The work of this thesis is motivated by the bene t of real-time HDR image processing which helps constructing better seeing aid devices for day-to-day uses. The seeing aids with HDR can achieve dynamic range greater than human eyes to capture visuals under various light conditions. Further, it helps range sensing devices to read the light codes better. This requires realtime HDR image processing running at 24 FPS. In this thesis, we demonstrate implementation of several HDR image compositing and tone mapping methods in CUDA to achieve realtime performance. In addition, a new tone mapping method termed PPEM is introduced as a novel tone mapping method by adjusting per pixel exposure. Finally, we apply relevant HDR methods to range sensing devices for robust reading.

The human vestibulo-ocular reflex (VOR) is known to undergo major plastic modification in coping with sensory conflict brought about by optical reversing prisms. The first phase of this study proposes a simple model to account for this modifiability in terms of known neurophysiology. To study the phenomenon further two series of experiments were conducted on long-term vision-reversed cats. For this a new computer technique was developed to analyse oculomotor responses. The first series studied the time course and amplitude dependence of adaptation; the second, the frequency response of the fully adapted system. The adaptive process exhibited strict limitations, the functional effectiveness of which is quantitatively defined. The findings as a whole suggest that adaptive mechanisms other than the VOR are at play and that far more complex interactions exist between vestibulo- and visual-motor mechanisms than originally envisaged.

La recherche présentée dans cette thèse est divisée en trois parties. Notre objectif dans la première partie est l’amélioration de la compression de l’image par stéganographie. Dans cette étude, la compression de données est effectuée en deux étapes. Tout d’abord, nous profitons du compactage d’énergie en utilisant JPEG pour réduire les données redondantes. Ensuite, nous intégrons des blocs de bits dans les blocs suivants de la même image stéganographie. Les bits intégrés servent à non seulement augmenter la taille du fichier de l’image compressée, mais aussi à diminuer davantage la taille du fichier. Les résultats expérimentaux montrent que notre méthode donne de meilleurs taux de compression tout en conservant une haute qualité de l’image. Le deuxième sujet de cette thèse propose un formalisme bayésien pour la stéganalyse d’image numérique qui permet la détection d’images stego, l’identification de l’algorithme de stéganographie utilisé, l’estimation de la longueur du message et l’emplacement, et l’anticipation dans le cas de l’intégration en utilisant un algorithme de stéganographie inconnu. La détection, l’identification et l’anticipation impliquent l’apprentissage discriminant dans l’espace des fonctions. L’estimation nécessite la fusion de classificateurs permettant la discrimination entre les sous-images et une intégration entière des couvertures de tailles différentes. La validation sur des images JPEG montre que le système proposé est efficace et permet d’anticiper des algorithmes de stéganographie inconnus. Le troisième sujet de la thèse décrit une méthode d’estimation du regard de l’oeil humain pendant un mouvement normal de la tête. Dans ce procédé, la position et l’orientation de la tête sont acquises par des données de profondeur fournies par Kinect. La direction de l’oeil est obtenue à partir d’images à haute résolution. Nous nous proposons la régression logistique multinomiale pour construire une fonction de mappage du regard et de vérifier l’état de l’iris. L’efficacité de la méthode proposée est validée par une évaluation de la performance pour plusieurs personnes avec différentes distances et poses par rapport à la caméra et dans différents états de l’oeil.

No description available.

The present study tested the hypothesis that distractor-based facilitation of visual search occurs because familiar distractors are processed and rejected in groups. We recorded participants’ eye movements during a visual search task to determine if familiar distractors were associated with an increased average distance between fixations and distractors. The study provided convergent evidence of a strong relation between search efficiency and distractor familiarity, wherein the distance between fixations and distractors increases with the efficiency of search. Further examination of eye movements suggested that the grouping of familiar distractors resulted in an efficient scanning of the search display by increasing the area of the display effectively processed during each fixation and therefore reducing the need to fixate individual distractors.

Previous works suggest that North Americans perceive visual information more analytically while East Asians perceive visual information more holistically. However, salient objects are also known to naturally attract human attention. Current studies examined to what extent culture influences visual attention. Study 1 demonstrated that highly salient objects attract passive viewers attention similarly across North American and East Asian cultures. In study 2, however, we revealed that such strong tendency for humans can be influenced by culture when people actively engaged in the observation. When participants were asked to report their observation, Canadian participants predominantly reported information regarding focal objects whereas Japanese participants also reported much information regarding contextual features. Consistently, culturally divergent patterns of eye movements were observed. The current study thus indicates that the active involvement in observation is especially important to understand the influence of culture on visual attention.

