【正文】 showing that our system has parable performance in terms of detection and falsepositive rates.Keywords: Face detection, Pattern recognition, Computer vision, Artificial neural networks, Ma chine learning1 IntroductionIn this paper, we present a neural networkbased algorithm to detect upright, frontal views of faces in grayscale images1. The algorithm works by applying one or more neural networks directly to portions of the input image, and arbitrating their results. Each network is trained to output the presence or absence of a face. The algorithms and training methods are designed to be general, with little customization for faces.Many face detection researchers have used the idea that facial images can be characterized directly in terms of pixel intensities. These images can be characterized by probabilistic models of the set of face images [4, 13, 15], or implicitly by neural networks or other mechanisms [3, 12, 14,19, 21, 23, 25, 26]. The parameters for these models are adjusted either automatically from exampleimages (as in our work) or by hand. A few authors have taken the approach of extracting features and applying either manually or automatically generated rules for evaluating these features [7, 11].Training a neural network for the face detection task is challenging because of the difficulty in characterizing prototypical “nonface” images. Unlike face recognition, in which the classes to be discriminated are different faces, the two classes to be discriminated in face detection are “images containing faces” and “images not containing faces”. It is easy to get a representative sample of images which contain faces, but much harder to get a representative sample of those which do not. We avoid the problem of using a huge training set for nonfaces by selectively adding images to thetraining set as training progresses [21]. This “bootstrap” method reduces the size of the training set needed. The use of arbitration between multiple networks and heuristics to clean up the results significantly improves the accuracy of the detector.Detailed descriptions of the example collection and training methods, network architecture,and arbitration methods are given in Section 2. In Section 3, the performance of the system is examined. We find that the system is able to detect % of the faces over a test set of 130 plex images, with an acceptable number of false positives. Section 4 briefly discusses some techniques that can be used to make the system run faster, and Section 5 pares this system with similar systems. Conclusions and directions for future research are presented in Section 6.2 Description of the SystemOur system operates in two stages: it first applies a set of neural networkbased filters to an image, and then uses an arbitrator to bine the outputs. The filters examine each location in the image at several scales, looking for locations that might contain a face. The arbitrator then merges detections from individual filters and eliminates overlapping detections. Stage One: A Neural NetworkBased FilterThe first ponent of our system is a filter that receives as input a 20x20 pixel region of the image, and generates an output ranging from 1 to 1, signifying the presence or absence of a face, respectively. To detect faces anywhere in the input, the filter is applied at every location in the image. To detect faces larger than the window size, the input image is repeatedly reduced in size (by subsampling), and the filter is applied at each size. This filter must have some invariance to position and scale. The amount of invariance determines the number of scales and positions at which it must be applied. For the work presented here, we apply the filter at every pixel position in the image, and scale the image down by a factor of for each step in the pyramid.The filtering algorithm is shown in Fig. 1. First, a preprocessing step, adapted from [21], isapplied to a window of the image. The window is then passed through a neural network, which decides whether the window contains a face. The preprocessing first attempts to equalize the intensity values in across the window. We fit a function which varies linearly across the window to the intensity values in an oval region inside the window. Pixels outside the oval (shown in Fig. 2a) may represent the background, so those intensity values are ignored in puting the lighting variation across the face. The linear function will approximate the overall brightness of each part of the window, and can be subtracted from the window to pensate for a variety of lighting conditions. Then histogram equalization is performed, which nonlinearly maps the intensity values to expand the range of intensities in the window. The histogram is puted for pixels inside an oval region in the window. This pensates for differences in camera input gains, as well as improving contrast in some cases. The preprocessing steps are shown in Fig. 2.The preprocessed window is then passed through a neural network. The network has retinalconnections to its input layer。 however, one such case is illustrated by the left two faces in Fig. 3B, where one face partially occludes another.The implementation of these two heuristics is illustrated in Fig. 6. Each detection at a particularlocation and scale is marked in an image pyramid, labelled the “output” pyramid. Then, each location in the pyramid is replaced by the number of detections in a specified neighborhood of that location. This has the effect of “spreading out” the detections. Normally, the neighborhood extends an equal number of pixels in the dimensions of scale