Image analysis – Pattern recognition – Template matching
Reexamination Certificate
2000-05-22
2004-08-31
Mehta, Bhavesh M. (Department: 2625)
Image analysis
Pattern recognition
Template matching
C382S119000, C382S225000, C705S014270, C707S793000
Reexamination Certificate
active
06785421
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates to analyzing one or more images of a user to determine the likelihood of user interest in materials that can be sent to the user.
BACKGROUND OF THE INVENTION
Photographic imaging service applications have been extended to include digital imaging technology. For Internet-based photographic service applications a consumer is provided a means for displaying his/her digital images with the digital images residing on a remote computer. Typical scenarios for these Internet-based digital imaging applications includes the viewing thumbnail versions of a collection of digital images, selection of a particular digital image for viewing,,enhancement, and/or printing. While there exist many different methods for an Internet-based photographic service provider to receive payment for the service rendered, many have chosen to display advertisement messages on the consumer's display screen and collect payment not from the consumer but from an advertisement client. At present, it is possible for the photographic service provider to perform directed advertisement if prior knowledge of the consumer in the form of a consumer profile is available. However, if no prior knowledge of the consumer is available directed advertising is not possible. Furthermore, the consumer profile may not be up-to-date. Moreover, the profile may not account for some facets of a consumer's buying habits. If an employee of the photographic service provider were to view the consumer's photographs, the employee could make intelligent decisions as to which advertisement client would most likely desire directed advertisement to the particular consumer. Aside from issues of privacy of consumer photographs, the process of humans observing photographs and making directed advertising decisions is too costly for consideration. Research has shown that unrelated directed advertisements are often considered nuisance by the consumer while directed advertisement which relate to the interests of the consumer are considered desirable. Digital imaging algorithms have for a long while been devised to analyze the content of digital images. In particular, the methods disclosed by Cullen et al. in U.S. Pat. No. 5,933,823, Ravela et al. in U.S. Pat. No. 5,987,456, and De Bonet et al. in U.S. Pat. No. 5,819,288 analyze digital images. In these digital imaging applications a database of digital images is maintained. For each digital image in the database a set of image features, expressed in mathematical form, are calculated. A query digital image is selected, usually initiated from the user of the digital imaging application, and compared to the digital images in the database. The same set of image features is calculated for the query digital image. A comparison between the calculated image features for the query digital image and the database digital images is performed and yields an image similarity value for each of the database digital images as a measure of overall similarity. The image similarity values are analyzed and the digital images with the highest image similarity values are displayed for the user.
While these digital image query applications are capable of analyzing digital images, none of the above mentioned disclosed methods relate the content of a set of consumer digital images to the likelihood of an advertisement client's desire to direct advertisement material to that particular consumer.
SUMMARY OF THE INVENTION
It is an object of the present invention to provide a digital imaging algorithm which can make intelligent directed advertising decisions by analyzing the image content of consumer digital image.
It is another object of the present invention to make use of a content of a user's image(s) to determine the likelihood that materials would be of interest to the user. Such materials can include products or services promotional materials.
This object is achieved by a method of analyzing one or more images of a user to determine the likelihood of user interest in materials that can be sent for display to the user, comprising:
a) selecting one or more images by a user;
b) automatically analyzing the one or more user images to determine the likelihood that materials in a set will be of interest to the user; and
c) selecting one or more items of materials based on their likelihood of interest to the user.
Advantages
It is an advantage of the present invention that it provides an advertiser or other purveyor of information with the opportunity to automatically make intelligent directed advertising decisions by analyzing the image content of consumer digital image.
It is another advantage of the present invention that by making use of a content of a user's image(s), the likelihood can efficiently and effectively be determined that materials would be of interest to the user. It is a feature of the invention that such materials can include products or service promotional materials.
REFERENCES:
patent: 5579471 (1996-11-01), Barber et al.
patent: 5696964 (1997-12-01), Cox et al.
patent: 5819288 (1998-10-01), De Bonet
patent: 5832131 (1998-11-01), Choo et al.
patent: 5933823 (1999-08-01), Cullen et al.
patent: 5963670 (1999-10-01), Lipson et al.
patent: 5987456 (1999-11-01), Ravela et al.
patent: 6035055 (2000-03-01), Wang et al.
patent: 6104835 (2000-08-01), Han
patent: 6128663 (2000-10-01), Thomas
patent: 6154771 (2000-11-01), Rangan et al.
patent: 6285788 (2001-09-01), Sezan et al.
patent: 6295061 (2001-09-01), Park et al.
patent: 6295526 (2001-09-01), Kreiner et al.
patent: 6379251 (2002-04-01), Auxier et al.
patent: 6389417 (2002-05-01), Shin et al.
patent: 6487538 (2002-11-01), Gupta et al.
patent: 6496857 (2002-12-01), Dustin et al.
patent: 6513052 (2003-01-01), Binder
patent: 6519584 (2003-02-01), Tognazzini et al.
patent: 6539375 (2003-03-01), Kawasaki
M. J. Swain and D. H. Ballard in “Color Indexing, Intl. Journal of Computer Vision”, vol. 7, No. 1, 1991, pp. 11-32.
G. Pass et al. in “Comparing Images Using Color Coherence Vectors”, Proceedings ACM Multimedia Conf., 1996.
Gindele Edward B.
Mehrotra Rajiv
Zhu Wei
Desire Gregory
Eastman Kodak Company
Mehta Bhavesh M.
Owens Raymond L.
LandOfFree
Analyzing images to determine if one or more sets of... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Analyzing images to determine if one or more sets of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Analyzing images to determine if one or more sets of... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3358018