Integrated approach to brightness and contrast normalization in appearance-based object detection
First Claim
1. A method for brightness and contrast normalization in appearance-based object detection, the method comprising:
- extracting a plurality of training images;
finding eigenimages corresponding to the training images;
receiving an input image;
forming a projection equation responsive to the eigenimages by adding a scaling and a shift to image intensity and simultaneously solving for intensity normalization parameters;
computing projected and normalized images;
computing an error-of-fit of the projected and normalized images;
thresholding the error-of-fit; and
determining object positions in accordance with the thresholded error-of-fit,wherein finding eigenimages comprises;
sub-sampling the training images;
forming training images of coarse resolution in accordance with the sub-sampled images;
computing eigenimages corresponding to the training images of coarse resolution;
interpolating the eigenimages for coarse resolution;
performing orthonormalization on the interpolated images by singular value decomposition; and
providing pseudo-eigenimages corresponding to the orthonormalized images for a finer resolution.
3 Assignments
0 Petitions
Accused Products
Abstract
A system and method for appearance-based object detection includes a first portion capable of brightness and contrast normalization for extracting a plurality of training images, finding eigenimages corresponding to the training images, receiving an input image, forming a projection equation responsive to the eigenimages, solving for intensity normalization parameters, computing the projected and normalized images, computing the error-of-fit of the projected and normalized images, thresholding the error-of-fit, and determining object positions in accordance with the thresholded error-of-fit; and optionally includes a second portion capable of forming eigenimages for multiresolution for sub-sampling the training images, forming training images of coarse resolution in accordance with the sub-sampled images, computing eigenimages corresponding to the training images of coarse resolution, interpolating the eigenimages for coarse resolution, performing orthonormalization on the interpolated images by singular value decomposition, and providing pseudo-eigenimages corresponding to the orthonormalized images for a finer resolution.
35 Citations
15 Claims
-
1. A method for brightness and contrast normalization in appearance-based object detection, the method comprising:
-
extracting a plurality of training images; finding eigenimages corresponding to the training images; receiving an input image; forming a projection equation responsive to the eigenimages by adding a scaling and a shift to image intensity and simultaneously solving for intensity normalization parameters; computing projected and normalized images; computing an error-of-fit of the projected and normalized images; thresholding the error-of-fit; and determining object positions in accordance with the thresholded error-of-fit, wherein finding eigenimages comprises; sub-sampling the training images; forming training images of coarse resolution in accordance with the sub-sampled images; computing eigenimages corresponding to the training images of coarse resolution; interpolating the eigenimages for coarse resolution; performing orthonormalization on the interpolated images by singular value decomposition; and providing pseudo-eigenimages corresponding to the orthonormalized images for a finer resolution. - View Dependent Claims (2, 3)
-
-
4. A method for brightness and contrast normalization in appearance-based obiect detection, the method comprising:
-
extracting a plurality of training images; finding eigenimages corresponding to the training images; receiving an input image; forming a projection equation responsive to the eigenimages by adding a scaling and a shift to image intensity and simultaneously solving for intensity normalization parameters; computing projected and normalized images; computing an error-of-fit of the projected and normalized images; thresholding the error-of-fit; and determining obiect positions in accordance with the thresholded error-of-fit, further comprising forming eigenimages for multiresolution, including; sub-sampling a plurality of training images; forming training images of coarse resolution in accordance with the sub-sampled images; computing coarse eigenimages corresponding to the training images of coarse resolution; interpolating the coarse eigenimages for a finer resolution; orthonormalizing the interpolated images; and providing pseudo-eigenimages corresponding to the orthonormalized images for a finer resolution, wherein the pseudo-eigenimages are formed with a projection equation responsive to the coarse eigenimages by adding a scaling and a shift to image intensity. - View Dependent Claims (5)
-
-
6. A system for brightness and contrast normalization in appearance-based object detection, the system comprising:
-
