Example-Based Learning for View-Based Human Face Detection

By Kah Kay Sung, Tomaso A. Poggio. 1998

We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face" and "nonface" model clusters. At each image location, a difference feature vector is computed between the local image pattern and the distribution-based model. A trained classifier determines, based on the difference feature vector measurements, whether or not a human face exists at the current image location. We show empirically that the distance metric we adopt for computing difference feature vectors, and the "nonface" clusters we include in our distribution-based model, are both critical for the success of our system.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Measuring Robustness to Natural Distribution Shifts in Image Classification (2020, methodology): “In the context of training sets, adversarial filtering is similar to hard negative mining, which is often used to generate training data for detection models [17, 30, 69, 83].”
Voting for Voting in Online Point Cloud Object Detection (2015, neutral): “[17, 2, 6]).”
Learning Multi-domain Convolutional Neural Networks for Visual Tracking (2015, background): “The optimal target state x ∗ is given by ﬁnding the example with the maximum positive score as (1)”
YOLOv4: Optimal Speed and Accuracy of Object Detection (2020, background): “In dealing with the problem of semantic distribution bias, a very important issue is that there is a problem of data imbalance between different classes, and this problem is often solved by hard negative example mining [72] or online hard example mining [67] in two-stage object detector.”
Three-dimensional image processing methods to identify and characterise aggregates in compacted asphalt mixtures (2010, methodology): “In the field of computer science, ANN has been extensively utilised for pattern recognition in images, with special emphasis on the application of face detection (Propp and Samal 1992, Rowley et al. 1998, Sung and Poggio 1998).”
Face Recognition (2018, unknown): “For example, [Sung and Poggio, 1998] used a combination of statistical measures and a multi-layer perceptron network for face detection.”
Dynamic Task Prioritization for Multitask Learning (2018, background): “We liken this to the problem of class imbalance, which is commonly remedied by hard negative mining [25, 26].”
Object class recognition by unsupervised scale-invariant learning (2003, background): “[6, 9, 11]), has recently gained some attention in the machine vision literature [1, 2, 3, 4, 13, 14, 19] with an emphasis on the detection of faces [12, 15, 16].”
FDDB: A benchmark for face detection in unconstrained settings (2010, background): “• single pose: the head is assumed to be in a single, upright pose (frontal [24, 18, 26] or profile [21]);”
Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (2016, methodology): “Since the training data are too large to fit in memory, we adopt the standard hard negative mining method [18], [58].”