Please read the abstract in the section 00front of this document / Dissertation (MEng (Electronic Engineering))--University of Pretoria, 2006. / Electrical, Electronic and Computer Engineering / unrestricted

Please read the abstract in the section 00front of this document. / Dissertation (M Eng (Electronic Engineering))--University of Pretoria, 2006. / Electrical, Electronic and Computer Engineering / unrestricted

No description available.

As people across the globe are becoming more interested in watching their weight, eating more healthily, and avoiding obesity, a system that can measure calories and nutrition in everyday meals can be very useful. Recently, there has been an increase in the usage of personal mobile technology such as smartphones or tablets, which users carry with them practically all the time. In this paper, we proposed a food calorie and nutrition measurement system that can help patients and dieticians to measure and manage daily food intake. Our system is built on food image processing and uses nutritional fact tables. Via a special calibration technique, our system uses the built-in camera of such mobile devices and records a photo of the food before and after eating it in order to measure the consumption of calorie and nutrient components. The proposed algorithm used color, texture and contour segmentation and extracted important features such as shape, color, size and texture. Using various combinations of these features and applying a support vector machine as a classifier, a good classification was achieved and simulation results show that the algorithm recognizes food categories with an accuracy rate of 92.2%, on average.

In this thesis, we propose and present a multimodal interaction system that can provide a natural way for human-computer interaction. The core idea of this system is to help users to interact with the machine naturally by recognizing various gestures from the user from a wearable device. To achieve this goal, we have implemented a system including both hardware solution and gesture recognizing approaches. For the hardware solution, we designed and implemented a data glove based interaction device with multiple kinds of sensors to detect finger formations, touch commands and hand postures. We also modified and implemented two gesture recognizing approach based on support vector machine (SVM) as well as the lookup table. The detailed design and information is presented in this thesis. In the end, the system achieves supporting over 30 kinds of touch commands, 18 kinds of finger formation, and 10 kinds of hand postures as well as the combination of finger formation and hand posture with the recognition rate of 86.67% as well as the accurate touch command detection. We also evaluated the system from the subjective user experience.

This thesis presents a framework for automatic recognition of human actions in un- controlled, realistic video data with fixed cameras, such as surveillance videos. In this thesis, we divide human action recognition into three steps: description, representation, and classification of local spatio-temporal features. The bag-of-features model was used to build the classifier. Fisher Vectors were also studied. We focus on the potential of the methods, with the joint optimization of two constraints: the classification precision and its efficiency. On the performance side, a new local descriptor, called Gradient Boundary Histograms (GBH), is adopted. It is built on simple spatio-temporal gradients, which can be computed quickly. We demonstrate that GBH can better represent local structure and motion than other gradient-based descriptors, and significantly outperforms them on large datasets. Our evaluation shows that compared to HOG descriptors, which are based solely on spatial gradient, GBH descriptor preserves the recognition precision even in difficult situation. Since surveillance video captured with fixed cameras is the emphasis of our study, removing the background before action recognition is helpful for improving efficiency. We first preprocess the video data by applying HOG to detect humans. GBH descriptor is then used at reduced spatial resolutions, which yields both high efficiency and low memory usage; in addition, we apply PCA to reduce the feature dimensions, which results in fast matching and an accelerated classification process. Experiments our methods achieved good performance in recognizing precision, while simultaneously highlighting effectiveness and efficiency.

An optical character recognition system was developed using the Lexiphone, a direct-translation reading machine for the blind, interfaced to a digital computer. The system was designed to read alphanumeric typewritten characters. In the development stages one serifed type-style was used exclusively. Three additional different, but serifed, type-styles were also used. Classification was performed by a method referred to as "component deletion". This method extends a nearest neighbours classification scheme enabling feature vectors differing in length by one two-bit segment to be compared by making their dimensionality the same. The method includes the classification of equal length vectors. The component deletion technique provided similar results to exact matching yet required significantly less training. Using carbon ribbon print, recognition was better than 92% for the four type-styles combined. The use of cloth ribbon for the type-style used in the development lowered recognition by a few percent. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate

