Thesis (Ph.D.) - University of Queensland, 2005. / Includes bibliography.

Thesis (M.S.)--West Virginia University, 2005. / Title from document title page. Document formatted into pages; contains vii, 57 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 53-57).

Thesis (Ph. D.)--Lehigh University, 2006. / Includes vita. Includes bibliographical references (leaves 175-189).

Localized operators, like Gabor wavelets and difference-of-Gaussian filters, are considered to be useful tools for image representation. This is due to their ability to form a ‘sparse code’ that can serve as a basis set for high-fidelity reconstruction of natural images. However, for many visual tasks, the more appropriate criterion of representational efficacy is ‘recognition’, rather than ‘reconstruction’. It is unclear whether simple local features provide the stability necessary to subserve robust recognition of complex objects. In this paper, we search the space of two-lobed differential operators for those that constitute a good representational code under recognition/discrimination criteria. We find that a novel operator, which we call the ‘dissociated dipole’ displays useful properties in this regard. We describe simple computational experiments to assess the merits of such dipoles relative to the more traditional local operators. The results suggest that non-local operators constitute a vocabulary that is stable across a range of image transformations.

Animals are sentient beings, capable of experiencing emotions. Being able to assess emotional states in farm animals is crucial to improving their welfare. Although the function of emotion is not primarily for communication, the outward expression of an emotional state involves changes in posture, vocalisations, odours and facial expressions. These changes can be perceived and used as indicators of emotional state by other animals. Since emotions can be perceived between conspecifics, understanding how emotions are identified and how they can spread within a social group could have a major impact on improving the welfare of farmed species, which are mostly reared in groups. A recently developed method for the evaluation of emotions in animals is based on cognitive biases such as judgment biases, i.e. an individual in a negative emotional state will show pessimistic judgments while and individual in a positive emotional state will show optimistic judgments. The aims of this project were to (A) establish whether sheep and goats can discriminate between images of faces of familiar conspecifics taken in different positive and negative situations, (B) establish whether sheep and goats perceive the valence (positive of negative) of the emotion expressed by the animal on the image, (C) validate the use of images of faces in cognitive bias studies. The use of images of faces of conspecifics as emotional stimuli was first validated, using a discrimination task in a two-armed maze. A new methodology was then developed across a series of experiments to assess spontaneous reactions of animals exposed to video clips or to images of faces of familiar conspecifics. Detailed observations of ear postures were used as the main behavioural indicator. Individual characteristics (dominance status within the herd, dominance pairwise relationships and humananimal relationship) were also recorded during preliminary tests and included in the analyses. The impact of a low-mood state on the perception of emotions was assessed in sheep after subjecting half of the animals to unpredictable negative housing conditions and keeping the other half in good standard housing conditions. Sheep were then presented with videos of conspecifics filmed in situations of varying valence. Reactions to ambiguous stimuli were evaluated by presenting goats with images of morphed faces. Goats were also presented with images of faces of familiar conspecifics taken situations of varying emotional intensity. Sheep could discriminate images of faces of conspecifics taken either in a negative or in a neutral situation and their learning process of the discrimination task was affected by the type of emotion displayed. Sheep reacted differently depending on the valence of the video clips (P < 0.05); however, there was no difference between the control and the low-mood groups (P > 0.05). Goats also showed different behavioural reactions to images of faces photographed in different situations (P < 0.05), indicating that they perceived the images as different. Responses to morphed images were not necessarily intermediate to responses to negative and positive images and not gradual either, which poses a major problem to the potential use of facial images in cognitive bias experiments. Overall, animals were more attentive towards images or videos of conspecifics in negative situations, i.e., presumably, in a negative emotional state. This suggests that sheep and goats are able to perceive the valence of the emotional state. The identity of the individual on the photo also affected the animals’ spontaneous reaction to the images. Social relationships such as dominance, but also affinity between the tested and photographed individual seem to influence emotion perception.

No description available.

Magister Scientiae - MSc / This thesis addresses analysis, evaluation and simulation of low complexity face detection algorithms and tracking that could be used on mobile phones. Network access control using face recognition increases the user-friendliness in human-computer interaction. In order to realize a real time system implemented on handheld devices with low computing power, low complexity algorithms for face detection and face tracking are implemented. Skin color detection algorithms and face matching have low implementation complexity suitable for authentication of cellular network services. Novel approaches for reducing the complexities of these algorithms and fast implementation are introduced in this thesis. This includes a fast algorithm for face detection in video sequences, using a skin color model in the HSV (Hue-Saturation-Value) color space. It is combined with a Gaussian model of the H and S statistics and adaptive thresholds. These algorithms permit segmentation and detection of multiple faces in thumbnail images. Furthermore we evaluate and compare our results with those of a method implemented in the Chromatic Color space (YCbCr). We also test our test data on face detection method using Convolutional Neural Network architecture to study the suitability of using other approaches besides skin color as the basic feature for face detection. Finally, face tracking is done in 2D color video streams using HSV as the histogram color space. The program is used to compute 3D trajectories for a remote surveillance system. / South Africa

No description available.

