Made available in DSpace on 2015-04-11T14:02:51Z (GMT). No. of bitstreams: 1 joyce.pdf: 2848954 bytes, checksum: 2975e0e84f1ae7a53273f20004ce6c78 (MD5) Previous issue date: 2013-03-12 / With the fast development of the Internet and the popularization of mobile devices, searching for a specific product in e-commerce Web sites through a query image has become a very promising area of research. In this context, CBIR (Content-Based Image Retrieval) techniques have been exploited to support and improve the shopping experience of consumers. In this dissertation, we address the problem of product visual search using an image as a query, instead of the more popular approach of search based on keywords. We propose a strategy for re-ranking based on multimedia information usually available in database of products. Our strategy makes use of category information and textual description associated with the top-k images of an initial ranking generated by CBIR techniques only. Experiments were performed considering the judgment of users on two collections of images collected from popular e-commerce Web sites. Our results show that our strategy achieves significant gains compared to an approach based only on CBIR techniques. / Com o rápido desenvolvimento da Internet, a popularização de dispositivos móveis e de sites de comércio eletrônico, procurar um produto específico a partir de uma imagem tem se tornado uma área de pesquisa promissora. Nesse contexto, técnicas de CBIR (Content-Based Image Retrieval) vêm sendo exploradas para apoiar e melhorar a experiência de compra dos consumidores. Neste trabalho, abordamos o problema de busca visual de produtos usando uma imagem como consulta, no lugar da mais popular abordagem de busca que é baseada em palavras-chave. Nós propomos uma estratégia de re-ranking que faz uso de informações multimídia normalmente disponíveis nas bases de dados de produtos. Nossa estratégia faz uso de informações de categoria e descrição textual associadas às imagens melhor posicionadas de um ranking inicial gerado por técnicas puramente de CBIR. Experimentos foram realizados considerando o julgamento de usuários em duas coleções de imagens coletadas a partir de sites de comércio eletrônico. Nossos resultados mostram que nossa estratégia alcança ganhos significativos quando comparada à busca puramente visual.

The ability to locate symbols on a visual display forms an integral part of the effective use of AAC systems. Characteristics of display design and perceptual features of symbols have been shown to influence rate and accuracy of symbol location (Thistle&Wilkinson, 2009; Wilkinson, Carlin,&Jagaroo, 2006). The current study endeavoured to compare the use of two colour-coded organisational strategies (alphabetical order and categorisation) for their effectiveness in symbol location and to investigate if some bottom-up features influenced the performance of the participants in these tasks. 114 learners in Grade 1 to 3 in a mainstream school were randomly divided into two groups. Both of the groups were exposed to two visual search tests in alternating order. The tests involved searching for 36 visual targets amongst 81 coloured Picture Communication Symbols on a computer screen in one of two colour-coded organizational methods, namely alphabetical order or categorisation. The data from the research task was collected through computer logging of all mouse selections. Findings showed that locating symbols on a computer screen with a categorisation strategy was significantly faster and more accurate than with an alphabetical strategy for the Grade 1 to 3 participants. The rate and accuracy of target symbol location in both the strategies decreased significantly as grade increased, as did the differences between rate and accuracy of target location when using the two strategies. It was also found that although the tests in this study placed heavy top-down processing demands on the participants, there was still evidence of bottom-up factors influencing their performance. Implications for display design in AAC clinical practice were discussed. / Thesis (PhD)--University of Pretoria, 2012. / Centre for Augmentative and Alternative Communication / unrestricted

Online shopping has become an important part of people’s daily life with the rapid development of e-commerce. In some domains such as books, electronics, and CD/DVDs, online shopping has surpassed or even replaced the traditional shopping method. Compared with traditional retailing, e-commerce is information intensive. One of the key factors to succeed in e-business is how to facilitate the consumers’ approaches to discover a product. Conventionally a product search engine based on a keyword search or category browser is provided to help users find the product information they need. The general goal of a product search system is to enable users to quickly locate information of interest and to minimize users’ efforts in search and navigation. In this process human factors play a significant role. Finding product information could be a tricky task and may require an intelligent use of search engines, and a non-trivial navigation of multilayer categories. Searching for useful product information can be frustrating for many users, especially those inexperienced users. This dissertation focuses on developing a new visual product search system that effectively extracts the properties of unstructured products, and presents the possible items of attraction to users so that the users can quickly locate the ones they would be most likely interested in. We designed and developed a feature extraction algorithm that retains product color and local pattern features, and the experimental evaluation on the benchmark dataset demonstrated that it is robust against common geometric and photometric visual distortions. Besides, instead of ignoring product text information, we investigated and developed a ranking model learned via a unified probabilistic hypergraph that is capable of capturing correlations among product visual content and textual content. Moreover, we proposed and designed a fuzzy hierarchical co-clustering algorithm for the collaborative filtering product recommendation. Via this method, users can be automatically grouped into different interest communities based on their behaviors. Then, a customized recommendation can be performed according to these implicitly detected relations. In summary, the developed search system performs much better in a visual unstructured product search when compared with state-of-art approaches. With the comprehensive ranking scheme and the collaborative filtering recommendation module, the user’s overhead in locating the information of value is reduced, and the user’s experience of seeking for useful product information is optimized.

