logging in or signing up gbr07 shen gufg 01 Urania Download Post to : URL : Related Presentations : Share Add to Flag Embed Email Send to Blogs and Networks Add to Channel Uploaded from authorPOINTLite Insert YouTube videos in PowerPont slides with aS Desktop Copy embed code: (To copy code, click on the text box) Embed: URL: Thumbnail: WordPress Embed Customize Embed The presentation is successfully added In Your Favorites. Views: 101 Category: Education License: All Rights Reserved Like it (0) Dislike it (0) Added: February 04, 2008 This Presentation is Public Favorites: 0 Presentation Description No description available. Comments Posting comment... Premium member Presentation Transcript Grouping Using Factor Graph: An Approach for finding Text with a Camera Phone: Grouping Using Factor Graph: An Approach for finding Text with a Camera Phone Huiying Shen and James Coughlan Smith-Kettlewell Eye Research Institute San Francisco, USASlide2: MotivationSlide3: “Webster” MotivationMore Examples: More Examples Find street signs, restaurants, addresses Find indoor signs as landmarks and info tagsWhy a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Why a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Why a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Why a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Why a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Our Algorithm: Feature Selection and Factor Graph: Our Algorithm: Feature Selection and Factor Graph Feature Selection Finding simple edges of four orientation Build up the more complex features Graph Model Group the features into factors Build the data driven graph model Using a simplified version of graph model to solve it non-iterativelyOur Algorithm: Feature Selection and Factor Graph: Our Algorithm: Feature Selection and Factor Graph Feature Selection Finding simple edges of four orientations Build up the more complex features Graph Model Group the features into factors Build the data driven graph model Using a simplified version of graph model to solve it non-iterativelyOur Algorithm: Feature Selection and Factor Graph: Our Algorithm: Feature Selection and Factor Graph Feature Selection Finding simple edges of four orientations Build up the more complex features Graph Model Group the features into factors Build the data driven graph model Using a simplified version of graph model to solve it non-iterativelyFeature Selection: Feature Selection Machine learning approaches Filter banks Sliding windows Learn the filters statistically Problems Lots of filters, difficult to understand and improve Require huge training data set Possible over-learning Possibly learning wrong things Feature Selection: Feature Selection Machine learning approaches Filter banks Sliding windows Learn the filters statistically Problems Lots of filters, difficult to understand and improve Require huge training data set Possible over-learning Possibly learning wrong things Slide15: Feature Selection: bottom upMatched Vertical/Horizontal Edgelets: Matched Vertical/Horizontal EdgeletsAnchored Vertical Edgelets: Anchored Vertical Edgelets --- Many factors are found according to the tops and the bottoms of the edgelets A factor graph model: A factor graph model --- Variables --- FactorsThe Equations: The EquationsOur Simplifications: Our Simplifications The variables have only two states: x=0 for ground, and x=1 for figure A factor potential function g(x) has only two values: g(x) = g1 x=1 for all x’s = g0, otherwise g1 >= g0, i.e., “if you don’t have nice things to say, say something neutral”Our Simplifications: Our Simplifications The variables have only two states: x=0 for ground, and x=1 for figure A factor potential function g(x) has only two values: g(x) = g1 x=1 for all x’s = g0, otherwise g1 >= g0, i.e., “if you don’t have nice things to say, say something neutral”Our Simplifications: Our Simplifications The variables have only two states: x=0 for ground, and x=1 for figure A factor potential function g(x) has only two values: g(x) = g1 x=1 for all x’s = g0, otherwise g1 >= g0, i.e., “If you don’t have anything nice to say, don’t say anything”An Example Factor Graph: An Example Factor Graph fA(x1,x2,x5) – top of chars w/ ascender fB(x3,x4,x6,x7,x8) – top of w/o ascender fC(x3,x4,x5,x6,x7,x8) – bottoms of 1st 6 sticks fD(x4,x5,x6,x7,x8,x9) – bottoms of next 6 sticks An Example Factor Graph: An Example Factor Graph fA(x1,x2,x5) – top of chars w/ ascender fB(x3,x4,x6,x7,x8) – top of w/o ascender fC(x3,x4,x5,x6,x7,x8) – bottoms of 1st 6 sticks fD(x4,x5,x6,x7,x8,x9) – bottoms of next 6 sticks Our Non-Iterative Algorithm: Our Non-Iterative Algorithm Set mx->f(x=0) = 0 initially Shift mf->x(x) after each iteration such that mf->x(x=0) = 0 The Algorithm converges after first iteration It can be implemented using fixed point operation onlyOur Non-Iterative Algorithm: Our Non-Iterative Algorithm Set mx->f(x=0) = 0 initially Shift mf->x(x) after each iteration such that mf->x(x=0) = 0 The Algorithm converges after first iteration It can be implemented using fixed point operation onlyAn example: An exampleMore examples: More examplesSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computation You do not have the permission to view this presentation. In order to view it, please contact the author of the presentation.
