Abstract—We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present a straightforward procedure for aligning positive face examples for training. To collect negative examples, we use a bootstrap algorithm, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting nonface training examples, which must be chosen to span the entire space of nonface images. Simple heuristics, such as using the fact that faces rarely overlap in images, can further improve the accuracy. Comparisons with several other state-of-the-art face detection systems are presented, showing that our system has comparable performance in terms of detection and false-positive rates. Index Terms—Face detection, pattern recognition, computer vision, artificial neural networks, machine learning.

We investigate the application of Support Vector Machines (SVMs) in computer vision. SVM is a learning technique developed by V. Vapnik and his team (AT&T Bell Labs.) that can be seen as a new method for training polynomial, neural network, or Radial Basis Functions classifiers. The decision surfaces are found by solving a linearly constrained quadratic programming problem. This optimization problem is challenging because the quadratic form is completely dense and the memory requirements grow with the square of the number of data points. We present a decomposition algorithm that guarantees global optimality, and can be used to train SVM's over very large data sets. The main idea behind the decomposition is the iterative solution of sub-problems and the evaluation of optimality conditions which are used both to generate improved iterative values, and also establish the stopping criteria for the algorithm. We present experimental results of our implementation of SVM, and demonstrate the ...

This paper presents a trainable object detection architecture that is applied to detecting people in static images of cluttered scenes. This problem poses several challenges. People are highly non-rigid objects with a high degree of variability in size, shape, color, and texture. Unlike previous approaches, this system learns from examples and does not rely on any a priori (handcrafted) models or on motion. The detection technique is based on the novel idea of the wavelet template that defines the shape of an object in terms of a subset of the wavelet coefficients of the image. It is invariant to changes in color and texture and can be used to robustly define a rich and complex class of objects such as people. We show how the invariant properties and computational efficiency of the wavelet template make it an effective tool for object detection. 1 Introduction The problem of object detection has seen a high degree of interest over the years. The fundamental problem is how to characte...

In this paper, we present a neural network-based face detection system. Unlike similar systems which are limited to detecting upright, frontal faces, this system detects faces at any degree of rotation in the image plane. The system employs multiple networks; a “router ” network first processes each input window to determine its orientation and then uses this information to prepare the window for one or more “detector ” networks. We present the training methods for both types of networks. We also perform sensitivity analysis on the networks, and present empirical results on a large test set. Finally, we present preliminary results for detecting faces rotated out of the image plane, such as profiles and semi-profiles. 1.

We present a neural network-based face detection system. A retinally connected neural network examines small windows of an image, and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We use a bootstrap algorithm for training the networks, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting non-face training examples, which must be chosen to span the entire space of non-face images. Comparisons with other state-of-the-art face detection systems are presented; our system has better performance in terms of detection and false-positive rates. This work was partially supported by a grant from Siemens Corporate Research, Inc., by the Department of the Army, Army Research Office under grant number DAAH04-94-G-0006, and by the Office of Naval Research under grant number N00014-95-1-0591. This work was started while Shumeet Balu...

We describe an algorithm for automatically learning discriminative components of objects with SVM classifiers. It is based on growing image parts by minimizing theoretical bounds on the error probability of an SVM. Component-based face classifiers are then combined in a second stage to yield a hierarchical SVM classifier. Experimental results in face classification show considerable robustness against rotations in depth and suggest performance at significantly better level than other face detection systems. Novel aspects of our approach are: a) an algorithm to learn component-based classification experts and their combination, b) the use of 3-D morphable models for training, and c) a maximum operation on the output of each component classifier which may be relevant for biological models of visual recognition.

This paper presents experimental comparisons of various image representations for object detection using kernel classifiers. In particular it discusses the use of support vector machines (SVM) for object detection using as image representations raw pixel values, projections onto principal components, and Haar wavelets. General linear transformations of the images through the choice of the kernel of the SVM are considered. Experiments showing the effects of histogram equalization, a non-linear transformation, are presented. Image representations derived from probabilistic models of the class of images considered, through the choice of the kernel of the SVM, are also evaluated. Finally, we present a feature selection method using SVMs, and show experimental results. Keywords: Support Vector Machines, Kernel, Wavelets, PCA, histogram equalization. 1. Introduction Detection of real-world objects in images, such as faces and people, is a challenging problem of fundamental importance in m...

Human faces provide enormous information and a friendly interface in intelligent human computer interaction. This has motivated a very active research area on, among others, face recognition, face tracking, pose estimation, expression recognition and gesture recognition. However, most existing methods on these topics assume human faces in an image or a image sequence have been identied and localized. To build a fully automated system that analyzes information of human faces, it is essential to develop robust and eÆcient algorithms to detect human faces. Given a single or a sequence of images, the goal of face detection is to identify and locate human faces regardless of their positions, scales, orientations and lighting conditions. Such problem is challenging because human faces are highly non-rigid objects with a high degree of variability in size, shape, color and texture. The purpose of this paper is to give a critical survey of existing techniques on face detection which has attra...

This thesis presents a general trainable framework for object detection in static images of cluttered scenes and a novel motion based extension that enhances performance over video sequences. The detection technique we develop is based on a wavelet representation of an object class derived from a statistical analysis of the class instances. By learning an object class in terms of a subset of an overcomplete dictionary of wavelet basis functions, we derive a compact representation of an object class which is used as input to a support vector machine classifier. The paradigm we present successfully handles the major difficulties of object detection: overcoming the in-class variability of complex classes such as faces and pedestrians and providing a very low false detection rate, even in unconstrained environments. We demonstrate the capabilities of the technique in two domains whose inherent information content differs significantly. The first system is face detection; we extend the met...

The paper proposes the application of majority voting on the output of several support vector machines in order to select the most suitable learning machine for frontal face detection. The first experimental results indicate a significant reduction of the rate of false positive patterns. 1.