In this paper we present a statistical framework for modeling the appearance of objects. Our work is motivated by the pictorial structure models introduced by Fischler and Elschlager. The basic idea is to model an object by a collection of parts arranged in a deformable configuration. The appearance of each part is modeled separately, and the deformable configuration is represented by spring-like connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. We use these models to address the problem of detecting an object in an image as well as the problem of learning an object model from training examples, and present efficient algorithms for both these problems. We demonstrate the techniques by learning models that represent faces and human bodies and using the resulting models to locate the corresponding objects in novel images.

Abstract. We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for the purpose of visual object recognition. We focus on a particular type of model where objects are represented as flexible constellations of rigid parts (features). The variability within a class is represented by a joint probability density function (pdf) on the shape of the constellation and the output of part detectors. In a first stage, the method automatically identifies distinctive parts in the training set by applying a clustering algorithm to patterns selected by an interest operator. It then learns the statistical shape model using expectation maximization. The method achieves very good classification results on human faces and rear views of cars. 1 Introduction and Related Work We are interested in the problem of recognizing members of object classes, where we define an object class as a collection of objects which share characteristic features or parts that are visually similar and occur in similar spatial configurations. When building models for object classes of this type, one is faced with three problems (see Fig. 1).

Learning visual models of object categories notoriously requires hundreds or thousands of training examples. We show that it is possible to learn much information about a category from just one, or a handful, of images. The key insight is that, rather than learning from scratch, one can take advantage of knowledge coming from previously learned categories, no matter how different these categories might be. We explore a Bayesian implementation of this idea. Object categories are represented by probabilistic models. Prior knowledge is represented as a probability density function on the parameters of these models. The posterior model for an object category is obtained by updating the prior in the light of one or more observations. We test a simple implementation of our algorithm on a database of 101 diverse object categories. We compare category models learned by an implementation of our Bayesian approach to models learned from by Maximum Likelihood (ML) and Maximum A Posteriori (MAP) methods. We find that on a database of more than 100 categories, the Bayesian approach produces informative models when the number of training examples is too small for other methods to operate successfully.

. Many object classes, including human faces, can be modeled as a set of characteristic parts arranged in a variable spatial configuration. We introduce a simplified model of a deformable object class and derive the optimal detector for this model. However, the optimal detector is not realizable except under special circumstances (independent part positions). A cousin of the optimal detector is developed which uses "soft" part detectors with a probabilistic description of the spatial arrangement of the parts. Spatial arrangements are modeled probabilistically using shape statistics to achieve invariance to translation, rotation, and scaling. Improved recognition performance over methods based on "hard" part detectors is demonstrated for the problem of face detection in cluttered scenes. 1 Introduction Visual recognition of objects (chairs, sneakers, faces, cups, cars) is one of the most challenging problems in computer vision and artificial intelligence. Historically, there has been a...

We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Our models represent objects as probabilistic constellations of rigid parts (features). The variability within a class is represented by a joint probability density function on the shape of the constellation and the appearance of the parts. Our method automatically identifies distinctive features in the training set. The set of model parameters is then learned using expectation maximization (see the companion paper [11] for details). When trained on different, unlabeled and unsegmented views of a class of objects, each component of the mixture model can adapt to represent a subset of the views. Similarly, different component models can also "specialize" on sub-classes of an object class. Experiments on images of human heads, leaves from different species of trees, and motor-cars demonstrate that the method works...

We present a class of statistical models for part-based object recognition that are explicitly parameterized according to the degree of spatial structure they can represent. These models provide a way of relating different spatial priors that have been used for recognizing generic classes of objects, including joint Gaussian models and tree-structured models. By providing explicit control over the degree of spatial structure, our models make it possible to study the extent to which additional spatial constraints among parts are actually helpful in detection and localization, and to consider the tradeoff in representational power and computational cost. We consider these questions for object classes that have substantial geometric structure, such as airplanes, faces and motorbikes, using datasets employed by other researchers to facilitate evaluation. We find that for these classes of objects, a relatively small amount of spatial structure in the model can provide statistically indistinguishable recognition performance from more powerful models, and at a substantially lower computational cost. 1.

The problem of efficiently and accurately locating patterns of interest in massive time series data sets is an important and non-trivial problem in a wide variety of applications, including diagnosis and monitoring of complex systems, biomedical data analysis, and exploratory data analysis in scientific and business time series. In this paper a probabilistic approach is taken to this problem. Using piecewise linear segmentations as the underlying representation, local features (such as peaks, troughs, and plateaus) are defined using a prior distribution on expected deformations from a basic template. Global shape information is represented using another prior on the relative locations of the individual features. An appropriately defined probabilistic model integrates the local and global information and directly leads to an overall distance measure between sequence patterns based on prior knowledge. A search algorithm using this distance measure is shown to efficiently and accurately f...

In this paper we describe a trainable object detector and its instantiations for detecting faces and cars at any size, location, and pose. To cope with variation in object orientation, the detector uses multiple classifiers, each spanning a different range of orientation. Each of these classifiers determines whether the object is present at a specified size within a fixed-size image window. To find the object at any location and size, these classifiers scan the image exhaustively. Each classifier is based on the statistics of localized parts. Each part is a transform from a subset of wavelet coefficients to a discrete set of values. Such parts are designed to capture various combinations of locality in space, frequency, and orientation. In building each classifier, we gathered the class-conditional statistics of these part values from representative samples of object and non-object images. We trained each classifier to minimize classification error on the training set by using Adaboost with Confidence-Weighted Predictions (Shapire and Singer, 1999). In detection, each classifier computes the part values within the image window and looks up their associated classconditional probabilities. The classifier then makes a decision by applying a likelihood ratio test. For efficiency, the classifier evaluates this likelihood ratio in stages. At each stage, the classifier compares the partial likelihood ratio to a threshold and makes a decision about whether to cease evaluation—labeling the input as non-object—or to continue further evaluation. The detector orders these stages of evaluation from a low-resolution to a high-resolution search of the image. Our trainable object detector achieves reliable and efficient detection of human faces and passenger cars with out-of-plane rotation.

In this paper we present a visual learning technique that maximizes the discrimination between positive and negative examples in a training set. We demonstrate our technique in the context of face detection with complex background without color or motion information, which has proven to be a challenging problem. We use a family of discrete Markov processes to model the face and background patterns and estimate the probability models using the data statistics. Then, we convert the learning process into an optimization, selecting the Markov process that optimizes the information-based discrimination between the two classes. The detection process is carried out by computing the likelihood ratio using the probability model obtained from the learning procedure. We show that because of the discrete nature of these models, the detection process is, by almost two orders of magnitude, less computationally expensive than neural network approaches. However, no improvement in terms of correct-answ...

Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in principle, superior performance, generative approaches provide many useful features, one of which is the ability to naturally establish explicit correspondence between model components and scene features – this, in turn, allows for the handling of missing data and unsupervised learning in clutter. We explore a hybrid generative/discriminative approach using ‘Fisher kernels ’ [1] which retains most of the desirable properties of generative methods, while increasing the classification performance through a discriminative setting. Furthermore, we demonstrate how this kernel framework can be used to combine different types of features and models into a single classifier. Our experiments, conducted on a number of popular benchmarks, show strong performance improvements over the corresponding generative approach and are competitive with the best results reported in the literature. 1