Data processing: artificial intelligence – Adaptive system
Reexamination Certificate
1999-09-23
2004-11-09
Knight, Anthony (Department: 2121)
Data processing: artificial intelligence
Adaptive system
C706S018000, C706S020000, C382S156000, C382S157000, C382S158000, C382S159000, C382S224000
Reexamination Certificate
active
06816847
ABSTRACT:
FIELD OF THE INVENTION
This invention relates generally to images, and more particularly to the aesthetic judgment of images.
BACKGROUND OF THE INVENTION
Graphics applications have become increasingly popular for computers, even for non-professional users. Graphics applications allow users to design their own images, for distribution, for example, to friends, family and co-workers. In addition, the increasing popularity of the Internet has meant that end users have even more distribution options for their work, such as posting images on web sites. The web site design process itself can be referred to as an image design process. As used herein, the term image is general, and encompasses any graphics-related work, such as web pages, created pictures, scanned-in pictures or pictures taken by digital camera, drawings, technical drawings, page layout for desktop publishing and work processing, etc. In short, the term image is inclusive of any element that includes something besides just straight text, and thus includes organization of text, which can be deemed a graphical organization of the text, etc.
A shortcoming of current graphics applications for computers, however, is that they cannot judge the end result of a user's creation. Many graphics applications, such as Visio, Microsoft® Picture-It®, and Microsoft® FrontPage®, provide wizards and templates to make the creation of images easier, and make the end result more professional looking. However, because the user is still given considerable discretion in the designing of the images, even when using wizards and templates, the user may unknowingly create something that looks unprofessional, or even garish-looking. Besides asking family, friends and co-workers for their opinions—who themselves are likely to be non-professionals—the user has few options for determining how aesthetic his or her image is.
For this and other reasons, then, there is a need for the present invention.
SUMMARY OF THE INVENTION
The invention relates to computerized aesthetic judgment of images. In one embodiment, a computer-implemented method inputs a training set of images, where each image has a corresponding set of one or more aesthetic scores. The method trains a classifier based on the training set, and outputs the classifier. An image can then be input into the classifier, such that an aesthetic score for the image is generated by the classifier and output. Furthermore, recommendations can be generated to improve the aesthetic score for the image, which are also output.
Thus, a number of sample images are surveyed by professional designers and graphic artists, among other professionals, where each image receives an aesthetic score from each professional, to make up the training set. This training set is then input into a classifier, such as a Bayesian classifier or a Support Vector Machine (SVM), which correlates the scores for the images based on features of the images, such as the presence and distribution of colors, etc. The resulting trained classifier can then be used by end users, to provide aesthetic scores for their own images. Recommendations to improve the aesthetic scores of the images, and thus the aesthetics of the images, can also be generated, based on the same features selected by the classifier, utilizing a gradient ascent or localized search approach, for example.
In this manner, embodiments of the invention provide for advantages not found within the prior art. Integrating an embodiment of the invention into graphics programs, or integrating an embodiment into a stand-alone program, allows end users to have access to professional judgment as to how “good” their created images “look.” The end users can make changes as necessary based on the resulting aesthetic scores of their images, to improve the images' scores, or rely on the recommendations made by an embodiment of the invention to improve the images' scores.
Embodiments of the invention include computer-implemented methods, computer-readable media, computers and computerized systems of varying scope. Still other embodiments, advantages and aspects of the invention will become apparent by reading the following detailed description, and by reference to the drawings.
REFERENCES:
patent: 5465321 (1995-11-01), Smyth
patent: 5559929 (1996-09-01), Wasserman
patent: 5561741 (1996-10-01), Wasserman
patent: 5659666 (1997-08-01), Thaler
patent: 5761383 (1998-06-01), Engel et al.
patent: 6018727 (2000-01-01), Thaler
patent: 6081612 (2000-06-01), Gutkowicz-Krusin et al.
patent: 6092059 (2000-07-01), Straforini et al.
patent: 6112195 (2000-08-01), Burges
patent: 6161130 (2000-12-01), Horvitz et al.
patent: 6182058 (2001-01-01), Kohavi
patent: 6192360 (2001-02-01), Dumais et al.
