Redeye artifact is the most prevalent problem in the flash photography, especially using compact cameras with built-in flash, which bothers both amateur and professional photographers. Hence, removing the affected redeye pixels has become an important skill. This thesis work presents a completely automatic approach for the purpose of redeye detection and removal and it consists of two modules: detection and correction of the redeye pixels in an individual eye, detection of two red eyes in an individual face.This approach is considered as a combination of some of the previous attempts in the area of redeye removal together with some minor and major modifications and novel ideas. The detection procedure is based on the redness histogram analysis followed by two adaptive methods, general and specific approaches, in order to find a threshold point. The correction procedure is a four step algorithm which does not solely rely on the detected redeye pixels. It also applies some more pixel checking, such as enlarging the search area and neighborhood checking, to improve the reliability of the whole procedure by reducing the image degradation risk. The second module is based on a skin-likelihood detection algorithm. A completely novel approach which is utilizing the Golden Ratio in order to segment the face area into some specific regions is implemented in the second module. The proposed method in this thesis work is applied on more than 40 sample images; by considering some requirements and constrains, the achieved results are satisfactory.

Eyes allow us to see and gather information about the environment. Eyes mainly act as an input organ as they collect light, but they also can be considered an output organ as they indicate the subject's gaze direction. Using the orientation of the head and the position of the eyes, it is possible to estimate the gaze path of an individual. Gaze estimation is a fast growing technology that track a person's eyes and head movements to "pin point" where the subject is looking at on a computer screen. The gaze direction is described as a person's line of sight. The gaze point, also known as the focus point, is defined as the intersection of the line of sight with the screen. Gaze tracking has an infinite number of applications such as monitoring driver alertness or helping track a person's eyes with a psychological disorder that cannot communicate his/her issues. Gaze tracking is also used as a human-machine interface for disabled people that have lost total control of their limbs. Another application of gaze estimation is marketing. Companies use the information given by the gaze estimation system from their customers to design their advertisements and products. / Electrical and Computer Engineering

Nowadays, there is growing interest in face detection applications for unconstrained environments. The increasing need for public security and national security motivated our research on the automatic face detection system. For public security surveillance applications, the face detection system must be able to cope with unconstrained environments, which includes cluttered background and complicated illuminations. Supervised approaches give very good results on constrained environments, but when it comes to unconstrained environments, even obtaining all the training samples needed is sometimes impractical. The limitation of supervised approaches impels us to turn to unsupervised approaches. In this thesis, we present an efficient and unsupervised face detection system, which is feature and configuration based. It combines geometric feature detection and local appearance feature extraction to increase stability and performance of the detection process. It also contains a novel adaptive lighting compensation approach to normalize the complicated illumination in real life environments. We aim to develop a system that has as few assumptions as possible from the very beginning, is robust and exploits accuracy/complexity trade-offs as much as possible. Although our attempt is ambitious for such an ill posed problem-we manage to tackle it in the end with very few assumptions.

In this paper is tested method for detection skin on the driver's head. It is based on skin color and motion detection. We also tested method for eye detection in image.

