4 pattern recognition

E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung 4. Pattern 4. Pattern Recognition Recognition E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung ▷ ▷ Introduction to Pattern Recognition System Introduction to Pattern Recognition System ▷ ▷ Feature Extraction Feature Extraction 효율화 효율화 : : Haar Haar - - like feature like feature 와 와 Integral Image Integral Image ▷ ▷ Dimension Reduction: PCA Dimension Reduction: PCA ▷ ▷ Bayesian Decision Theory Bayesian Decision Theory ▷ ▷ Bayesian Discriminant Function for Normal Density Bayesian Discriminant Function for Normal Density ▷ ▷ Linear Discriminant Analysis Linear Discriminant Analysis ▷ ▷ Linear Discriminant Functions Linear Discriminant Functions ▷ ▷ Support Vector Machine Support Vector Machine ▷ ▷ k Nearest Neighbor k Nearest Neighbor ▷ ▷ Statistical Clustering Statistical Clustering E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Introduction Introduction E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Machine Perception [2] Machine Perception [2] • Build a machine that can recognize patterns: – Speech recognition – Fingerprint identification – OCR (Optical Character Recognition) – DNA sequence identification E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Components of Pattern Classification System [6] Components of Pattern Classification System [6] E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Types of Prediction Problems [6] Types of Prediction Problems [6] E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Feature and Pattern [6] Feature and Pattern [6] E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Feature and Pattern [6] Feature and Pattern [6] E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Classifier [6] Classifier [6] E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Pattern Recognition Approaches [6] Pattern Recognition Approaches [6] [...]... Learning and Adaptation [2] • Supervised Learning: a teacher provides a category label or cost for each pattern in a training set, and seeks to reduce the sum of the costs for these patterns • Unsupervised Learning: there is no explicit teacher, and the system forms clusters or “natural grouping” of the input patterns • Reinforcement Learning: no desired category signal is given; instead, the only teaching.. .Pattern Recognition Approaches [6] E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Machine Perception [2] (Example) “Sorting incoming Fish on a conveyor according to species using optical sensing”... which have been used by Papageorgiou et al (1998) Three kinds of features: two-rectangle feature, three-rectangle feature, and four-rectangle feature Given that the base resolution of the detector is 24x 24, the exhaustive set of rectangle feature is quite large, 160,000 E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Haar-like Feature: Integral Image [7] Rectangle features can be computed . hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung 4. Pattern 4. Pattern Recognition Recognition E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung ▷ ▷ Introduction to Pattern Recognition System Introduction to Pattern Recognition. hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Pattern Recognition Approaches [6] Pattern Recognition Approaches [6] E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Pattern Recognition Approaches [6] Pattern Recognition. hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Feature and Pattern [6] Feature and Pattern [6] E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Feature and Pattern [6] Feature and Pattern [6] E-mail: hogijung@hanyang.ac.kr http://web.yonsei.ac.kr/hgjung Classifier