patent: 6278799 (2001-08-01), Hoffman
patent: 6293904 (2001-09-01), Blazey et al.
patent: 6306077 (2001-10-01), Prabhu et al.
patent: 6327581 (2001-12-01), Platt
patent: 6356884 (2002-03-01), Thaler
Machado et al., “Computing Aesthetics”, Lecture Notes in Computer Science, 1998, retrieved from the Internt, http://citeseer.ist.psu.edu/336758.html.*
Oh et al., “Image Thresholding by Indicator Kriging, IEEE Transactions on Pattern Analysis and Machine Intelligence”, 1998.*
Reich, Y., “A Model of Aesthetidc Judgement”, A Model of Aesthetic Judgement in Design in Engineering, 1993, vol. 8, Iss 2, pp. 141-153.*
Yasuda et al., “Application of Neural Network to Aesthetic Design of Bridges”, Proceedings of the 2nd International Symposium on Uncertainty Modeling and Analysis, Apr. 1993, pp. 534-541.*
Laaksonen et al., “PicSOM: Self-Organizing Maps for Content-Based Image Retrieval”, International Joint Conference on Neur Networks, vol 4, Jul. 1999, pp. 2470-2473.*
Parisi et al., “Car Plate Recognition by Neural Networks and Image Processing”, Proceedings of the IEEE International Symposium on Circuits and Systems, vol. 3, May 1998, pp. 195-198.*
Wong et al., “A Two-Level Model-based Object Recognition Technique”, 1994 International Symposium on Speech, Image Processing and Neural Networks, Apr. 1994, vol. 1, pp. 319-322.*
Alwis et al., “Searching Image Databases Containing Trademarks”, IEE Colloquium on Neural Networks in Interactive Multimedia Systems, Oct. 1998, pp. 2/1-2/5.*
Machado et al., “Generation and Evaluation of Artworks”, 1997, Retrieved from the Internet: http://www.cs.tu-berlin.de/~mki/EuroCog/ papers/Machado/machado_Ok.ps.*
Machado et al., “Model Proposal for a Constructed Artist”, Proceedings of the 1st World Multiconference on Systemics, Cybernetics and Informatics, SCI'97/ISAS'97, vol. 2, pp. 521-528, Jul. 1997.*
Machado et al., “Computing Aesthetics”, Proceedings of the 24th Brazillian Symposium on Artifical Intelligence, SBIA'98, LNAI Series, pp. 219-229, Nov. 1998.*
Cromp et al., “Data Mining of Multidemsional Remotely Sensed Images”, Proceedings of the 2nd International Conference on Information and Knowledge Management, pp. 471-481, 1993.*
Perlovsky, L.I., “Emotions, Learning and Control”, Proceedings of the 1999 IEEE International Symposium on Intelligent Control/Intelligent Systems and Semiotics, pp. 132-137, Sep. 1999.*
Watanabe et al., “Analysis and Visualization of Properties of Free-Form Surfaces”, Proceedings of the 1998 IEEE Conference on Information Visualization, pp. 174-177, Jul. 1998.*
Purchase, H.C., “The Effects of Graph Layout”, Proceedings of the 1998 Australasian Computer Human Interaction Conferenc pp. 80-86, Nov. 1998.*
Koch et al., “Coactive Aesthetics and Control Theory”, Proceedings of the 5th IEEE International Symposium on Intelligent Control, vol. 1, pp. 93-97, Sep. 1990.*
Toyama, K., “Head Parallax Tracking for Control of a Virtual Space: A Comparison of Algorithms”, 1999 IEEE International Conference on Systems, Man, and Cybernetics, vol. 6, pp. 1-6, Oct. 1999.*
Jagielski, R., An Application of Neural Networks to Emulation of Aesthetic Judgements, Proceedings of the 1st New Zealand International Two-Stream Conference on ANN and Expert-Systems, Nov. 1993, pp. 334-337.*
Yasuda et al., Aesthetic Design System of Structures Using Neural Network and
Booker Kelvin
Fischer Craig S.
Knight Anthony
Lyon & Harr L.L.P.
LandOfFree
computerized aesthetic judgment of images does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with computerized aesthetic judgment of images, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and computerized aesthetic judgment of images will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3303953