(moving or acting with great speed) (moving or acting with great speed) Nhận Dạng Đối Tượng Sử dụng thuật toán Adaptive Boosting (increase the strength or value of Sth) (increase the strength or value of Sth) Original Author Paul Viola & Michael Jones Người Trình Bày: Nguyễn Đăng Bình Outline   Giới thiệu (Introduction) Thuật toán Boosting cho học phân lớp (The Boost algorithm for classifier learning)     Hàm phân lớp yếu (Weak learner constructor)   Lựa chọn đặc tính, đặc trưng (Feature Selection) Phân lớp mạnh (The strong classifier) Khó khăn (A tremendously difficult problem) Kết (Result) Kết luận (Conclusion) What had we done?  Tiếp cận máy học cho phát nhận dạng đối tượng trực quan    Khả xử lý ảnh nhanh (extremely rapidly) Achieving high detection rates Three key contributions   Speed up the feature evaluation Speed up the feature evaluation A new image representation  Integral Image A learning algorithm( Based on AdaBoost[5]) Select a small # of visual features from a larger set Select a small # of visual features from a larger set yield an efficient classifiers yield an efficient classifiers  A combining classifiers method  cascade classifiers Discard the background regions Discard the background regions of the image of the image A demonstration on face detection  A frontal face detection system x 288 on a PentiumIII 700 MHz 384  384 x 288 on a PentiumIII 700 MHz The detector run at 15 frames per second without resorting to image differencing or skin color detection Image difference in video sequences Image difference in video sequences Working only with a single grey scale image Working only with a single grey scale image The broad practical applications for a extremely fast face detector   User Interface, Image Databases, Teleconferencing The system can be implemented on a small low power devices Compaq iPaq  frame/sec Training process for classifier  The attentional operator is trained to detect examples of a particular class - a supervised training process Face classifier is constructed In the domain of face detection In the domain of face detection < 1% false negative < 1% false negative