1 / 29

Pattern Recognition - Face detection using Adaboosting

Pattern Recognition - Face detection using Adaboosting. Presented by Master Course, 2 nd Semester Kim Sung Yong. Overview. Viola Jones technique overview Features Integral Images Feature Extraction Adaboost algorithms Cascade of boosted classifiers Training and Example Results.

mmanson
Download Presentation

Pattern Recognition - Face detection using Adaboosting

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Pattern Recognition - Face detection using Adaboosting Presented by Master Course, 2nd Semester Kim Sung Yong

  2. Overview • Viola Jones technique overview • Features • Integral Images • Feature Extraction • Adaboost algorithms • Cascade of boosted classifiers • Training and Example Results

  3. Viola Jones technique overview • Three major contributions/phases of the algorithm : • Feature extraction • Classification using boosting • Multi-scale detection algorithm • Feature extraction and feature evaluation. • Rectangular features are used, with a new image representation their calculation is very fast. • Classifier training and feature selection using a slight variation of a method called AdaBoost. • A combination of simple classifiers is very effective

  4. Overview • Viola Jones technique overview • Features • Integral Images • Feature Extraction • Adaboost algorithms • Cascade of boosted classifiers • Training and Example Results

  5. Features Four basic types. They are easy to calculate. The white areas are subtracted from the black ones. A special representation of the sample called the integral image makes feature extraction faster.

  6. Overview • Viola Jones technique overview • Features • Integral Images • Feature Extraction • Adaboost algorithms • Cascade of boosted classifiers • Training and Example Results

  7. Integral images Summed area tables A representation that means any rectangle’s values can be calculated in four accesses of the integral image.

  8. Fast Computation of Pixel Sums

  9. Overview • Viola Jones technique overview • Features • Integral Images • Feature Extraction • Adaboost algorithms • Cascade of boosted classifiers • Training and Example Results

  10. Feature Extraction Features are extracted from sub windows of a sample image. The base size for a sub window is 24 by 24 pixels. Each of the four feature types are scaled and shifted across all possible combinations In a 24 pixel by 24 pixel sub window there are ~160,000 possible features to be calculated.

  11. Overview • Viola Jones technique overview • Features • Integral Images • Feature Extraction • Adaboost algorithms • Cascade of boosted classifiers • Training and Example Results

  12. Adaboost algorithms

  13. Boosting Example

  14. First classifier

  15. First 2 classifiers

  16. First 3 classifiers

  17. Final Classifier learned by Boosting

  18. Recall: Perceptron Operation • Equations of “thresholded” operation: • = 1 (if w1x1 +… wd xd + wd+1 > 0) • o(x1, x2,…, xd-1, xd) • = -1 (otherwise)

  19. Perceptron with just a Single Feature • Equations of “thresholded” operation: • Equivalent to x1 > - wd+1 / w1 i.e., equivalent to comparing the feature to a threshold Learning = finding the best threshold for a single feature Can be trained by gradient descent (or direct search) • = 1 (if w1x1 + wd+1 > 0) • o(x1) • = -1 (otherwise)

  20. Final Classifier learned by Boosting

  21. How is classifier combining done?

  22. Useful Features Learned by Boosting

  23. Overview • Viola Jones technique overview • Features • Integral Images • Feature Extraction • Adaboost algorithms • Cascade of boosted classifiers • Training and Example Results

  24. A Cascade of Classifiers

  25. Cascade of Boosted Classifiers • 단계 검사 방법 • 단계 검사 방법의 개요 • 검출 시 연산 속도를 향상하기 위해 AdaBoost 분류를 단계 구조로 만들어 적용한다. • 단계 구조는 여러 개의 스테이지(stage)를 나누고 스테이지 별로 약한 분류기의 수를 다르게 하여 수행하는 방법이다. • 처음 스테이지 분류에는 영상에 포함된 대부분의 비얼굴을 제거하는 기능이 있어 단일 스테이지를 적용하는 방법보다 좋은 성능을 얻게 된다. • 단계 검출 방법의 원리는 얼굴 영상(포지티브 영상)은 그대로 유지하면서 대부분의 비얼굴 영상(네거티브 영상)을 초기 단계에서 걸러냄으로써 나머지 단계에서 좀 더 복잡한 영상에 대한분류에 집중할 수 있도록 고안한 것이다. • 단계 검사(cascade method)첫 번째 단계에서 거짓 긍정률(false positive rate)을 어느 정도 감수해야 한다. • 높은 거짓 긍정률 자체는 분류기로 사용하기에 적합하지 않지만 이후의 단계를 거침으로써 더욱 더 판별력이 좋아지게 된다.

  26. Overview • Viola Jones technique overview • Features • Integral Images • Feature Extraction • Adaboost algorithms • Cascade of boosted classifiers • Training and Example Results

  27. Training In paper, 24x24 images of faces and non faces (positive and negative examples).

  28. Sample results using the Viola-Jones Detector Notice detection at multiple scales

  29. More Detection Examples

More Related