1 / 11

Automated Rule of Thirds Compliancy

Automated Rule of Thirds Compliancy. Sam Olver Sucheth Suresh. Rule of Thirds Overview. The “Rule of Thirds” grid divides a photograph horizontally and vertically into thirds A viewer’s eyes are naturally drawn to the four intersections created by the grid

lenora
Download Presentation

Automated Rule of Thirds Compliancy

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Automated Rule of Thirds Compliancy Sam Olver Sucheth Suresh

  2. Rule of Thirds Overview • The “Rule of Thirds” grid divides a photograph horizontally and vertically into thirds • A viewer’s eyes are naturally drawn to the four intersections created by the grid • Aligning the subject of the photo to one of these intersections results in a more balanced looking image http://upload.wikimedia.org/wikipedia/commons/c/ce/Rivertree_thirds_md.gif

  3. Correcting Images to Follow the Rule of Thirds • Simplest method: Cropping • Results in loss of photo elements • Our method: Seam Carving • Remove seams on one side of a feature point (vertically and horizontally) to shift it to a rule of thirds intersection

  4. Our Goal • Input a photograph containing a single face • Find locations of the subject’s eyes (or face center if eyes are undetectable) • Determine the minimum distance between a feature point and a rule of thirds intersection • Run the seam-carving algorithm to shift the feature point to the intersection

  5. Implementation MATLAB Computer Vision System Toolbox Seam Carving for Content-Aware Image Resizing by Shai Avidan and Ariel Shamir

  6. Good Results Input Image Output Image

  7. More Good Results Input Image Output Image

  8. Not So Good Results Input Image Output Image

  9. More Advanced Applications • Automated profile picture correction • Manual image cropping, then automatic readjustment to follow the rule of thirds

  10. Limitations • Unreliability in detecting feature points (eyes, face) • Large amounts of seam carving distorts the image

  11. Summary • The rule of thirds is one of the core fundamentals that every photographer tries to follow. • This is an application that helps photographers adhere to this rule. • It has the potential to improve the quality of millions of images that are being uploaded on the web. Feel free to visit the project website: http://ruleofthirdsproject.wordpress.com

More Related