https://www.cin.ufpe.br/~rps/Artigos/Face%20Detection%20-%20%20A%20Survey.pdf

Face Detection

This paper describes the development and quantitative assessment of an approach to face detection (FD), with the application of image classification in mind. The approach entitled 'crude automatic face extraction' (CAFE), is based on skin colour segmentation, multiple image representations and multi-resolution scanning. It is a direct extension of an approach by Huang (1994). Assessment is in terms of false acceptance (FA) and false rejection (FR) scores using a large quantity of unconstrained typical Internet images, some of which contain faces and some of which do not. Skin-based colour segmentation is introduced as a front-end, along with several additional low-level image representations, the benefits of which can be seen by a reduction in the FA score from 74% to 17%. It is also noted that a skin probability map can improve FD significantly.

Face detection in colour images

A system and method for detecting a face using a pattern classifier learning face images and near face images are provided. The system includes a basis vector extractor, which receives a plurality of face images and a plurality of near-face images and extracts a plurality of face basis vectors expressing the face images and a plurality of near-face basis vectors expressing the near-face images; a feature vector extractor, which extracts face feature vectors and near-face feature vectors by projecting the face images and the near-face images upon the face and near-face feature vectors and projects an image, which is input for face detection, upon the basis vectors to extract the feature vector of the input image; a clustering unit, which classifies the face feature vectors and the near-face feature vectors into predetermined sub-classes and outputs a sub-class number of a sub-class including the feature vector of the input image among the sub-classes; a pattern classifier trainer, which trains each pattern classifier corresponding to a certain sub-class using face feature vectors and near-face feature vectors, which are included in the sub-class; and a face determiner, which applies the feature vector of the input image to the pattern classifier corresponding to the sub-class including the feature vector of the input image and determines whether the input image is a face image using the pattern classifier.

Method and system for face detection using pattern classifier

Face detection is the foremost task in building vision-based humancomputer interaction systems and in particular in applications such as face recognition, face identification, face tracking, expression recognition and content based image retrieval. A robust face detection system must be able to detect faces irrespective of illuminations, shadows, cluttered backgrounds, facial pose, orientation and facial expressions. Many approaches for face detection have been proposed. However, as revealed by FRVT 2002 tests, face detection in outdoor images with uncontrolled illumination and in images with varied pose (non-frontal profile views) is still a serious problem. In this chapter, we describe a Local-Global Graph (LGG) based method for detecting faces and for recognizing facial expressions accurately in real world image capturing conditions both indoor and outdoor, and with a variety of illuminations (shadows, high-lights, non-white lights) and in cluttered backgrounds. The LG Graph embeds both the local information (the shape of facial feature is stored within the local graph at each node) and the global information (the topology of the face). The LGG approach for detecting faces with maximum confidence from skin segmented images is described. The LGG approach presented here emulates the human visual perception for face detection. In general, humans first extract the most important facial features such as eyes, nose, mouth, etc. and then inter-relate them for face and facial expression representations. Facial expression recognition from the detected face images is obtained by comparing the LG Expression Graphs with the existing the Expression models present in the LGG database. The methodology is accurate for the expression models present in the database.

Skin-based Face Detection-Extraction and Recognition of Facial Expressions

Atomic decompositions are lower-cost alternatives to the principal component analysis (PCA) in tasks where sparse signal representation is required. In pattern classifications tasks, e.g. face detection, a careful selection of atoms is needed in order to ensure an optimal and fast-operating decomposition to be used in the feature extraction stage. In this contribution, adaptive boosting is used as criterion for selecting optimal atoms as features in frontal face detection
system. The goal is to speed up the learning process by a proper combination of a dictionary of atoms and a weak learner. Dictionaries of anisotropic wavelet packets are used where the total number of atoms is still feasible for large-size images. In the adaptive boosting algorithm a Bayesian classifier is used as a weak learner instead of a simple threshold, thus ensuring a higher accuracy for slightly increased computational cost during the detection stage. The
experimental results obtained for four different dictionaries are quite promising based on the good localization properties of the anisotropic wavelet packet functions.

Face detection by optimal atomic decomposition

Dimension reduction via linear subspace is very important in image pattern detection and recognition. This paper presents two new methods of dimension reduction and develops algorithms to locate human faces in gray-scale still images. The first technique develops eigenface subspace and eigenclutter subspace which represent faces and clutters respectively. The second technique chooses a common subspace to maximize the Bhattacharyya distance of two Gaussian distributions. Compared with the first method, the second method is more computationally efficient with slightly higher error rate. Our simulation result indicates that both methods outperform conventional template-based methods such as matched filter and eigenface methods.

T.Q. Nguyen

Papers

Two subspace methods to discriminate faces and clutters