Eye tracking has a number of useful applications ranging from monitoring a vehicle driver for possible signs of fatigue, providing an interface to enable severely disabled people to communicate with others, to a number of medical applications. Most eye tracking applications require a non-intrusive way of tracking the eyes, making a camera-based approach a natural choice. However, although significant progress has been made in recent years, modern eye tracking systems still have not overcome a number of challenges including eye occlusions, variable ambient lighting conditions and inter-subject variability. This thesis describes the complete design and implementation of a real-time camera-based eye tracker, which was developed mainly for indoor applications. The developed eye tracker relies on the so-called bright/dark pupil effect for both the eye detection and eye tracking phases. The bright/dark pupil effect was realised by the development of specialised hardware and near-infrared illumination, which were interfaced with a machine vision camera. For the eye detection phase the performance of three different types of classifiers, namely neurals networks, SVMs and AdaBoost were directly compared with each other on a dataset consisting of 17 individual subjects from different ethnic backgrounds. For the actual tracking of the eyes, a Kalman filter was combined with the mean-shift tracking algorithm. A PC application with a graphical user interface (GUI) was also developed to integrate the various aspects of the eye tracking system, which allows the user to easily configure and use the system. Experimental results have shown the eye detection phase to be very robust, whereas the eye tracking phase was also able to accurately track the eyes from frame-to-frame in real-time, given a few constraints. AFRIKAANS : Oogvolging het ’n beduidende aantal toepassings wat wissel van die deteksie van bestuurderuitputting, die voorsiening van ’n rekenaarintervlak vir ernstige fisies gestremde mense, tot ’n groot aantal mediese toepassings. Die meeste toepassings van oogvolging vereis ’n nie-indringende manier om die oë te volg, wat ’n kamera-gebaseerde benadering ’n natuurlike keuse maak. Alhoewel daar alreeds aansienlike vordering gemaak is in die afgelope jare, het moderne oogvolgingstelsels egter nogsteeds verskeie uitdagings nie oorkom nie, insluitende oog okklusies, veranderlike beligtingsomstandighede en variansies tussen gebruikers. Die verhandeling beskryf die volledige ontwerp en implementering van ’n kamera-gebaseerde oogvolgingsstelsel wat in reële tyd werk. Die ontwikkeling van die oogvolgingsstelsel maak staat op die sogenaamde helder/donker pupil effek vir beide die oogdeteksie en oogvolging fases. Die helder/donker pupil effek was moontlik gemaak deur die ontwikkeling van gespesialiseerde hardeware en naby-infrarooi illuminasie. Vir die oogdeteksie fase was die akkuraatheid van drie verskillende tipes klassifiseerders getoets en direk vergelyk, insluitende neurale netwerke, SVMs en AdaBoost. Die datastel waarmee die klassifiseerders getoets was, het bestaan uit 17 individuele toetskandidate van verskillende etniese groepe. Vir die oogvolgings fase was ’n Kalman filter gekombineer met die gemiddelde-verskuiwings algoritme. ’n Rekenaar program met ’n grafiese gebruikersintervlak was ontwikkel vir ’n persoonlike rekenaar, sodat al die verskillende aspekte van die oogvolgingsstelsel met gemak opgestel kon word. Eksperimentele resultate het getoon dat die oogdeteksie fase uiters akkuraat en robuust was, terwyl die oogvolgings fase ook hoogs akuraat die oë gevolg het, binne sekere beperkinge. Copyright / Dissertation (MEng)--University of Pretoria, 2011. / Electrical, Electronic and Computer Engineering / unrestricted

Human face recognition is an important area in the field of biometrics. It has been an active area of research for several decades, but still remains a challenging problem because of the complexity of the human face. In this thesis we describe fully automatic solutions that can locate faces and then perform identification and verification. We present a solution for face localisation using eye locations. We derive an efficient representation for the decision hyperplane of linear and nonlinear Support Vector Machines (SVMs). For this we introduce the novel concept of $\rho$ and $\eta$ prototypes. The standard formulation for the decision hyperplane is reformulated and expressed in terms of the two prototypes. Different kernels are treated separately to achieve further classification efficiency and to facilitate its adaptation to operate with the fast Fourier transform to achieve fast eye detection. Using the eye locations, we extract and normalise the face for size and in-plane rotations. Our method produces a more efficient representation of the SVM decision hyperplane than the well-known reduced set methods. As a result, our eye detection subsystem is faster and more accurate. The use of fractals and fractal image coding for object recognition has been proposed and used by others. Fractal codes have been used as features for recognition, but we need to take into account the distance between codes, and to ensure the continuity of the parameters of the code. We use a method based on fractal image coding for recognition, which we call the Fractal Neighbour Distance (FND). The FND relies on the Euclidean metric and the uniqueness of the attractor of a fractal code. An advantage of using the FND over fractal codes as features is that we do not have to worry about the uniqueness of, and distance between, codes. We only require the uniqueness of the attractor, which is already an implied property of a properly generated fractal code. Similar methods to the FND have been proposed by others, but what distinguishes our work from the rest is that we investigate the FND in greater detail and use our findings to improve the recognition rate. Our investigations reveal that the FND has some inherent invariance to translation, scale, rotation and changes to illumination. These invariances are image dependent and are affected by fractal encoding parameters. The parameters that have the greatest effect on recognition accuracy are the contrast scaling factor, luminance shift factor and the type of range block partitioning. The contrast scaling factor affect the convergence and eventual convergence rate of a fractal decoding process. We propose a novel method of controlling the convergence rate by altering the contrast scaling factor in a controlled manner, which has not been possible before. This helped us improve the recognition rate because under certain conditions better results are achievable from using a slower rate of convergence. We also investigate the effects of varying the luminance shift factor, and examine three different types of range block partitioning schemes. They are Quad-tree, HV and uniform partitioning. We performed experiments using various face datasets, and the results show that our method indeed performs better than many accepted methods such as eigenfaces. The experiments also show that the FND based classifier increases the separation between classes. The standard FND is further improved by incorporating the use of localised weights. A local search algorithm is introduced to find a best matching local feature using this locally weighted FND. The scores from a set of these locally weighted FND operations are then combined to obtain a global score, which is used as a measure of the similarity between two face images. Each local FND operation possesses the distortion invariant properties described above. Combined with the search procedure, the method has the potential to be invariant to a larger class of non-linear distortions. We also present a set of locally weighted FNDs that concentrate around the upper part of the face encompassing the eyes and nose. This design was motivated by the fact that the region around the eyes has more information for discrimination. Better performance is achieved by using different sets of weights for identification and verification. For facial verification, performance is further improved by using normalised scores and client specific thresholding. In this case, our results are competitive with current state-of-the-art methods, and in some cases outperform all those to which they were compared. For facial identification, under some conditions the weighted FND performs better than the standard FND. However, the weighted FND still has its short comings when some datasets are used, where its performance is not much better than the standard FND. To alleviate this problem we introduce a voting scheme that operates with normalised versions of the weighted FND. Although there are no improvements at lower matching ranks using this method, there are significant improvements for larger matching ranks. Our methods offer advantages over some well-accepted approaches such as eigenfaces, neural networks and those that use statistical learning theory. Some of the advantages are: new faces can be enrolled without re-training involving the whole database; faces can be removed from the database without the need for re-training; there are inherent invariances to face distortions; it is relatively simple to implement; and it is not model-based so there are no model parameters that need to be tweaked.

