DeviParikh WACV 2008

50 %
50 %
Information about DeviParikh WACV 2008

Published on February 27, 2008

Author: Fenwick


Slide1:  Localization and Segmentation of 2D High Capacity Color Barcodes Gavin Jancke Microsoft Research, Redmond Devi Parikh Carnegie Mellon University Motivation:  Motivation UPC Barcode QR Code Datamatrix HCCB:  HCCB Microsoft’s High Capacity Color Barcode Application:  Application Uniquely identifying commercial audiovisual works such as motion pictures, video games, broadcasts, digital video recordings and other media Goal:  Goal Locate and Segment the barcode from consumer images Overview:  Overview Design specifications of Microsoft’s HCCB Approach Localization Segmentation Progressive Strategy Results Conclusions Microsoft’s HCCB:  Microsoft’s HCCB 4 or 8 colors Triangles String of colors palette Microsoft’s HCCB:  Microsoft’s HCCB Microsoft’s HCCB:  Microsoft’s HCCB Microsoft’s HCCB:  Microsoft’s HCCB Microsoft’s HCCB:  Microsoft’s HCCB R rows S symbols per row S = (r+1)*R Aspect ratio: r Approach:  Approach Thresholding Orientation prediction Corner localization Row localization Symbol localization Color assignments Barcode localization Barcode segmentation point inside the barcode is known Localization: Thresholding:  Localization: Thresholding Identify thick white band and row separators Normalization Adaptive Localization: Orientation:  Localization: Orientation orientation orientation distance -90 90 0 summation Localization: Corners:  Localization: Corners Rough estimates whiteness mask non-texture mask combined mask Localization: Corners:  Localization: Corners Gradient based refinement Localization: Corners:  Localization: Corners Line based refinement Segmentation: Rows:  Segmentation: Rows Summation Flip? Segmentation: Symbols:  Segmentation: Symbols Local search Number of symbols per row q(S,E) = Sq(samples|S,E) Segmentation: Colors:  Segmentation: Colors Palette Observations:  Segmentation results given accurate localization Satisfactory Corner localization Unsatisfactory No one strategy works well on all images However (1) Errors of different strategies are complementary (2) Results are verifiable with decoder in the loop! Observations Progressive strategy:  Progressive strategy Hence – progressive strategy! Similar to ensemble of weak classifiers Or hypothesize-and-test Multiple strategies: Rough + gradient + line, or rough + line, or rough + gradient, or rough alone Different values of threshold during rough corner detection Total 12 Order of strategies Results:  Results Dataset of 500 images Performance metric: % barcodes successfully decoded Decoder model: Barcode successfully decoded if 80% of symbols are correctly identified Results:  Results Allows for explicit trade-off between accuracy and computational time Results:  Results Results:  Results Results:  Results Results:  Results Results:  Results Results:  Results Results:  Results Results:  Results Results:  Results Results:  Results Conclusions:  Conclusions 2D High Capacity Color Barcode (HCCB) Successful localization and segmentation of HCCB from consumer images Varying densities, aspect ratios, lighting, color balance, image quality, etc. Simple computer vision and image processing techniques Progressive strategy Acknowledgements:  Acknowledgements Microsoft Research Larry Zitnick Andy Wilson Zhengyou Zhang Carnegie Mellon University Advisor: Tsuhan Chen Slide37:  Thank you!

Add a comment

Related presentations

Related pages

Feature-Based Part Retrieval for Interactive 3D Reassembly

Interactive 3D Reassembly Devi Parikh1, ... DeviParikh_WACV_2007 Author: dparikh Created Date: 1/22/2008 6:41:34 PM ...
Read more

Devi Parikh | Virginia Tech | Papers -

Devi Parikh, Virginia Tech, Bradley Dept of Electrical and Computer Engineering, Faculty Member. Studies Computer Vision. Log In; ... 2008. WACV 2008. ...
Read more