Paradoxical results on object-recognition delayed nonmatching-to-sample (DNMS) tasks have been found in monkeys and rats that receive either partial, ischemia-induced hippocampal lesions or complete hippocampal ablation. Ischemia results in severe DNMS impairments, which have been attributed to circumscribed CA1 cell loss. However, ablation studies indicate that the hippocampus plays only a minimal role in the performance of the DNMS task. Two hypotheses have been proposed to account for these discrepant findings (Bachevalier & Mishkin, 1989). First, the "hippocampal interference" hypothesis posits that following ischemia, the partially damaged hippocampus may disrupt activity in extrahippocampal structures that are important for object-recognition memory. Second, previously undetected ischemia-induced extrahippocampal damage may be responsible for the DNMS impairments attributed to CA1 cell loss. To test the "hippocampal interference" hypothesis, the effect of partial NMDAinduced lesions of the dorsal hippocampus were investigated on DNMS performance in rats. These lesions damaged much of the same area, the CA1, as did ischemia; but did so without depriving the entire forebrain of oxygen, thereby reducing the possibility of extrahippocampal damage. In Experiment 1, rats were trained on the DNMS task prior to receiving an NMDA-lesion. Postoperatively, these rats reacquired the nonmatching rule at a rate equivalent to controls and were unimpaired in performance at delays up to 300 s. In Experiment 2, naive rats were given NMDA-lesions and then trained on DNMS. These rats acquired the DNMS rule at a rate equivalent to controls and performed normally at delays up to 300 s. These findings suggest that interference from a partially damaged hippocampus cannot account for the ischemia-induced DNMS impairments and that they are more likely produced by extrahippocampal neuropathology. In Experiment 3, rats from the previous study were tested on the Morris water-maze. Compared to sham-lesioned animals, rats with partial lesions of the dorsal hippocampus were impaired in the acquisition of the water-maze task. Thus, subtotal NMDA-lesions of the hippocampus impaired spatial memory while leaving nonspatial memory intact. Mumby et al. (1992b) suggested that the ischemia-induced extrahippocampal damage underlying the DNMS deficits is mediated or produced by the postischemic hippocampus. To test this idea, preoperatively trained rats in Experiment 4 were subject to cerebral ischemia followed within 1hr by hippocampal aspiration lesions. It was hypothesized that ablation soon after ischemia would block the damage putatively produced by the postischemic hippocampus and thereby prevent the development of postoperative DNMS deficits. Unlike "ischemia-only" rats, the rats with the combined lesion were able to reacquire the nonmatching rule at a normal rate and performed normally at delays up to 300 s. Thus, hippocampectomy soon after ischemia eliminated the pathogenic process that lead to ischemia-induced DNMS deficits. Experiment 5 investigated the role of ischemiainduced CA1 cell death as a factor in the production of extrahippocampal neuropathology. Naive rats were given NMDA-lesions of the dorsal hippocampus followed 3 weeks later by cerebral ischemia. If the ischemia-induced CA1 neurotoxicity is responsible for producing extrahippocampal damage then preischemic ablation should attenuate this process and prevent the development of DNMS impairments. This did not occur: Rats with the combined lesion were as impaired as the "ischemia-only" rats in the acquisition of the DNMS task. This suggests that the ischemia-induced pathogenic processes that result in extrahippocampal neuropathology comprise more than CA1 neurotoxicity. The findings presented in this thesis are consistent with the idea that ischemiainduced DNMS deficits in rats are the result of extrahippocampal damage mediated or produced by the postischemic hippocampus. The discussion focuses on three main points: 1) How might the post-ischemic hippocampus be involved in the production of extrahippocampal neuropathology? 2) In what brain region(s) might this damage be occurring? 3) What anatomical, molecular, or functional neuropathology might ischemia produce in extrahippocampal brain regions? The results are also discussed in terms of a specialized role for the hippocampus in mnemonic functions and the recently emphasized importance of the rhinal cortex in object-recognition memory. / Arts, Faculty of / Psychology, Department of / Graduate

No description available.

No description available.