Visual conditions such as retinitis pigmentosa and Usher syndrome can gradually cause tunnel vision. Patients with these conditions usually face difficulties with navigation, avoiding obstacles, and performing visual search. Loss of mobility can affect patients' independence and quality of life. One of the rehabilitation strategies for patients with tunnel vision is the use of optical aids to enhance mobility performance. The main method used to evaluate the usefulness of optical aids is the patient’s subjective report after extended wear. In order to evaluate optical aid effectiveness in the clinic, a new test based on the visual search paradigm was designed to assess the patient's visual awareness. This was named the assessment of visual awareness (AVA) test. The main aim of this study was to develop the AVA test, establish its sensitivity, validity and repeatability, and then use it to investigate the efficacy of optical aids in this group of people. The AVA test consists of 32 peripheral targets presented at four different locations: 1st annulus (at 5° from the central fixation), 2nd annulus (10°), 3rd annulus (20°) and 4th annulus (30°)). In this study, the peripheral targets were presented singly against a spatial noise background in a presentation area of 81° H × 62° V. Participants were allowed to use head and eye movements and were asked to search for and locate each target. The detection time (DT) was recorded. A new, sensitive and easy to set up indoor mobility course was also designed and validated prior to its use in validating the AVA test. A total of 50 normally sighted participants with simulated tunnel vision (TV) (5° to 20°, in 5° steps) and 20 patients with TV (retained field 4° to 21°) were tested. The AVA test was found to be responsive to the change in field of view (FoV) and to the target locations in both groups of participants. In the simulated group, a significant relationship was found between FoV and DT at each annulus (r ranging from -0.55 to -0.77, p < 0.0001). A significant relationship was found between target location and DT within each FoV size (20°, 15°, 10° and 5°) (r ranging from 0.53 to 0.84, p < 0.0001). In the TV patients, a statistically significant relationship was found between FoV and DT at each annulus (r range from -0.40 to -0.60, p < 0.05). The target location was shown to have a significant relationship with the DT within each FoV size (r ranging from 0.50 to 0.60, p < 0.05). Finally, the AVA test was found to be significantly related to the simulated TV participants' performance on the indoor mobility course. The AVA test was used to assess the efficacy of three optical aids: the partial aperture prism (10 patients), the Tri-field prism (10 patients) and the reverse telescope (4 patients). The AVA test showed no significant improvement in DT with either of the prisms and the participants did not find these aids helpful. DT with the reverse telescope improved, but none of the participants were willing to use these on extended trial. The AVA test gave clear indications of the efficacy of each aid, a result which could affirm the importance of the AVA test. In conclusion, the AVA test was found to be sensitive, valid and repeatable. DT did not improve in either of the optical aids which were found to be unsuccessful, suggesting that the AVA could be a promising clinical test. However the aids which showed improved DT were not evaluated over the longer term, and therefore did not allow full evaluation of the AVA test.

Enrollment in post-secondary education for individuals with autism spectrum disorder (ASD) is increasing; however, students with ASD are less likely to complete a degree than students with other disabilities. Classroom performance requires attending to course-related information while filtering distractions. These attentional functions are critical for academic achievement. However, ASD is associated with pervasive impairments in attentional filtering. The present study used visual search, a task in which individuals with ASD excel, to investigate filtering of irrelevant social and non-social auditory information in college students with and without ASD. Results of the present study suggest a filtering deficit for individuals with ASD and indicate that this filtering impairment is present for both social and non-social information. Importantly, these deficits are present on a task in which individuals with ASD excel. Our findings suggest that irrelevant social and non-social sounds may adversely affect performance in college-aged students with high-functioning ASD and highlight the importance of minimizing competing background noise for these students.