A device capable of continuously monitoring an individual’s levels of alertness in real-time is highly desirable for preventing drowsiness and lapse related accidents. This thesis presents the development of a non-intrusive and light-insensitive video-based system that uses computer-vision methods to localize face, eyes, and eyelids positions to measure level of eye closure within an image, which, in turn, can be used to identify visible facial signs associated with drowsiness and behavioural microsleeps. The system was developed to be non-intrusive and light-insensitive to make it practical and end-user compliant. To non-intrusively monitor the subject without constraining their movement, the video was collected by placing a camera, a near-infrared (NIR) illumination source, and an NIR-pass optical filter at an eye-to-camera distance of 60 cm from the subject. The NIR-illumination source and filter make the system insensitive to lighting conditions, allowing it to operate in both ambient light and complete darkness without visually distracting the subject. To determine the image characteristics and to quantitatively evaluate the developed methods, reference videos of nine subjects were recorded under four different lighting conditions with the subjects exhibiting several levels of eye closure, head orientations, and eye gaze. For each subject, a set of 66 frontal face reference images was selected and manually annotated with multiple face and eye features. The eye-closure measurement system was developed using a top-down passive feature-detection approach, in which the face region of interest (fROI), eye regions of interests (eROIs), eyes, and eyelid positions were sequentially localized. The fROI was localized using an existing Haar-object detection algorithm. In addition, a Kalman filter was used to stabilize and track the fROI in the video. The left and the right eROIs were localized by scaling the fROI with corresponding proportional anthropometric constants. The position of an eye within each eROI was detected by applying a template-matching method in which a pre-formed eye-template image was cross-correlated with the sub-images derived from the eROI. Once the eye position was determined, the positions of the upper and lower eyelids were detected using a vertical integral-projection of the eROI. The detected positions of the eyelids were then used to measure eye closure. The detection of fROI and eROI was very reliable for frontal-face images, which was considered sufficient for an alertness monitoring system as subjects are most likely facing straight ahead when they are drowsy or about to have microsleep. Estimation of the y- coordinates of the eye, upper eyelid, and lower eyelid positions showed average median errors of 1.7, 1.4, and 2.1 pixels and average 90th percentile (worst-case) errors of 3.2, 2.7, and 6.9 pixels, respectively (1 pixel 1.3 mm in reference images). The average height of a fully open eye in the reference database was 14.2 pixels. The average median and 90th percentile errors of the eye and eyelid detection methods were reasonably low except for the 90th percentile error of the lower eyelid detection method. Poor estimation of the lower eyelid was the primary limitation for accurate eye-closure measurement. The median error of fractional eye-closure (EC) estimation (i.e., the ratio of closed portions of an eye to average height when the eye is fully open) was 0.15, which was sufficient to distinguish between the eyes being fully open, half closed, or fully closed. However, compounding errors in the facial-feature detection methods resulted in a 90th percentile EC estimation error of 0.42, which was too high to reliably determine extent of eye-closure. The eye-closure measurement system was relatively robust to variation in facial-features except for spectacles, for which reflections can saturate much of the eye-image. Therefore, in its current state, the eye-closure measurement system requires further development before it could be used with confidence for monitoring drowsiness and detecting microsleeps.