This dissertation reports the development of a technique for automated face recognition, using color images. One of the more powerful techniques for recognition of faces in monochromatic images has been extended to color by the use of hypercomplex numbers called quaternions. Two software implementations have been written of the new method and the analogous method for use on monochromatic images. Test results show that the new method is superior in accuracy to the analogous monochrome method. Although color images are generally collected, the great majority of published research efforts and of commercially available systems use only the intensity features. This surprising fact provided motivation to the three thesis statements proposed in this dissertation. The first is that the use of color information can increase face recognition accuracy. Face images contain many features, some of which are only easily distinguishable using color while others would seem more robust to illumination variation when color is considered. The second thesis statement is that the currently popular technique of graph-based face analysis and matching of features extracted from application of a family of Gabor filters can be extended to use with color. A particular method of defining a filter appropriate for color images is used; the usual complex Gabor filter is adapted to the domain of quaternions.. Four alternative approaches to the extension of complex Gabor filters to quaternions are defined and discussed; the most promising is selected and used as the basis for subsequent implementation and experimentation. The third thesis statement is that statistical analysis can identify portions of the face image that are highly relevant — i.e., locations that are especially well suited for use in face recognition systems. Conventionally, the Gabor-based graph method extracts features at locations that are equally spaced, or perhaps selected manually on a non-uniform graph. We have defined a relevance image, in which the intensity values are computed from the intensity variance across a number of images from different individuals and the mutual information between the pixel distributions of sets of images from different individuals and the same individual. A complete software implementation of the new face recognition method has been developed. Feature vectors called jets are extracted by application of the novel quaternion Gabor filter, and matched against models of other faces. In order to test the validity of the thesis statements, a parallel software implementation of the conventional monochromatic Gabor graph method has been developed and side-by-side testing has been conducted. Testing results show accuracy increases of 3% to 17% in the new color-based method over the conventional monochromatic method. These testing results demonstrate that color information can indeed provide a significant increase in accuracy, that the extension of Gabor filters to color through the use of quaternions does give a viable feature set, and that the face landmarks chosen via statistical methods do have high relevance for face discrimination. / Ph. D.

Automatic face recognition has attracted the attention of many research institutes, commercial industries, and government agencies in the past few years mainly due to the emergence of numerous applications, such as surveillance, access control to secure facilities, and airport screening. Almost all of the research on the early days of face recognition was focused on using 2-D (intensity/portrait) images of the face. While several sophisticated 2-D solutions have been proposed, unbiased evaluation studies show that their collective performance remains unsatisfactory, and degrades significantly with variations in lighting condition, face position, makeup, or existence of non-neutral facial expressions. Recent developments in 3-D imaging technology has made cheaper, quicker and more reliable acquisition of 3-D facial models a reality. These 3-D facial models contain information about the anatomical structure of the face that remains constant under variable lighting conditions, facial makeup, and pose variations. Thus, researchers are considering to utilize 3-D structure of the face alone or in combination with 2-D information to alleviate inherent limitations of 2-D images and attain better performance. Published 3-D face recognition algorithms have demonstrated promising results confirming the effectiveness of 3-D facial models in dealing with the above mentioned factors contributing to the failure of 2-D face recognition systems. However, the majority of these 3-D algorithms are extensions of conventional 2-D approaches, where intensity images are simply replaced by 3-D models rendered as range images. These algorithms are not specifically tailored to exploit abundant geometric and anthropometric clues available in 3-D facial models. In this dissertation we introduce innovative 3-D and 2-D+3-D facial measurements (features) that effectively describe the geometric characteristics of the corresponding faces. Some of the features described in this dissertation, as well as many features proposed in the literature are defined around or between meaningful facial landmarks (fiducial points). In order to reach our goal of designing an accurate automatic face recognition system, we also propose a novel algorithm combining 3-D (range) and 2-D (portrait) Gabor clues to pinpoint a number of points with meaningful anthropometric definitions with significantly better accuracies than those achievable using a single modality alone. This dissertation is organized as follows. In Chapter 1, various biometric modalities are introduced and the advantages of the facial biometrics over other modalities are discussed. The discussion in Chapter 1 is continued with introduction of the face recognition’s modes of operation followed by some current and potential future applications. The problem statement of this dissertation is also included in this chapter. In Chapter 2, an extensive review of the successful 2-D, 3-D, and 2-D+3-D face recognition algorithms are provided. Chapter 3 presents the details of our innovative 3-D and 2-D+3-D face features, as well as our accurate fiducial point detection algorithm. Conclusions and directions for future extensions are presented in Chapter 4. / text