gbr07 shen gufg 01

Uploaded from authorPOINTLite
Views:
 
Category: Education
     
 

Presentation Description

No description available.

Comments

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, USA

Slide2: 

Motivation

Slide3: 

“Webster” Motivation

More Examples: 

More Examples Find street signs, restaurants, addresses Find indoor signs as landmarks and info tags

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,……

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-iteratively

Our 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-iteratively

Our 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-iteratively

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

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 up

Matched Vertical/Horizontal Edgelets: 

Matched Vertical/Horizontal Edgelets

Anchored 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 --- Factors

The Equations: 

The Equations

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 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 only

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 only

An example: 

An example

More examples: 

More examples

Summary / 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

Summary / 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

Summary / 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

Summary / 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

Summary / 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

Summary / 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