Face detection in video sequence is becoming popular in surveillance applications. The trade-off between obtaining discriminative features to achieve accurate detection versus computational overhead of extracting these features, which affects the classification speed, is a persistent problem. Two ideas are introduced to increase the features’ discriminative power. These ideas are used to implement two frontal face detectors examined on a 2D low-resolution surveillance sequence. First contribution is the parallel classifier. High discriminative power features are achieved by fusing the decision from two different features trained classifiers where each type of the features targets different image structure. Accurate and fast to train classifier is achieved. Co-occurrence of Local Binary Patterns (CoLBP) features is proposed, the pixels of the image are targeted. CoLBP features find the joint probability of multiple LBP features. These features have computationally efficient feature extraction and provide high discriminative features; hence, accurate detection is achieved.

Face detection in video sequence is becoming popular in surveillance applications. The trade-off between obtaining discriminative features to achieve accurate detection versus computational overhead of extracting these features, which affects the classification speed, is a persistent problem. Two ideas are introduced to increase the features’ discriminative power. These ideas are used to implement two frontal face detectors examined on a 2D low-resolution surveillance sequence. First contribution is the parallel classifier. High discriminative power features are achieved by fusing the decision from two different features trained classifiers where each type of the features targets different image structure. Accurate and fast to train classifier is achieved. Co-occurrence of Local Binary Patterns (CoLBP) features is proposed, the pixels of the image are targeted. CoLBP features find the joint probability of multiple LBP features. These features have computationally efficient feature extraction and provide high discriminative features; hence, accurate detection is achieved.

Face detection refers to a number of techniques that identify faces in images and videos. As part of the senior project exercise at Pomona College, I explore the process of face detection using a JavaScript library called CLMtrackr. CLMtrackr works in any browser and detects faces within the video stream captured by a webcam. The focus of this paper is to explore the shortcomings in the inclusivity of the CLMtrackr library and consequently that of face detection. In my research, I have used two datasets that contain human faces with diverse backgrounds, in order to assess the accuracy of CLMtrackr. The two datasets are the MUCT and PPB. In addition, I investigate whether skin color is a key factor in determining face detection's success, to ascertain where and why a face might not be recognized within an image. While my research and work produced some inconclusive results due to a small sample size and a couple outliers in my outputs, it is clear that there is a trends toward the CLMtrackr algorithm recognizing faces with lighter skin tones more often than darker ones.

Made available in DSpace on 2016-03-15T19:37:53Z (GMT). No. of bitstreams: 1 Jorge Candido.pdf: 1397085 bytes, checksum: e82ad6a587c16813c068018b87471755 (MD5) Previous issue date: 2007-02-26 / This work presents a face detection system that uses a Bayesian Network to combine information from different computational cheap visual operators. The aim in this work is to show that combining simple features in a Bayesian Network allows building an enhanced face detector system, increasing the detection rate and speeding up the face detection process. This face detector has been developed to work in the stream acquired by a USB computer camera. After the detector finds a face in the stream, a face tracking system begins to work, locating the eyes position at the screen. The system is part of a high precision optical mouse system that will be used in human-computer interface, helpin users with certain disabilities. / Neste trabalho, foi desenvolvido um sistema automático de detecção e rastreio de face. O sistema de detecção de face é composto de três operadores visuais que fazem a detecção de atributos faciais simples. A característica principal destes operadores é que eles são construídos para funcionar com custo computacional baixo, otimizando o tempo de processamento. Os operadores foram construídos utilizando técnicas de redes neurais para a detecção dos olhos, casamento de modelos para a detecção da boca e para a identificação de cor de pele. Os operadores visuais formam os elementos básicos do detector de face cujos resultados são combinados em uma Rede Bayesiana que define o resultado final do algoritmo de detecção de face . O uso da Rede Bayesiana proporciona ao sistema um melhor desempenho em relação aos operadores individualmente . Este detector foi implementado de forma a analisar as imagens captadas quadro a quadro por uma câmera de vídeo USB. Quando acontece uma detecção de face, a mesma passa a ser ratreada por um sistema de rastreio que busca a região de cor de pele da face, determinando sua posição na tela. Este sistema pode ser utilizado em diversas aplicações que requerem a detecção de faces, em particular, este sistema faz parte de um sistema de mouse óptico de alta precisão para, por exemplo, facilitar a interface homem máquina para pessoas com problemas de coordenação motora.