gbr07 shen gufg 01 Urania Download Post to : URL : Related Presentations : Share Add to Flag Embed Email Send to Blogs and Networks Add to Channel Uploaded from authorPOINTLite Insert YouTube videos in PowerPont slides with aS Desktop Copy embed code: (To copy code, click on the text box) Embed: URL: Thumbnail: WordPress Embed Customize Embed The presentation is successfully added In Your Favorites. Views: 101 Category: Education License: All Rights Reserved Like it (0) Dislike it (0) Added: February 04, 2008 This Presentation is Public Favorites: 0 Presentation Description No description available. Comments Posting comment... Premium member Presentation Transcript Grouping Using Factor Graph: An Approach for finding Text with a Camera Phone: Grouping Using Factor Graph: An Approach for finding Text with a Camera Phone Huiying Shen and James Coughlan Smith-Kettlewell Eye Research Institute San Francisco, USASlide2: MotivationSlide3: “Webster” MotivationMore Examples: More Examples Find street signs, restaurants, addresses Find indoor signs as landmarks and info tagsWhy a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Why a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Why a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Why a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Why a Cell Phone: Why a Cell Phone Everyone has one A Smart phone is a capable computer But, it has limited resources, compared to a desktop, And, has NO float point processor A simple and efficient algorithm is needed,……Our Algorithm: Feature Selection and Factor Graph: Our Algorithm: Feature Selection and Factor Graph Feature Selection Finding simple edges of four orientation Build up the more complex features Graph Model Group the features into factors Build the data driven graph model Using a simplified version of graph model to solve it non-iterativelyOur Algorithm: Feature Selection and Factor Graph: Our Algorithm: Feature Selection and Factor Graph Feature Selection Finding simple edges of four orientations Build up the more complex features Graph Model Group the features into factors Build the data driven graph model Using a simplified version of graph model to solve it non-iterativelyOur Algorithm: Feature Selection and Factor Graph: Our Algorithm: Feature Selection and Factor Graph Feature Selection Finding simple edges of four orientations Build up the more complex features Graph Model Group the features into factors Build the data driven graph model Using a simplified version of graph model to solve it non-iterativelyFeature Selection: Feature Selection Machine learning approaches Filter banks Sliding windows Learn the filters statistically Problems Lots of filters, difficult to understand and improve Require huge training data set Possible over-learning Possibly learning wrong things Feature Selection: Feature Selection Machine learning approaches Filter banks Sliding windows Learn the filters statistically Problems Lots of filters, difficult to understand and improve Require huge training data set Possible over-learning Possibly learning wrong things Slide15: Feature Selection: bottom upMatched Vertical/Horizontal Edgelets: Matched Vertical/Horizontal EdgeletsAnchored Vertical Edgelets: Anchored Vertical Edgelets --- Many factors are found according to the tops and the bottoms of the edgelets A factor graph model: A factor graph model --- Variables --- FactorsThe Equations: The EquationsOur Simplifications: Our Simplifications The variables have only two states: x=0 for ground, and x=1 for figure A factor potential function g(x) has only two values: g(x) = g1 x=1 for all x’s = g0, otherwise g1 >= g0, i.e., “if you don’t have nice things to say, say something neutral”Our Simplifications: Our Simplifications The variables have only two states: x=0 for ground, and x=1 for figure A factor potential function g(x) has only two values: g(x) = g1 x=1 for all x’s = g0, otherwise g1 >= g0, i.e., “if you don’t have nice things to say, say something neutral”Our Simplifications: Our Simplifications The variables have only two states: x=0 for ground, and x=1 for figure A factor potential function g(x) has only two values: g(x) = g1 x=1 for all x’s = g0, otherwise g1 >= g0, i.e., “If you don’t have anything nice to say, don’t say anything”An Example Factor Graph: An Example Factor Graph fA(x1,x2,x5) – top of chars w/ ascender fB(x3,x4,x6,x7,x8) – top of w/o ascender fC(x3,x4,x5,x6,x7,x8) – bottoms of 1st 6 sticks fD(x4,x5,x6,x7,x8,x9) – bottoms of next 6 sticks An Example Factor Graph: An Example Factor Graph fA(x1,x2,x5) – top of chars w/ ascender fB(x3,x4,x6,x7,x8) – top of w/o ascender fC(x3,x4,x5,x6,x7,x8) – bottoms of 1st 6 sticks fD(x4,x5,x6,x7,x8,x9) – bottoms of next 6 sticks Our Non-Iterative Algorithm: Our Non-Iterative Algorithm Set mx->f(x=0) = 0 initially Shift mf->x(x) after each iteration such that mf->x(x=0) = 0 The Algorithm converges after first iteration It can be implemented using fixed point operation onlyOur Non-Iterative Algorithm: Our Non-Iterative Algorithm Set mx->f(x=0) = 0 initially Shift mf->x(x) after each iteration such that mf->x(x=0) = 0 The Algorithm converges after first iteration It can be implemented using fixed point operation onlyAn example: An exampleMore examples: More examplesSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computationSummary / Discussion: Summary / Discussion A simplified factor graph algorithm is developed for camera cell phones Variables take only two states Factor functions g(x) take only two values “No bad mouth”: g1 >= g0 Non-iterative No floating point computation