The ability of the human eye to change its overall refractive power so that people can focus on objects both far and near is termed accommodation. Research into how the eye automatically changes its accommodation, demands an instrument capable of tracking the accommodation with fine resolution and adequate corner frequency. An instrument capable of tracking the ocular accommodation is called an optometer. Reports of earlier optometers show that optometers using the older Scheiner principlecan have the required precision and dynamics required to track the micro fluctuations accommodation. However optometers using the Scheiner principle require precise alignment to the patient’s pupil to be maintained throughout the measurement time. Previous optometers have used the radiation reflected from the patient’s cornea (calledthe corneal reflection) to initially align the optical axis of the optometer to the centre of the patient’s pupil. Since the Scheiner principle optometer uses radiant energy reflected from the patient’s retina to make a refractive measurement, the idea of using this same radiant energy for patient alignment is investigated. Earlier optometers have blocked the corneal reflection from reaching the photodetectors for the retinal reflection using a small fixed light stop. Since it is not possible to use a fixed light stop if the retinal reflection is used for alignment, the feasibility of using crossed linear polarizers is experimentally evaluated. The results showed that about78% of the radiant energy reflected from the front lens of an artificial eye could be eliminated using crossed linear polarizers. Whether the Scheiner principle measurement of refraction of an artificial eye could be done with 78% of the front lens (corneal) reflection removed was investigated. The results were not conclusive. There was not a measureable indication of when the refraction of the experimental optometer matched that of the artificial eye. The experimental optometer system attempts to use a servo controlled mirror system to move the optical axis of the optometer so that it coincides with the optical axis of an artificial eye. The design, development and testing of the mirror system is described. The mirror system enables the optometer to perform a two dimensional scan over the pupil plane of the patient’s eye or an artificial eye. During the scanning, the total radiant power reflected can be measured. For the optometer to be aligned using radiation reflected from the retina, a scan of the pupil plane of should reveal the pupil boundaries. This was experimentally demonstrated to work. Unfortunately time limitations did not permit further development of an automatic eye alignment and tracking system.

The ability of the human eye to change its overall refractive power so that people can focus on objects both far and near is termed accommodation. Research into how the eye automatically changes its accommodation, demands an instrument capable of tracking the accommodation with fine resolution and adequate corner frequency. An instrument capable of tracking the ocular accommodation is called an optometer. Reports of earlier optometers show that optometers using the older Scheiner principlecan have the required precision and dynamics required to track the micro fluctuations accommodation. However optometers using the Scheiner principle require precise alignment to the patient’s pupil to be maintained throughout the measurement time. Previous optometers have used the radiation reflected from the patient’s cornea (calledthe corneal reflection) to initially align the optical axis of the optometer to the centre of the patient’s pupil. Since the Scheiner principle optometer uses radiant energy reflected from the patient’s retina to make a refractive measurement, the idea of using this same radiant energy for patient alignment is investigated. Earlier optometers have blocked the corneal reflection from reaching the photodetectors for the retinal reflection using a small fixed light stop. Since it is not possible to use a fixed light stop if the retinal reflection is used for alignment, the feasibility of using crossed linear polarizers is experimentally evaluated. The results showed that about78% of the radiant energy reflected from the front lens of an artificial eye could be eliminated using crossed linear polarizers. Whether the Scheiner principle measurement of refraction of an artificial eye could be done with 78% of the front lens (corneal) reflection removed was investigated. The results were not conclusive. There was not a measureable indication of when the refraction of the experimental optometer matched that of the artificial eye. The experimental optometer system attempts to use a servo controlled mirror system to move the optical axis of the optometer so that it coincides with the optical axis of an artificial eye. The design, development and testing of the mirror system is described. The mirror system enables the optometer to perform a two dimensional scan over the pupil plane of the patient’s eye or an artificial eye. During the scanning, the total radiant power reflected can be measured. For the optometer to be aligned using radiation reflected from the retina, a scan of the pupil plane of should reveal the pupil boundaries. This was experimentally demonstrated to work. Unfortunately time limitations did not permit further development of an automatic eye alignment and tracking system.