Human face recognition is an important area in the field of biometrics. It has been an active area of research for several decades, but still remains a challenging problem because of the complexity of the human face. In this thesis we describe fully automatic solutions that can locate faces and then perform identification and verification. We present a solution for face localisation using eye locations. We derive an efficient representation for the decision hyperplane of linear and nonlinear Support Vector Machines (SVMs). For this we introduce the novel concept of $\rho$ and $\eta$ prototypes. The standard formulation for the decision hyperplane is reformulated and expressed in terms of the two prototypes. Different kernels are treated separately to achieve further classification efficiency and to facilitate its adaptation to operate with the fast Fourier transform to achieve fast eye detection. Using the eye locations, we extract and normalise the face for size and in-plane rotations. Our method produces a more efficient representation of the SVM decision hyperplane than the well-known reduced set methods. As a result, our eye detection subsystem is faster and more accurate. The use of fractals and fractal image coding for object recognition has been proposed and used by others. Fractal codes have been used as features for recognition, but we need to take into account the distance between codes, and to ensure the continuity of the parameters of the code. We use a method based on fractal image coding for recognition, which we call the Fractal Neighbour Distance (FND). The FND relies on the Euclidean metric and the uniqueness of the attractor of a fractal code. An advantage of using the FND over fractal codes as features is that we do not have to worry about the uniqueness of, and distance between, codes. We only require the uniqueness of the attractor, which is already an implied property of a properly generated fractal code. Similar methods to the FND have been proposed by others, but what distinguishes our work from the rest is that we investigate the FND in greater detail and use our findings to improve the recognition rate. Our investigations reveal that the FND has some inherent invariance to translation, scale, rotation and changes to illumination. These invariances are image dependent and are affected by fractal encoding parameters. The parameters that have the greatest effect on recognition accuracy are the contrast scaling factor, luminance shift factor and the type of range block partitioning. The contrast scaling factor affect the convergence and eventual convergence rate of a fractal decoding process. We propose a novel method of controlling the convergence rate by altering the contrast scaling factor in a controlled manner, which has not been possible before. This helped us improve the recognition rate because under certain conditions better results are achievable from using a slower rate of convergence. We also investigate the effects of varying the luminance shift factor, and examine three different types of range block partitioning schemes. They are Quad-tree, HV and uniform partitioning. We performed experiments using various face datasets, and the results show that our method indeed performs better than many accepted methods such as eigenfaces. The experiments also show that the FND based classifier increases the separation between classes. The standard FND is further improved by incorporating the use of localised weights. A local search algorithm is introduced to find a best matching local feature using this locally weighted FND. The scores from a set of these locally weighted FND operations are then combined to obtain a global score, which is used as a measure of the similarity between two face images. Each local FND operation possesses the distortion invariant properties described above. Combined with the search procedure, the method has the potential to be invariant to a larger class of non-linear distortions. We also present a set of locally weighted FNDs that concentrate around the upper part of the face encompassing the eyes and nose. This design was motivated by the fact that the region around the eyes has more information for discrimination. Better performance is achieved by using different sets of weights for identification and verification. For facial verification, performance is further improved by using normalised scores and client specific thresholding. In this case, our results are competitive with current state-of-the-art methods, and in some cases outperform all those to which they were compared. For facial identification, under some conditions the weighted FND performs better than the standard FND. However, the weighted FND still has its short comings when some datasets are used, where its performance is not much better than the standard FND. To alleviate this problem we introduce a voting scheme that operates with normalised versions of the weighted FND. Although there are no improvements at lower matching ranks using this method, there are significant improvements for larger matching ranks. Our methods offer advantages over some well-accepted approaches such as eigenfaces, neural networks and those that use statistical learning theory. Some of the advantages are: new faces can be enrolled without re-training involving the whole database; faces can be removed from the database without the need for re-training; there are inherent invariances to face distortions; it is relatively simple to implement; and it is not model-based so there are no model parameters that need to be tweaked.

The project is focused on methods of obtaining large number of images of human faces. Such database should then serve as a set of data for face detection and recognition by the means of supervised machine learning. The work deals with the basic principles of supervised machine learning and available data sets for this procedure. Project contains proposals of techniques and implementation of algorithms suitable for acquiring images from video and a concept of user interface for semi-automatic acceptation and annotation of located images.

The thesis deals with eye blink detection, which is part of complex topic of face detection and recognition. The work intents on digital image processing. There is analyse of the topic and description of image databases for testing. Two main chapters describe design of eye blink detection with digital image processing with IR technology and without IR technology.