Scribd Logo
Upload

Welcome to Scribd!

  • 76 views

    Classifier

    Uploaded by

    Ashik Mahmud
    This document discusses various techniques for object recognition in images, including: 1) Bag-of-words models and visual words with spatial location to represent images. 2) Part-based models that represent objects as combinations of parts. 3) Discriminative methods such as nearest neighbors, neural networks, support vector machines, and conditional random fields for classification. 4) Techniques including boosting, cascades of classifiers, and shared features across objects that enable efficient and multi-class object recognition.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd

    Classifier

    Uploaded by

    Ashik Mahmud
    76 views39 pages
    This document discusses various techniques for object recognition in images, including: 1) Bag-of-words models and visual words with spatial location to represent images. 2) Part-based models that represent objects as combinations of parts. 3) Discriminative methods such as nearest neighbors, neural networks, support vector machines, and conditional random fields for classification. 4) Techniques including boosting, cascades of classifiers, and shared features across objects that enable efficient and multi-class object recognition.

    Original Title

    classifier.ppt

    Copyright

    © © All Rights Reserved

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses various techniques for object recognition in images, including: 1) Bag-of-words models and visual words with spatial location to represent images. 2) Part-based models that represent objects as combinations of parts. 3) Discriminative methods such as nearest neighbors, neural networks, support vector machines, and conditional random fields for classification. 4) Techniques including boosting, cascades of classifiers, and shared features across objects that enable efficient and multi-class object recognition.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    76 views39 pages

    Classifier

    Uploaded by

    Ashik Mahmud
    This document discusses various techniques for object recognition in images, including: 1) Bag-of-words models and visual words with spatial location to represent images. 2) Part-based models that represent objects as combinations of parts. 3) Discriminative methods such as nearest neighbors, neural networks, support vector machines, and conditional random fields for classification. 4) Techniques including boosting, cascades of classifiers, and shared features across objects that enable efficient and multi-class object recognition.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    of 39

    Agenda

    Introduction
    Bag-of-words models
    Visual words with spatial location
    Part-based models
    Discriminative methods
    Segmentation and recognition
    Recognition-based image retrieval
    Datasets & Conclusions

    Classifier based methods


    Object detection and recognition is formulated as a classification problem.
    The image is partitioned into a set of overlapping windows
    and a decision is taken at each window about if it contains a target object or not.
    Background

    Where are the screens?

    Bag of image patches

    Decision
    boundary

    Computer screen

    In some feature space

    Discriminative methods
    Nearest neighbor

    Neural networks

    106 examples

    Support Vector Machines and Kernels

    Conditional Random Fields

    Nearest Neighbors
    Difficult due to high intrinsic dimensionality of images
    - lots of data needed
    - slow neighbor lookup

    106 examples

    Shakhnarovich, Viola, Darrell 2003

    Torralba, Fergus, Freeman 2008

    Multi-layer Hubel-Wiesel
    architectures
    Neural networks

    Biologically inspired

    LeCun, Bottou, Bengio, Haffner 1998


    Rowley, Baluja, Kanade 1998
    Hinton & Salakhutdinov 2006
    Ranzato, Huang, Boureau, LeCun 2007
    Riesenhuber & Poggio 1999
    Serre, Wolf, Poggio. 2005
    Mutch & Lowe 2006

    Support Vector Machines


    Face detection

    Combining Multiple Kernels

    Heisele, Serre, Poggio, 2001

    Varma & Roy 2007


    Bosch, Munoz, Zisserman 2007

    Pyramid Match Kernel

    Grauman & Darrell 2005

    Conditional Random Fields


    Kumar & Hebert 2003

    Quattoni, Collins, Darrell 2004

    More in
    Segmentation section

    Boosting
    A simple algorithm for learning robust classifiers
    Freund & Shapire, 1995
    Friedman, Hastie, Tibshhirani, 1998

    Provides efficient algorithm for sparse visual


    feature selection
    Tieu & Viola, 2000
    Viola & Jones, 2003

    Easy to implement, not requires external


    optimization tools.

    A simple object detector with Boosting


    Download
    Toolbox for manipulating dataset
    Code and dataset

    Matlab code
    Gentle boosting
    Object detector using a part based model

    Dataset with cars and computer monitors

    http://people.csail.mit.edu/torralba/iccv2005/

    Boosting
    Boosting fits the additive model

    by minimizing the exponential loss

    Training samples
    The exponential loss is a differentiable upper bound to the misclassification error.

    Weak classifiers
    The input is a set of weighted training
    samples (x,y,w)
    Regression stumps: simple but commonly
    used in object detection.
    fm(x)
    b=Ew(y [x> ])
    Four parameters:

    a=Ew(y [x< ])

    From images to features:


    A myriad of weak detectors
    We will now define a family of visual
    features that can be used as weak
    classifiers (weak detectors)

    Takes image as input and the output is binary response.


    The output is a weak detector.

