Submitted by Patrícia Cerveira (pcerveira1@gmail.com) on 2017-06-07T18:57:51Z No. of bitstreams: 1 Fernando Otávio Gomes da Fonseca_Dissertação.pdf: 3191276 bytes, checksum: f567916527bd35630c5b6be3fb1b0c6e (MD5) / Approved for entry into archive by Biblioteca da Escola de Engenharia (bee@ndc.uff.br) on 2017-06-29T16:27:45Z (GMT) No. of bitstreams: 1 Fernando Otávio Gomes da Fonseca_Dissertação.pdf: 3191276 bytes, checksum: f567916527bd35630c5b6be3fb1b0c6e (MD5) / Made available in DSpace on 2017-06-29T16:27:45Z (GMT). No. of bitstreams: 1 Fernando Otávio Gomes da Fonseca_Dissertação.pdf: 3191276 bytes, checksum: f567916527bd35630c5b6be3fb1b0c6e (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / O presente trabalho visa estudar e comparar 2 métodos de detecção de faces em imagens, a fim de averiguar a eficiência e eficácia dos mesmos, propondo melhorias nos processos avaliados. O método de detecção de caraterísticas em imagens proposto por Viola e Jones é ainda uma referência na detecção de faces. Neste trabalho serão avaliadas propostas de melhorias nesse processo e comparados resultados quando utilizadas redes neurais mais modernas para o treinamento da base de dados. Realizamos simulações computacionais desenvolvidas em Matlab para obtenção dos resultados do comportamento dos sistemas e ao final do trabalho apresentamos as conclusões e sugestões de projetos futuros. / This work aims to study and compare two methods of face detection in images, in order to verify theirefficiency and effectiveness, proposing improvements in such processes. The feature detection method in images proposed by Viola and Jones is also a reference in detecting faces. In this work improvement proposals will be evaluated in thatprocess and compared results when used more modern neural networks for the training database. We performed computer simulations developed in Matlab to obtain theresults onsystems behavior. At the endof the work,we present the conclusions and suggestions for future projects.

>Magister Scientiae - MSc / This research proposes an approach to recognizing facial expressions in the presence of rotations and partial occlusions of the face. The research is in the context of automatic machine translation of South African Sign Language (SASL) to English. The proposed method is able to accurately recognize frontal facial images at an average accuracy of 75%. It also achieves a high recognition accuracy of 70% for faces rotated to 60◦. It was also shown that the method is able to continue to recognize facial expressions even in the presence of full occlusions of the eyes, mouth and left/right sides of the face. The accuracy was as high as 70% for occlusion of some areas. An additional finding was that both the left and the right sides of the face are required for recognition. As an addition, the foundation was laid for a fully automatic facial expression recognition system that can accurately segment frontal or rotated faces in a video sequence.

This thesis focuses on the design and development of a web application that offers help in managing family photographic material, with the emphasis on data integrity and security, and maximum transparency when handling personal information. The application will be usable on any device with a screen, web browser and internet connection. One of its key features will be face detection on uploaded photographs.

This thesis focuses on the development of an open source software capable of automatic face detection in an image captured by a thermal camera, followed by a temperature measuring. This software is supposed to aid in the COVID-19 pandemics. The developed software is independent of used thermal camera. In this thesis, I am using TIM400 thermal camera. The implementation of the face detection was achieved by an OpenCV module. The methods tested were Template Matching, Eigen Faces, and Cascade Classifier. The last-mentioned had the best results, hence was used in the final version of the software. Cascade Classifier is looking for the eyes and their surrounding area in the image, allowing the software to subsequently measure the temperature on the surface of one's forehead. One can therefore be wearing a face mask or a respirator safely. The temperature measuring works in real time and the software is able to capture several people at once. It then keeps a record of the temperature of each measured individual as well as the time of the measurement. The software as a whole is a part of an installation file compatible with the Windows operating system. The functionality of this software was tested – the video recordings are included in this thesis.

The aim of this work is to realize a system in the Matlab-Simulink environment, which will be able to detect and recognize the human face from the input image. The created model will actually simulate the biometric security systems working on the principle of face recognition. The work is divided into two parts. In the first part, several methods for face detection from image are described. We focused on the symptomatic oriented and color segmentation methods. The pattern matching method is also described and implemented; the advantage ofthe pattern matching that it can be used either for face detection or face recognition. The second part of this work contains a description of the face recognition. Where PCA (Principal Component Analysis) are used for this task, this part of the work also includes experimental results of tests performed on our methods.

