Proc. IS&T/SPIE Conf. on Sensors, Color, Cameras, and Systems for Digital Photography, Jan. 18-22, 2004, vol. 5301, pp. 364-373, San Jose, CA USA

Unsupervised Automation of Photographic Composition Rules in Digital Still Cameras

Serene Banerjee and Brian L. Evans

Department of Electrical and Computer Engineering, Engineering Science Building, The University of Texas at Austin, Austin, TX 78712-1084 USA -

Draft of Paper - Talk


When taking pictures, professional photographers apply photographic composition rules, e.g. rule of thirds. The rule of thirds says to place the main subject's center at one of four places: at 1/3 or 2/3 of the picture width from left edge, and 1/3 or 2/3 of the picture height from the top edge. This paper develops low-complexity unsupervised methods for digital still cameras to (1) segment the main subject and (2) realize the rule-of-thirds.

The main subject segmentation method uses the auto-focus filter, opens the shutter aperture fully, and segments the resulting image. These camera settings place the main subject in focus and blur the rest of the image by diffused light. The segmentation utilizes the difference in frequency content between the main subject and blurred background. The segmentation does not depend on prior knowledge of the indoor/outdoor setting or scene content.

The rule-of-thirds method moves the centroid of the main subject to the closest of the four rule-of-thirds locations. We first define an objective function that measures how close the main subject placement obeys the rule-of-thirds, and then reposition the main subject in order to optimize the objective function. For multiple main subjects, the proposed algorithm could be extended to use rule-of-triangles by adding an appropriate constraint.


The following questions and comments were made by those attending the presentation:
  1. Why did you use a 3x3 filter for blurring -- you could use a 5x5 or 7x7 for more blur?
  2. When you shift pixels to generate a picture, following the rule-of-thirds, wouldn't it be better to have a wide angle camera, and capture more surrounding? This way even after the pixels are shifted, the borders will still have good data.
  3. Did you perform any subjective testing to see which of the pictures generated by the algorithm were more appealing to the user?
  4. In future would you do any scene analysis to see if the main subject is moving, before introducing linear blur?
  5. One can see that the segmentation is not perfect, but I would take it for the lower complexity.
  6. I can see how segmenting the main subject would be good for constrained image transmission, one can spend more bits where the main subject is located.

COPYRIGHT NOTICE: All the documents on this server have been submitted by their authors to scholarly journals or conferences as indicated, for the purpose of non-commercial dissemination of scientific work. The manuscripts are put on-line to facilitate this purpose. These manuscripts are copyrighted by the authors or the journals in which they were published. You may copy a manuscript for scholarly, non-commercial purposes, such as research or instruction, provided that you agree to respect these copyrights.

Last Updated 06/12/04.