    A myriad of weak detectors

    Yuille, Snow, Nitzbert, 1998


    Amit, Geman 1998
    Papageorgiou, Poggio, 2000
    Heisele, Serre, Poggio, 2001
    Agarwal, Awan, Roth, 2004
    Schneiderman, Kanade 2004
    Carmichael, Hebert 2004

    Weak detectors
    Textures of textures
    Tieu and Viola, CVPR 2000

    Every combination of three filters


    generates a different feature

    This gives thousands of features. Boosting selects a sparse subset, so computations


    on test time are very efficient. Boosting also avoids overfitting to some extend.

    Haar wavelets
    Haar filters and integral image
    Viola and Jones, ICCV 2001

    The average intensity in the


    block is computed with four
    sums independently of the
    block size.

    Haar wavelets
    Papageorgiou & Poggio (2000)

    Polynomial SVM

    Edges and chamfer distance

    Gavrila, Philomin, ICCV 1999

    Edge fragments
    Opelt, Pinz, Zisserman,
    ECCV 2006

    Weak detector = k edge


    fragments and threshold.
    Chamfer distance uses 8
    orientation planes

    Histograms of oriented gradients


    SIFT, D. Lowe, ICCV 1999

    Dalal & Trigs, 2006

    Shape context
    Belongie, Malik, Puzicha, NIPS 2000

    Weak detectors
    Part based: similar to part-based generative
    models. We create weak detectors by
    using parts and voting for the object center
    location

    Car model

    Screen model

    These features are used for the detector on the course web site.

    Weak detectors
    First we collect a set of part templates from a set of training
    objects.
    Vidal-Naquet, Ullman, Nature Neuroscience 2003

    Weak detectors
    We now define a family of weak detectors as:

    Better than chance

    Weak detectors
    We can do a better job using filtered images

    Still a weak detector


    but better than before

    Example: screen detection


    Feature
    output

    Example: screen detection


    Feature
    output

    Thresholded
    output

    Weak detector
    Produces many false alarms.

    Example: screen detection


    Feature
    output

    Thresholded
    output

    Strong classifier
    at iteration 1

    Example: screen detection


    Feature
    output

    Thresholded
    output

    Second weak detector


    Produces a different set of
    false alarms.

    Strong
    classifier

    Example: screen detection


    Feature
    output

    Thresholded
    output

    Strong
    classifier

    +
    Strong classifier
    at iteration 2

    Example: screen detection


    Thresholded
    output

    Strong
    classifier

    Feature
    output

    Strong classifier
    at iteration 10

    Example: screen detection


    Thresholded
    output

    Strong
    classifier

    Feature
    output

    Adding
    features
    Final
    classification

    Strong classifier
    at iteration 200

    Cascade of classifiers

    Fleuret and Geman 2001, Viola and Jones 2001

    100%
    Precision

    100 features
    30 features
    3 features

    0%
    Recall
    100%
    We want the complexity of the 3 features classifier with the performance of the 100
    features classifier:

    Select a threshold with high


    recall for each stage.
    We increase precision using
    the cascade

    Some goals for object recognition


    Able to detect and recognize many object
    classes
    Computationally efficient
    Able to deal with data starving situations:
    Some training samples might be harder to
    collect than others
    We want on-line learning to be fast

    Shared features
    Is learning the object class 1000 easier
    than learning the first?

    Can we transfer knowledge from one


    object to another?
    Are the shared properties interesting by
    themselves?

    Shared features
    Independent binary classifiers:
    Screen detector
    Car detector
    Face detector
    Binary classifiers that share features:
    Screen detector
    Car detector
    Face detector
    Torralba, Murphy, Freeman. CVPR 2004. PAMI 2007

    50 training samples/class
    29 object classes
    2000 entries in the dictionary
    Class-specific features

    Results averaged on 20 runs


    Error bars = 80% interval

    Shared features

    Krempp, Geman, & Amit, 2002


    Torralba, Murphy, Freeman. CVPR 2004

    Generalization as a function of
    object similarities
    12 viewpoints

    K = 2.1

    Area under ROC

    Area under ROC

    12 unrelated object classes

    Number of training samples per class

    K = 4.8

    Number of training samples per class

    Torralba, Murphy, Freeman. CVPR 2004. PAMI 2007

    Sharing patches
    Bart and Ullman, 2004
    For a new class, use only features similar to features that where good for other
    classes:

    Proposed Dog
    features

    Sharing transformations
    Miller, E., Matsakis, N., and Viola, P. (2000). Learning from one example
    through shared densities on transforms. In IEEE Computer Vision and
    Pattern Recognition.

    Transformations are shared


    and can be learnt from other tasks.

    Some references on multiclass

    Caruana 1997
    Schapire, Singer, 2000
    Thrun, Pratt 1997
    Krempp, Geman, Amit, 2002
    E.L.Miller, Matsakis, Viola, 2000
    Mahamud, Hebert, Lafferty, 2001
    Fink 2004
    LeCun, Huang, Bottou, 2004
    Holub, Welling, Perona, 2005

    You might also like