1Recognizing and Learning Object CategoriesBased on work and slides by R. Fergus, P. Perona, A. Zisserman, A. Efros, J. Ponce, S. Lazebnik, C. Schmid, F. DiMaio, and othersTraditional Problem: Single Object Recognition2Most Objects Exhibit Considerable Intra-Class VariabilityTask: Recognition of object categoriesSome object categoriesLearn from just examplesDifficulties:f Size variationf Background clutterf Occlusionf Intra-class variationf Viewpoint variationf Illumination variation3ChairsRelated by function, not formApproach 1: Discriminative MethodsObject detection and recognition is formulated as a classification problemBag of image patchesDecision boundary… and a decision is taken at each window about if it contains a target object or notComputer screenBackgroundIn some feature spaceWhere are the screens?The image is partitioned into a set of overlapping windows4HRCT Lung ImageDilated bronchusTraining ExamplesBronchiectasis(positive examples)Non-Bronchiectasis(negative examples)24 × 24 images5§ Formulation: binary classificationFormulation+1-1x1x2x3xN……xN+1xN+2xN+M-1 -1? ? ?…Training data: each image patch is labeledas containing the object or notTest dataFeatures x =Labelsy =Where belongs to some family of functions• Classification function• Minimize misclassification error(Not that simple: we need some guarantees that there will be generalization)Discriminative Methods106examplesNearest NeighborShakhnarovich, Viola, Darrell 2003Berg, Berg, Malik 2005…Neural NetworksLeCun, Bottou, Bengio, Haffner 1998Rowley, Baluja, Kanade 1998…Support Vector Machines and KernelsConditional Random FieldsMcCallum, Freitag, Pereira 2000Kumar, Hebert 2003…Guyon, VapnikHeisele, Serre, Poggio, 2001…6Object categorization: Object categorization: the statistical viewpointthe statistical viewpoint)|( imagezebrap)( ezebra|imagnopvs.§ Bayes’s rule:)()()|()|()|()|(zebranopzebrapzebranoimagepzebraimagepimagezebranopimagezebrap⋅=posterior ratiolikelihood ratio prior ratioObject categorization: Object categorization: the statistical viewpointthe statistical viewpoint)()()|()|()|()|(zebranopzebrapzebranoimagepzebraimagepimagezebranopimagezebrap⋅=posterior ratiolikelihood ratio prior ratio§ Discriminative methods model the posterior§ Generative methods model the likelihood and prior7Discriminative§ Direct modeling of ZebraNon-zebraDecisionboundary)|()|(imagezebranopimagezebrap§ Model and Generative)|( zebraimagep) |( zebranoimagepMiddle LowHighMiddleLow )|( zebranoimagep)|( zebraimagep8Three main issuesThree main issues§ Representation§ How to represent an object category§ Learning§ How to form the classifier, given training data§ Recognition§ How the classifier is to be used on novel dataConstructing models of image contentBasic components: local features and spatial relationsTextures Objects Scenes9Constructing models of image contentBasic components: local features and spatial relationsTextures Objects ScenesLocal modelConstructing models of image contentBasic components: local features and spatial relationsTextures Objects ScenesLocal model10Constructing models of image contentBasic components: local features and spatial relationsTextures Objects ScenesLocal modelSemi-local modelConstructing models of image contentBasic components: local features and spatial relationsTextures Objects ScenesLocal modelSemi-local model11Constructing models of image contentBasic components: local features and spatial relationsTexturesLocal modelObjectsSemi-local modelScenesGlobal model(usually appearance)Approach 2: Generative Methods using Bag of Words Models§ An image is represented by a collection of “visual words” and their corresponding counts given a universal dictionary§ Object categories are modeled by the distributions of these visual words§ Although “bag of words” models can use both generative and discriminative approaches, here we will focus on generative models12ObjectObjectBag of ‘words’Bag of ‘words’Analogy to documentsAnalogy to documentsOf all the sensory impressions proceeding to the brain, the visual experiences are the dominant ones. Our perception of the world around us is based essentially on the messages that reach the brain from our eyes. For a long time it was thought that the retinal image was transmitted point by point to visual centers in the brain; the cerebral cortex was a movie screen, so to speak, upon which the image in the eye was projected. Through the discoveries of Hubel and Wiesel we now know that behind the origin of the visual perception in the brain there is a considerably more complicated course of events. By following the visual impulses along their path to the various cell layers of the optical cortex, Hubel and Wiesel have been able to demonstrate that the message about the image falling on the retina undergoes a step-wise analysis in a system of nerve cells stored in columns. In this system each cell has its specific function and is responsible for a specific detail in the pattern of the retinal image.sensory, brain, visual, perception, retinal, cerebral cortex,eye, cell, optical nerve, imageHubel, WieselChina is forecasting a trade surplus of $90bn (£51bn) to $100bn this year, a threefold increase on 2004's $32bn. The Commerce Ministry said the surplus would be created by a predicted 30% jump in exports to $750bn, compared with a 18% rise in imports to $660bn. The figures are likely to further annoy the US, which has long argued that China's exports are unfairly helped by a deliberately undervalued yuan. Beijing agrees the surplus is too high, but says the yuan is only one factor. Bank of China governor Zhou Xiaochuan said the country also needed to do more to boost domestic demand so more goods stayed within the country. China increased the value of the yuan against the dollar by 2.1% in July and permitted it to trade within a narrow band, but the US wants the yuan to be allowed to trade freely. However, Beijing has made it clear that it will take its time and tread carefully before allowing the yuan to rise further in value.China, trade, surplus, commerce, exports, imports, US, yuan, bank, domestic, foreign, increase, trade, value13categorycategorydecisiondecisionlearninglearningfeature detection& representationcodewords dictionarycodewords dictionaryimage representationcategory modelscategory models(and/or) classifiers(and/or) classifiersrecognitionrecognition141. Feature