extraction means for extracting a plurality of training images; finding means for finding eigenimages corresponding to the training images; receiving means for receiving an input image; forming/solving means for forming a projection equation responsive to the eigenimages by adding a scaling and a shift to image intensity and simultaneously solving for intensity normalization parameters; computing means for computing projected and normalized images; fitting means for computing an error-of-fit of the projected and normalized images; thresholding means for thresholding the error-of-fit; and determining means for determining object positions in accordance with the thresholded error-of-fit, wherein said finding means comprises; sub-sampling means for sub-sampling the training images; training means for forming training images of coarse resolution in accordance with the sub-sampled images; eigenimaging means for computing eigenimages corresponding to the training images of coarse resolution; interpolating means for interpolating the eigenimages for coarse resolution; orthonormalization means for performing orthonormalization on the interpolated images by singular value decomposition; and pseudo-eigenimaging means for providing pseudo-eigenimages corresponding to the orthonormalized images for a finer resolution. - View Dependent Claims (7, 8)
-
-
9. A system for brightness and contrast normalization in appearance-based object detection, the system comprising:
-
extraction means for extracting a plurality of training images; finding means for finding eigenimages corresponding to the training images; receiving means for receiving an input image; forming/solving means for forming a projection equation responsive to the eigenimages by adding a scaling and a shift to image intensity and simultaneously solving for intensity normalization parameters; computing means for computing projected and normalized images; fitting means for computing an error-of-fit of the projected and normalized images; thresholding means for thresholding the error-of-fit; and determining means for determining object positions in accordance with the thresholded error-of-fit; means for forming eigenimages for multiresolution, including; sub-sampling means for sub-sampling a plurality of training images; training means for forming training images of coarse resolution in accordance with the sub-sampled images; eigenimaging means for computing coarse eigenimages corresponding to the training images of coarse resolution; interpolating means for interpolating the coarse eigenimages for a finer resolution; orthonormalizing means for orthonormalizing the interpolated images; and pseudo-eigenimaging means for providing pseudo-eigenimages corresponding to the orthonormalized images for a finer resolution, wherein the pseudo-eigenimages are formed with a projection equation responsive to the coarse eigenimages by adding a scaling and a shift to image intensity. - View Dependent Claims (10)
-
-
11. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for brightness and contrast normalization in appearance-based object detection, the method steps comprising:
-
extracting a plurality of training images; finding eigenimages corresponding to the training images; receiving an input image; forming a projection equation responsive to the eigenimages by adding a scaling and a shift to image intensity and simultaneously solving for intensity normalization parameters; computing projected and normalized images; computing an error-of-fit of the projected and normalized images; thresholding the error-of-fit; and determining object positions in accordance with the thresholded error-of-fit, wherein the program step of finding eigenimages comprises; sub-sampling the training images; forming training images of coarse resolution in accordance with the sub-sampled images; computing eigenimages corresponding to the training images of coarse resolution; interpolating the eigenimages for coarse resolution; performing orthonormalization on the interpolated images by singular value decomposition; and providing pseudo-eigenimages corresponding to the orthonormalized images for a finer resolution. - View Dependent Claims (12, 13)
-
-
14. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for brightness and contrast normalization in appearance-based object detection, the method steps comprising:
-
extracting a plurality of training images; finding eigenimages corresponding to the training images; receiving an input image; forming a projection equation responsive to the eigenimages by adding a scaling and a shift to image intensity and simultaneously solving for intensity normalization parameters; computing projected and normalized images; computing an error-of-fit of the projected and normalized images; thresholding the error-of-fit; and determining object positions in accordance with the thresholded error-of-fit, further comprising method steps for forming eigenimages for multiresolution, including; sub-sampling a plurality of training images; forming training images of coarse resolution in accordance with the sub-sampled images; computing coarse eigenimages corresponding to the training images of coarse resolution; interpolating the coarse eigenimages for a finer resolution; orthonormalizing the interpolated images; and providing pseudo-eigenimages corresponding to the orthonormalized images for a finer resolution, wherein the pseudo-eigenimages are formed with a projection equation responsive to the coarse eigenimages by adding a scaling and a shift to image intensity. - View Dependent Claims (15)
-
Specification