Image analysis – Pattern recognition – Feature extraction
Reexamination Certificate
1999-09-17
2004-03-23
Dastouri, Mehrdad (Department: 2623)
Image analysis
Pattern recognition
Feature extraction
C382S203000, C382S180000, C345S632000, C358S450000, C358S453000
Reexamination Certificate
active
06711291
ABSTRACT:
FIELD OF THE INVENTION
The invention relates generally to the field of digital image processing and digital image understanding and, more particularly, to the automatic placement of an item such as a figurative element or text within an image.
BACKGROUND OF THE INVENTION
The creation of custom picture postcards or other picture souvenir items often presents a customer with an opportunity to place a text caption, a set of thought bubbles, or a figurative element within a digital image. Currently many systems offering these services such as digital print kiosks or web sites offer a user two options, a fixed location on the image (without regard to image content) or a location chosen by the user. Often the choice of the item's size or color is similarly limited. Conversely, the choices may be essentially limitless if the system offers little or nor guidance to the user. For a great number of people, this can lead to time consuming indecision. Limiting the options of the user may speed up the process, but will frustrate the user if the options offered are not aesthetically pleasing.
U.S. Pat. No. 5,901,245, which issued May 4, 1999 to the assignee of this application, describes a method for detecting open space in an image. The method involves the creation of an activity map for determining the activity of the digital image, and then determining which pixels in the activity map are below a threshold. Open space is identified as contiguous pixels of the activity map having values below the determined threshold. This method identifies regions within the image which are suitable for the inclusion of text or figurative elements into the image. While the location of open space does assist the user in finding an appropriate location in an image for an item, the mere location of an open space region does not ineluctably lead to an aesthetically pleasing use of the space.
Consequently, a need exists to more fully automate the process of placing a desired item within an open space in a given digital image, particularly to render the item and, if necessary, its surroundings to produce an aesthetically pleasing final image.
SUMMARY OF THE INVENTION
The present invention is directed to overcoming one or more of the problems set forth above. Briefly summarized, according to one aspect of the present invention, the invention resides in a method for placing a human understandable item in a digital image including the steps of (a) digitally processing the digital image to recognize and identify an optimal location in the digital image for placing the item and (b) modifying the placement of the item in relation to human understandable image content so as to minimally obscure such human understandable image content in the digital image.
The recognition and identification of an optimal location further includes the identification of an optimal region comprising open space in the digital image and then finding an optimal location within the optimal region. The placement of the item may be done so as to minimally obscure human understandable image content in other locations of the optimal region, or in regions of the digital image adjoining the optimal region. The modified placement of the image may be based on evaluating the proportion of image pixels in the item that occlude pixels outside of either the optimal location or the optimal region. Typical items processed by this method include a caption, text or a figurative element.
Alternately, the invention may be seen to reside in a method for placing a human understandable item in a digital image so as enhance the prominence of the item in relation to human understandable content in the digital image, including the steps of (a) digitally processing the digital image to recognize and identify an optimal location in the digital image for placing the item and (b) modifying one or more attributes of the item in relation to the human understandable image content to enhance the prominence of the item in the digital image. Such attributes include the color, size or shape of the item.
The present invention has the advantage of automatically choosing a set of locations, sizes, and colors for a desired item to be placed within a given digital picture that are aesthetically pleasing, and thereby curtailing the time and effort required by the user for said task.
REFERENCES:
patent: 5267333 (1993-11-01), Aono et al.
patent: 5459819 (1995-10-01), Watkins et al.
patent: 5815645 (1998-09-01), Fredlund et al.
patent: 5825996 (1998-10-01), Davis et al.
patent: 5901245 (1999-05-01), Warnick et al.
patent: 5953076 (1999-09-01), Astle et al.
patent: 5986671 (1999-11-01), Fredlund et al.
patent: 6005972 (1999-12-01), Fredlund et al.
patent: 6069713 (2000-05-01), Kusama
patent: 6151009 (2000-11-01), Kanade et al.
patent: 6236407 (2001-05-01), Leban et al.
patent: 6282317 (2001-08-01), Luo et al.
U.S. patent application Ser. No. 09/223,860, Jiebo Luo et al., filed Aug. 28, 2001.
“Digital Image Processing” by Gonzales and Woods. Addison-Wesley, 1992, pp. 583-586.
Mehrotra Rajiv
Stubler Peter O.
Dastouri Mehrdad
Eastman Kodak Company
Woods David M.
LandOfFree
Method for automatic text placement in digital 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 Method for automatic text placement in digital images, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for automatic text placement in digital images will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3239413