. Learning images can enhance the weight image or it can be adjusted by iteration to achieve robust fitting results.
REFERENCES:
patent: 6151403 (2000-11-01), Luo
patent: 20020106112 (2002-08-01), Chen et al.
Jolly et al. “Vehicle Segmentation and Classification Using Deformable Templates.” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 18, No. 3, Mar. 1996, pp. 293-308.*
Mirhosseini et al. “A Hierarchical and Adaptive Deformable Model for Mouth Boundary Detection.” Proc. Int. Conf. on Image Processing, vol. 2, Oct. 26, 1997, pp. 756-759.*
Park et al. “Initialization of Deformable Templates Using Weighted Gaussian Approximations.” Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, vol. 4, Jun. 5, 2000, pp. 2231-2234.
Lee Shih-Jong J.
Oh Seho
LandOfFree
Robust method for image feature estimation does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Robust method for image feature estimation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Robust method for image feature estimation will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3469581