Semi-automated processes are becoming more common within the field of waste management. They are often more efficient and improves the waste operators’ work environment in terms of security and health factors. The French company Veolia, engaged in waste management, has for these reasons developed the Tri Télé-Opéré (TTO) - a system where the direct contact between operator and waste is removed, and the waste is separated via a touch screen. The waste line is currently shown with a series of images in the system. This explorative study investigated how a representation of the line was perceived when using dynamic images on the screen. Diverse sequences with various parameters (viewpoint, direction and pace) were studied in order to observe how they supported the recognition and designation of the operators working with the system. Qualitative results from user tests performed with both novices and waste operators identified parameters that should be considered when using dynamic images of the waste line. The study shows that assembled images captured with an angle of 90°, shown in a slideshow mode are preferred. The viewpoint should furthermore be clear and detailed and the information should be displayed in a direction that corresponds to the long side of the screen, while having a size that make use of the screen surface. Moreover, the results suggest that the pace of the waste line could be increased if parameters allowing good recognition are used simultaneously. This study provides a first insight in how users perceive the TTO with dynamic images and which parameters that could facilitate the work. It is furthermore believed that a further development of this representation of information could ameliorate the future work situation for the waste operators, and thus also the efficiency of the sorting process. / Halvautomatiserade processer blir allt vanligare inom området avfallshantering. Det är ofta mer effektiva och förbättrar avfallsoperatörernas arbetsmiljö när det kommer till säkerhet- och hälsoaspekter. Det franska företaget Veolia, som arbetar med insamling och hantering av avfall, har på grund utav detta utvecklat Tri Télé-Opéré (TTO) – ett system där direktkontakten mellan sorterare och avfall har avlägsnats och avfallet istället sorteras via en pekskärm. Systemet visar för tillfället upp avfallslinan med en serie stillbilder. Denna explorativa studie har undersökt hur linan uppfattades med dynamiska bilder på skärmen. Diverse sekvenser med olika parametrar (synvinkel, riktning och hastighet) studerades för att se hur de stödde avfallsoperatörernas igenkänning och klassificering i sorteringen vid skärmen. Kvalitativa resultat från användartest utförda med både nybörjare och avfallsoperatörer identifierade parametrar som bör beaktas när en presentation av avfallslinan med dynamiska bilder används. Studien visar att ett bildspel bestående av bilder tagna med en 90° vinkel föredrogs. Synvinkeln bör vara tydlig och informationen bör visas i en riktning som överensstämmer med skärmens långsida, samt ha en storlek som tar vara på bildskärmens yta. Hastigheten på avfallslinan kan ökas om parametrar som möjliggör ett bra igenkännande används simultant. Denna studie ger en första inblick i hur användarna upplever TTO med dynamiska bilder, och vilka parametrar som skulle kunna underlätta arbetet. En vidareutveckling av denna informationspresentation kan förbättra den framtida arbetssituationen för avfallsoperatörer, och därmed också effektiviteten i sorteringsprocessen.

The study of cognition as it relates to expert performance in sport is an area that has received increased attention over the last 25 years. This has been made possible by the fact that the domain of sport offers a rich and diverse setting in which to study cognition and its links to human performance, coupled with the abundant supply of highly practiced athletes providing unique opportunities to study these factors in a natural environment. The quality of on-field decision-making of expert athletes has received attention in a number of open-skill sporting codes, including basketball, field hockey and soccer. Decision-making quality of expert athletes in rugby union, as an invasive, open-skill sporting code, has not received the same amount of attention. Past studies on the decision-making of expert athletes in sport have tended to be carried through the isolation of specific cognitive functions and describing the role of each isolated function in the decision-making process. Given the speed at which decisions have to be made, as a result of time pressure, the isolation of cognitive functions yields valuable insights into the decision-making processes of expert athletes in competitive, on-field situations. While these cognitive functions can be studied in isolation, they do however form part of a bigger process that enables the expert athlete to make high quality on-field decisions. It is for this reason that it was decided to study these different functions in combination, as set out by the Information Processing Approach to cognitive functioning. According to this approach, the decision-making process consists on three main phases, namely that of Visual Search Strategies, Anticipation and Response Selection. This study was aimed at examining the quality of on-field decision-making of expert rugby players, as well as the influence of the competitive level at which rugby is played on decision-making quality. In order to achieve this goal it was necessary to develop a measurement instrument that can be used by expert rugby players to assess the quality of decisions made on the field of play. As it is difficult for outside observers to establish what players are thinking or focusing their attention on when making decisions on the field, it was necessary to design the instrument as a self-report measure of decision-making. By being made aware of one’s strong and weak points in on-field decision-making, expert rugby players can focus their attention on improving the underdeveloped facets of their game. The measurement of decision-making according to three distinct phases allows for increased accuracy in the identification of those cognitive areas that need improvement in order to improve overall playing ability. By changing the way the expert rugby player thinks about certain aspects of the game, most notably those aspects that the player has difficulty with, it becomes possible for the player to address these difficulties and make improvements wherever necessary. Copyright / Dissertation (MA)--University of Pretoria, 2008. / Psychology / unrestricted

No description available.

No description available.

No description available.