the viola jones face detector n.
Skip this Video
Loading SlideShow in 5 Seconds..
The Viola/Jones Face Detector PowerPoint Presentation
Download Presentation
The Viola/Jones Face Detector

Loading in 2 Seconds...

play fullscreen
1 / 17

The Viola/Jones Face Detector - PowerPoint PPT Presentation

  • Uploaded on

The Viola/Jones Face Detector. Prepared with figures taken from “Robust real-time object detection” CRL 2001/01, February 2001. Three Measures Toward Speeded Up Detection. Integral image: a fast way to compute simple “features”

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
Download Presentation

The Viola/Jones Face Detector

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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
    Presentation Transcript
    1. The Viola/Jones Face Detector Prepared with figures taken from “Robust real-time object detection” CRL 2001/01, February 2001

    2. Three Measures Toward Speeded Up Detection • Integral image: a fast way to compute simple “features” • In Adaboost the weak learner is nothing but a feature selector. The advantage is that if there are N weak learners there are merely N features to compute. • Cascaded combination of classifiers. Most of true negatives are rejected very fast at the at the first few stages. Can keep high detection rate and low false positive rate.

    3. Image Features Rectangle filters Similar to Haar wavelets Base resolution is 24-by-24 11 scales, scaling factor of 1.25 45396 features

    4. Rectangular Features for Face Detection Forehead, eye features can be captured

    5. Fast Feature Computation: Integral Image • Integral image valueat a pixel (x, y) is the sum of the pixel values of the original image above and to the left of (x, y), inclusive. • Integral image can be computed by one pass through the image

    6. Computing Sum within a Rectangle by Integral Image • The sum of the pixels within rectangle D can be computed with four array references. • The value of the integral image at location 1 is the sum of the pixels in rectangle A. • The value at location 2 is A + B, at location 3 is A + C, and at location 4 is A + B + C + D. • The sum within D can be computed as 4 + 1 - (2 + 3).

    7. Constrained Classifier: Feature Selection • Restrict the weak learner to a single feature • A weak classifier hj(x) consists of a feature fj, a threshold j, and a parity pj indicating the direction of inequality sign: • x is a 24-by-24 sub-window of an image

    8. Boosting Algorithm

    9. Learning Result Must do better

    10. Cascading Classifiers The initial classifier eliminates a large number of negative examples with verylittle processing. Subsequent layers eliminate additional negatives but require additional computation. After several stages of processing the number of sub-windows have been reduced radically.

    11. How Cascading Can Meet Performance? For K stages of cascading with each stage having fi as the false positive rate, the overall false positive rate for the cascade is Similarly, the overall detection rate is To keep F very low and D very high, for each stage the goal is to have very high detection rate (close to 100%), but moderate false positive rate (say, 30%)

    12. Cascaded Classifier • A 1 feature classifier achieves 100% detection rate and about 50% false positive rate. • A 5 feature classifier achieves 100% detection rate and 40% false positive rate (20% cumulative) • using data from previous stage. • A 20 feature classifier achieve 100% detection rate with 10% false positive rate (2% cumulative) 50% 20% 2% IMAGE SUB-WINDOW 5 Features 20 Features FACE 1 Feature F F F NON-FACE NON-FACE NON-FACE

    13. Building A Cascaded Detector

    14. Classifier is Learned from Labeled Data • Training Data • 4916 hand labeled faces • All frontal • 10000 non faces • Faces are normalized • Scale, translation • Many variations • Across individuals • Illumination • Pose (rotation both in plane and out)

    15. Boosted Face Detection • For each round of boosting: • Evaluate each rectangle filter on each example • Sort examples by filter values • Select best threshold for each filter (min Z) • Select best filter/threshold (= Feature) • Reweight examples • Weeks to learn train • 15 frames per second to detect faces from unknown images.

    16. Performance

    17. Output of Face Detector on Test Images