Este trabalho tem como objetivo desenvolver uma metodologia baseada em lógica nebulosa, (KLIR ; YUAN, 1995) para detectar faces humanas em imagens digitais. Considerando que pessoas conseguem reconhecer facilmente as faces humanas, este trabalho prevê a pesquisa da informação relativa a esse reconhecimento utilizando os resultados obtidos, em um esquema \"fuzzy\", para identificação de faces humanas em imagens digitais. É proposto então um algoritmo que classifique automaticamente as regiões de uma imagem em faces humanas ou não. O conhecimento para a construção da base de regras foi obtido através de informações das pessoas por meio de uma pesquisa de campo onde as respostas foram numericamente armazenadas para a geração da classificação nebulosa. Foram gerados desenhos line-draw que de uma maneira global representam as faces humanas. Esses desenhos foram apresentados às pessoas entrevistadas que forneceram subsídios para a montagem das regras \"fuzzy\". O algoritmo foi capaz de a partir daí, identificar faces humanas em imagens digitalizadas. Imagens simples contendo uma face frontal foram submetidas a um algoritmo e ao passarem por processamento (extração de bordas, erosão, binarização, etc...) perderam características, tornando difícil sua identificação. O algoritmo \"fuzzy\" foi capaz de atribuir um grau de pertinência à imagem dentro do conjunto de faces humanas frontais. A lógica nebulosa possui história recente, porém, desde cedo, demonstra sua versatilidade, principalmente por traduzir modelos não lineares ou imprecisos, os quais não apresentam convergência através de modelagem matemática convencional. / The present master dissertation aims to develop a methodology based on fuzzy pattern (KLIR; YUAN, 1995) to detect human faces in digital images. Considering that people are easily able to recognize human faces, this study foresees the research of the relative information to this recognition using the acquire results, in a \"fuzzy\" scheme, for the identification of human faces in digital images. It\'s proposed an algorithm which automatically classifies or not the regions of an image in human faces. It is based on the information acquired from people by means of a field research where the answers are stored numerically for the creation of the fuzzy classification. Drawings line-draw were created to represent human faces and were presented to the people interviewed to furnish information for the creation of the fuzzy rules. After that the algorithm was able to identify human faces in digitalized images. The algorithm utilizes simple images containing a frontal face, which lose their characteristics when they are processed (edges extration, erosion, binary image, etc...) and make their identification difficult. The fuzzy algorithm is also able to classify the images within the set of frontal human faces. The fuzzy logic has a recent history, however, it has always demonstrated its versatility, mainly regarding the translation of non-linear or inexact models which do not present conventional mathematical convergence through modeling.

Human face recognition systems have gained a considerable attention during last few years. There are very many applications with respect to security, sensitivity and secrecy. Face detection is the most important and first step of recognition system. Human face is non rigid and has very many variations regarding image conditions, size, resolution, poses and rotation. Its accurate and robust detection has been a challenge for the researcher. A number of methods and techniques are proposed but due to a huge number of variations no one technique is much successful for all kinds of faces and images. Some methods are exhibiting good results in certain conditions and others are good with different kinds of images. Image discriminating techniques are widely used for pattern and image analysis. Common discriminating methods are discussed. / SIPL, Mechatronics, GIST 1 Oryong-Dong, Buk-Gu, Gwangju, 500-712 South Korea tel. 0082-62-970-2997

This work is on a method for face detection through analysis of photos. Accurate location of faces and point out the faces are implemented. In the first step, we use Cb and Cr channel to find where the skin color parts are on the photo, then remove noise which around the skin parts, finally, use morphology technique to detect face part exactly. Our result shows this approach can detect faces and establish a good technical based for future face recognition.

>Magister Scientiae - MSc / The South African Sign Language research group at the University of the Western Cape is in the process of creating a fully-edged machine translation system to automatically translate between South African Sign Language and English. A major component of the system is the ability to accurately recognise facial expressions, which are used to convey emphasis, tone and mood within South African Sign Language sentences. Traditionally, facial expression recognition research has taken one of two paths: either recognising whole facial expressions of which there are six i.e. anger, disgust, fear, happiness, sadness, surprise, as well as the neutral expression; or recognising the fundamental components of facial expressions as defined by the Facial Action Coding System in the form of Action Units. Action Units are directly related to the motion of specific muscles in the face, combinations of which are used to form any facial expression. This research investigates enhanced recognition of whole facial expressions by means of a hybrid approach that combines traditional whole facial expression recognition with Action Unit recognition to achieve an enhanced classification approach.

The diploma thesis focuses on programming in the Matlab for the Raspberry Pi 3 platform. For the purpose of the presentation, there are two applications designed for Raspberry Pi that are using available hardware, camera and servos. The first application serves as colour object detecting and accurate tracking by using camera calibration. The second application serves as a face detection and recognition. These applications are implemented by modern methods and knowledge of computer vision. Tracking of the objects and face recognition are verified by an experiment that reveals the accuracy of the used methods.

This thesis deals with human recognition on a videorecording. Convolution neural network was used for face recognition, from which we will get multidimensional vector, which will allow to determine person’s identity. There are demands imposed on the system, for it to be able to work in real time and could be used for example for person recognition at various conferences, or as a part of security system. Whole system is written in Python language. Part of this thesis is dataset in form of videorecords with persons.