Many studies have found evidence of abnormal eye movement control in Parkinson's disease. Deficits in the inhibition of unintended saccades and slowed initiation of intentional saccades have been reported in some, but not all, investigations. Also over recent years the presence of cognitive impairment in a proportion of patients with Parkinson's disease has been highlighted. Efficient use of working memory resources is thought to be involved in the performance of tasks in both domains. With a comprehensive selection of saccadic and neuropsychological tasks, the current study investigated whether aspects of abnormal oculomotor control are associated with impairment of cognitive functions. Nineteen Parkinson's disease patients and eighteen healthy age matched control subjects performed six eye movement tasks and completed a neuropsychological test battery assessing five different aspects of cognitive functioning. Deficits were found in both the oculomotor and the cognitive domain in the group of patients. As a group, the patients made more reflexive errors in antisaccade tasks, more inhibition errors in a delayed response task, and were slower to initiate intentional saccades. The three measures of abnormal oculomotor control were not consistently associated with cognitive impairments or with each other. Longer latencies of correct antisaccades and increased number of errors in a delayed response task were associated with lower scores in different cognitive tests. Reflexive errors in the antisaccade task were not associated with cognitive deficits, but with the tendency to produce very fast visually triggered responses. The results suggest that, at least in Parkinson's disease, different neural mechanisms may be involved in specific aspects of abnormal oculomotor control.

Part of the aim of this thesis was to explore a model for producing very fast saccade latencies in the 80 to 120ms range. Its primary motivation was to explore a possible interaction by uniquely combining three independent saccade factors: the gap effect, target-feature-discrimination, and saccadic inhibition of return (IOR). Its secondary motivation was to replicate (in a more conservative and tightly controlled design) the surprising findings of Trottier and Pratt (2005), who found that requiring a high resolution task at the saccade target location speeded saccades, apparently by disinhibition. Trottier and Pratt’s finding was so surprising it raised the question: Could the oculomotor braking effect of saccadic IOR to previously viewed locations be reduced or removed by requiring a high resolution task at the target location? Twenty naïve untrained undergraduate students participated in exchange for course credit. Multiple randomised temporal and spatial target parameters were introduced in order to increase probability of exogenous responses. The primary measured variable was saccade latency in milliseconds, with the expectation of higher probability of very fast saccades (i.e. 80-120ms). Previous research suggested that these very fast saccades could be elicited in special testing circumstances with naïve participants, such as during the gap task, or in highly trained observers in non-gap tasks (Fischer & Weber, 1993). Trottier and Pratt (2005) found that adding a task demand that required naïve untrained participants to obtain a feature of the target stimulus (and to then make a discriminatory decision) also produced a higher probability of very fast saccade latencies. They stated that these saccades were not the same as saccade latencies previously referred to as express saccades produced in the gap paradigm, and proposed that such very fast saccades were normal. Carpenter (2001) found that in trained participants the probability of finding very fast saccades during the gap task increased when the horizontal direction of the current saccade continued in the same direction as the previous saccade (as opposed to reversing direction) – giving a distinct bimodality in the distribution of latencies in five out of seven participants, and likened his findings to the well known IOR effect. The IOR effect has previously been found in both manual key-press RT and saccadic latency paradigms. Hunt and Kingstone (2003) stated that there were both cortical top-down and oculomotor hard-wired aspects to IOR. An experiment was designed that included obtain-target-feature and oculomotor-prior-direction, crossed with two gap level offsets (0ms & 200ms-gap). Target-feature discrimination accuracy was high (97%). Under-additive main effects were found for each factor, with a three-way interaction effect for gap by obtain-feature by oculomotor-prior-direction. Another new three-way interaction was also found for anticipatory saccade type. Anticipatory saccades became significantly more likely under obtain-target-feature for the continuing oculomotor direction. This appears to be a similar effect to the increased anticipatory direction-error rate in the antisaccade task. These findings add to the saccadic latency knowledge base and in agreement with both Carpenter and Trottier and Pratt, laboratory testing paradigms can affect saccadic latency distributions. That is, salient (meaningful) targets that follow more natural oculomotor trajectories produce higher probability of very fast latencies in the 80-120ms range. In agreement with Hunt and Kingstone, there appears to be an oculomotor component to IOR. Specifically, saccadic target-prior-location interacts differently for obtain-target-feature under 200-ms gap than under 0ms-gap, and is most likely due predominantly to a predictive disinhibitory oculomotor momentum effect, rather than being due to the attentional inhibitory effect proposed for key-press IOR. A new interpretation for the paradigm previously referred to as IOR is offered that includes a link to the smooth pursuit system. Additional studies are planned to explore saccadic interactions in more detail.