This master thesis deals with the issues of the eye blink recognition from video. The main task is to analyse algorithms dealing with a detection of persons and make a program that could recognize the eye blink. Analysis of these algorithms and their problems are in the first part of this thesis. In the second part design and properties of my program are described. The realization of the program is based on the method of move detection using the accumulated difference frame, which helps to identify the eye areas. The eye blink detection algorithm tests a match between a tresholded pattern of the eye area taken from the actual frame and the frame before. The resolution whether the eye blink happened or not, is based on the level of the match. The algorithm is designed for watching a sitting man, which is slightly moving. The background can be a little dynamic as well. An average quality video with a moderator and dynamic backround was used as a tested subject.

My diploma thesis deals about face detection in picture. I try to outline problems of computer vision, artificial intelligence and machine learning. I described in details the proposed detection by Viola and Jones, which uses AdaBoost learning algorithm. This method was deliberately chosen for speed and detection accuracy. This detector was made in programming language C / C + + using the OpenCV library. To a final learning was used database of faces images „MIT CVCL Face Database“. The main goal was to propose the face detector utilizable also in video-sequences.

This diploma thesis deals with the options of image processing on mobile platforms, especially on Android operating system, and their use in a driver drowsiness detection system. The introductory part analyses the influence of drowsiness on drivers, focusing chiefly on the microsleep, and describes the already existing driver drowsiness detection systems. The thesis proceeds by the description of possibilities of image processing on mobile platforms with the emphasis on Android operating system together with the OpenCV library, known from the desktop interface. This is followed by comparison of various options of library implementation on a mobile platform. The chapter on image processing describes the algorithms for the detection of objects in the image, usable for detection of face, eyes and their posture. The practical part implements the selected methods for the Android operating system. A referential application was created to provide an explanatory demonstration of these methods on a real device. The individual methods are compared on the basis of time consumption, error rate and other factors.

<div> <p>People spend most of their time indoors. Because people’s health and productivity are highly dependent on the quality of the indoor thermal environment, it is important to provide occupants with healthy, comfortable and productive indoor thermal environment. However, inappropriate thermostat temperature setpoint settings not only wasted large amount of energy but also make occupants less comfortable. This study intended to develop a new control strategy for HVAC systems to adjust the thermostat setpoint automatically and accordingly to provide a more comfortable and satisfactory thermal environment.</p> <p>This study first trained an image classification model based on CNN to classify occupants’ amount of clothing insulation (clothing level). Because clothing level was related to human thermal comfort, having this information was helpful when determining the temperature setpoint. By using this method, this study performed experimental study to collect comfortable air temperature for different clothing levels. This study collected 450 data points from college student. By using the data points, this study developed an empirical curve which could be used to calculate comfortable air temperature for specific clothing level. The results obtained by using this curve could provide environments that had small average dissatisfaction and average thermal sensation closed to neutral.</p> <p>To adjust the setpoint temperature according to occupants’ thermal comfort, this study used mean facial skin temperature as an indicator to determine the thermal comfort. Because when human feel hot, their body temperature would rise and vice versa. To determine the correlation, we used a long wave infrared (LWIR) camera to non-invasively obtain occupant’s facial thermal map. By processing the thermal map with Haar-cascade face detection program, occupant’s mean facial skin temperature was calculated. By using this method, this study performed experimental study to collect occupant’s mean facial skin temperature under different thermal environment. This study collected 225 data points from college students. By using the data points, this study discovered different intervals of mean facial skin temperature under different thermal environment. </p> <p>Lastly, this study used the data collected from previous two investigations and developed a control platform as well as the control logic for a single occupant office to achieve the objective. The measured clothing level using image classification was used to determine the temperature setpoint. According to the measured mean facial skin temperature, the setpoint could be further adjusted automatically to make occupant more comfortable. This study performed 22 test sessions to validate the new control strategy. The results showed 91% of the tested subjects felt neutral in the office</p> </div> <br>

Human key point tracking such as face detection and recognition has become an increasingly popular research topic. It is a platform independent functionality and already being implemented on a wide range of platforms. Android is one such platform that runs on mobile phones and top of many edge devices such as car devices and smart home appliances. In the current times, AI and ML related applications are slightly moving into those edge devices due to various reasons such as security and low latency. The hardware enhancements are also backing this trend that happened over the last few years. Many solutions and algorithms have been proposed in this context, and various frameworks and models have also been developed. Even though there are different models available, they tend to deliver varying results in terms of performance. Evaluating these different alternatives to find an optimized solution is a problem worth addressing. In this thesis project, several selected face detection and recognition models have been implemented in an Android device, and their performance been evaluated. Google ML Kit showed the best results among the face detection methods since it took only around 68 milliseconds on average to detect a face. Out of the three face recognition algorithms evaluated, FaceNet was the most accurate as it showed an accuracy above 95% for most cases. Meanwhile, MobileFaceNet was the fastest algorithm, and it took only around 90 milliseconds on average to produce and output. Eventually, a face recognition application was also developed using the best performing models selected from the experiment.