Image analysis – Image enhancement or restoration
Reexamination Certificate
1999-07-30
2004-04-06
Williams, Kimberly A. (Department: 2697)
Image analysis
Image enhancement or restoration
C382S260000, C382S261000, C358S475000
Reexamination Certificate
active
06718067
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates to image descriptors and image processing. More specifically, the present invention relates to manipulating illumination effects associated with an image.
BACKGROUND
Image processing allows for the comparison of a reference image against another image or multiple images in order to determine a “match” or correlation between the respective images. Accordingly, a variety of different image matching techniques have been employed to determine such a match or correlation between images.
One such image matching technique is known as object classification. The object classification technique operates by segmenting the original image into a series of discrete objects which are then measured using a variety of shape measurement identifications, such as shape dimensions and statistics, to identify each discrete object. Accordingly, each of the discrete objects are then classified into different categories by comparing the shape measurement identifications associated with each of the discrete objects against known shape measurement identifications of known reference objects. As such, the shape measurement identifications associated with each of the discrete objects are compared against known shape measurement identifications of known reference objects in order to determine a correlation or match between the images.
Another image matching technique used for determining a match between images is a process known as match filtering. Match filtering utilizes a pixel-by-pixel or image mask comparison of an area of interest associated with the proffered image against a corresponding area of interest contained in the reference image. Accordingly, provided the area of interest associated with the proffered image matches the corresponding area of interest of the reference image, via comparison, an area or pixel match between the images is accomplished and the images are considered to match.
Yet another image matching technique utilizes a series of textual descriptors which are associated with different reference images. The textual descriptors describe the image with textual descriptions, such as shape (e.g., round), color (e.g., green), and item (e.g., ball). Accordingly, when a proffered image is received for comparison, the textual descriptor of the proffered image is compared against the textual descriptors associated with the reference image(s). As such, the textual descriptor associated with the respective images under comparison are compared to each other in order to determine the best match between the textual descriptions associated with each image, and therefore a match between the respective images.
A common problem that may occur in such image matching techniques is the “mismatching” of images, based upon different illuminations or illumination effects that act on the objects to generate different illumination effects in the images, that are being compared to each other. For instance, one common physical image may have different illumination effects acting on or associated with the physical image, thereby creating different illuminated variations or versions of the common physical image. Accordingly, the different illuminated variations or versions of the common physical image may be mistakenly interpreted as being different physical images based upon the different illumination effects acting on or associated with the common physical image. As such, even though illuminated variations or versions of the common physical image are of the same physical image, the variations or versions of the same common physical image may be interpreted as different physical images due to the different illumination or illumination effects acting on or associated with the common physical image.
It is therefore desirable to provide a technique wherein the effects of illumination effects, which act upon or are associated with the objects in images under comparison, are effectively reduced or eliminated, so as to alleviate the problem of improperly interpreting illuminated variations of a common physical image as different distinct physical images.
SUMMARY OF THE INVENTION
A method of manipulating illumination effects associated with an image. Initially, image data is filtered to provide orientation data and energy data for a base image and an illuminated base image, the illuminated base image being a illuminated variation of the base image. Next, an illumination function is generated based upon illumination difference between the filtered base image and the filtered illuminated base image, the energy data of the filtered illuminated base image being related to the energy data of the filtered base image by the illumination function. Then the energy data of the filtered base image is normalized using the primary energy data of the filtered base image, and the energy data of the filtered illuminated base image is normalized using the primary energy data of the filtered illuminated base image.
REFERENCES:
patent: 4082431 (1978-04-01), Ward, III
patent: 4649568 (1987-03-01), Kiesel et al.
patent: 5734747 (1998-03-01), Vaidyanathan
patent: 5956427 (1999-09-01), Greenspan et al.
patent: 6084227 (2000-07-01), Rhoads
patent: 6088470 (2000-07-01), Camus et al.
patent: 6256409 (2001-07-01), Wang
patent: 6445834 (2002-09-01), Rising, III
patent: 2001/0038718 (2001-11-01), Kumar et al.
William Tafel Freeman, “Steerable Filters and Local Analysis of Image Structure”, Jun. 1992, Massachussetts Institute of Technology, Media Arts and Sciences Section.*
W.T. Freeman et al. “The Design and Use of Steerable Filters”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Sep. 1991, pp 891-906, vol. 15, issue 9.*
W.T. Freeman et al., “Steerable Filters for Early Vision, Image Analysis, and Wavelet Decomposition”, International Conference on Computer Vision, 1990, pp 406-415.*
Bharath, A.A., “Steerable filters for multirate shape extraction”, Feb. 29, 2000, Time Scale and Time Frequency Analysis and Applications, Ref. No. 2000/019, pp. 17/1-17/6.*
Ramamurthi, B., Gersho, A., “Edge-oriented filtering of images with application to post-processing of vector quantized images”, Accoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP, Mar. 1984, vol. 9, pp. 573-576.
Blakely , Sokoloff, Taylor & Zafman LLP
Sony Corporation
Vida Melanie
Williams Kimberly A.
LandOfFree
Method of manipulating illumination effects associated with... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method of manipulating illumination effects associated with..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of manipulating illumination effects associated with... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3218957