Over the last decade, storage of non text-based data in databases has become an increasingly important trend in information management. Image in particular, has been gaining popularity as an alternative, and sometimes more viable, option for information storage. While this presents a wealth of information, it also creates a great problem in retrieving appropriate and relevant information during searching. This has resulted in an enormous growth of interest, and much active research, into the extraction of relevant information from non text-based databases. In particular,content-based image retrieval (CBIR) systems have been one of the most active areas of research. The retrieval principle of CBIR systems is based on visual features such as colour, texture, and shape or the semantic meaning of the images. To enhance the retrieval speed, most CBIR systems pre-process the images stored in the database. This is because feature extraction algorithms are often computationally expensive. If images are to be retrieved from the World-Wide-Web (WWW), the raw images have to be downloaded and processed in real time. In this case, the feature extraction speed becomes crucial. Ideally, systems should only use those feature extraction algorithms that are most suited for analysing the visual features that capture the common relationship between the images in hand. In this thesis, a statistical discriminant analysis based feature selection framework is proposed. Such a framework is able to select the most appropriate visual feature extraction algorithms by using relevance feedback only on the user labelled samples. The idea is that a smaller image sample group is used to analyse the appropriateness of each visual feature, and only the selected features will be used for image comparison and ranking. As the number of features is less, an improvement in the speed of retrieval is achieved. From experimental results, it is found that the retrieval accuracy for small sample data has also improved. Intelligent E-Business has been used as a case study in this thesis to demonstrate the potential of the framework in the application of image retrieval system. In addition, an inter-query framework has been proposed in this thesis. This framework is also based on the statistical discriminant analysis technique. A common approach in inter-query for a CBIR system is to apply the term-document approach. This is done by treating each image’s name or address as a term, and the query session as a document. However, scalability becomes an issue with this technique as the number of stored queries increases. Moreover, this approach is not appropriate for a dynamic image database environment. In this thesis, the proposed inter-query framework uses a cluster approach to capture the visual properties common to the previously stored queries. Thus, it is not necessary to “memorise” the name or address of the images. In order to manage the size of the user’s profile, the proposed framework also introduces a merging approach to combine clusters that are close-by and similar in their characteristics. Experiments have shown that the proposed framework has outperformed the short term learning approach. It also has the advantage that it eliminates the burden of the complex database maintenance strategies required in the term-document approach commonly needed by the interquery learning framework. Lastly, the proposed inter-query learning framework has been further extended by the incorporation of a new semantic structure. The semantic structure is used to connect the previous queries both visually and semantically. This structure provides the system with the ability to retrieve images that are semantically similar and yet visually different. To do this, an active learning strategy has been incorporated for exploring the structure. Experiments have again shown that the proposed new framework has outperformed the previous framework.

Zugl.: Aachen, Techn. Hochsch., Diss., 2007

Chemnitz, Techn. Univ., Diplomarb., 2008.

Thesis (Ph. D.)--Drexel University, 2005. / Includes abstract and vita. Includes bibliographical references (leaves 171-190).

Thesis (Ph. D.)--Carnegie Mellon University, 1989. / "August 28, 1989." "CMU-CS-89-193." eContent provider-neutral record in process. Description based on print version record. Includes bibliographical references and indexes.

Konstanz, Univ., Diplomarb. 1999.

Master of Information Systems

A dissertation submitted to the Faculty of Science, University of the Witwatersrand, Johannesburg, in fulfilment of the requirements for the degree of Master of Science., University of the Witwatersrand, Johannesburg, 2018 / Social network sites such as Twitter have created vibrant and diverse communities in which users express their opinions and views on a variety of topics such as politics. Extensive research has been conducted in countries such as Ireland, Germany and the United States, in which text mining techniques have been used to obtain information from politically oriented tweets. The purpose of this research was to determine if text mining techniques can be used to uncover meaningful information from a corpus of political tweets collected during the 2014 South African General Election. The Twitter Application Programming Interface was used to collect tweets that were related to the three major political parties in South Africa, namely: the African National Congress (ANC), the Democratic Alliance (DA) and the Economic Freedom Fighters (EFF). The text mining techniques used in this research are: sentiment analysis, clustering, association rule mining and word cloud analysis. In addition, a correlation analysis was performed to determine if there exists a relationship between the total number of tweets mentioning a political party and the total number of votes obtained by that party. The VADER (Valence Aware Dictionary for sEntiment Reasoning) sentiment classifier was used to determine the public’s sentiment towards the three main political parties. This revealed an overwhelming neutral sentiment of the public towards the ANC, DA and EFF. The result produced by the VADER sentiment classifier was significantly greater than any of the baselines in this research. The K-Means cluster algorithm was used to successfully cluster the corpus of political tweets into political-party clusters. Clusters containing tweets relating to the ANC and EFF were formed. However, tweets relating to the DA were scattered across multiple clusters. A fairly strong relationship was discovered between the number of positive tweets that mention the ANC and the number of votes the ANC received in election. Due to the lack of data, no conclusions could be made for the DA or the EFF. The apriori algorithm uncovered numerous association rules, some of which were found to be interest- ing. The results have also demonstrated the usefulness of word cloud analysis in providing easy-to-understand information from the tweet corpus used in this study. This research has highlighted the many ways in which text mining techniques can be used to obtain meaningful information from a corpus of political tweets. This case study can be seen as a contribution to a research effort that seeks to unlock the information contained in textual data from social network sites. / MT 2018

No description available.

Natural Language (NL) descriptions can be one of the most convenient ways to initialize a visual tracker. NL descriptions can also help provide information for longer-term invariance, thus helping the tracker cope better with typical visual tracking challenges, e.g. occlusion, motion blur, etc. However, deriving a formulation to combine the strengths of appearance-based tracking with the NL modality is not straightforward. In this thesis, we use deep neural networks to learn a joint representation of language and vision that can perform various tasks, such as visual tracking by NL, tracked-object retrieval by NL, and spatio-temporal video groundings by NL. First, we study the Single Object Tracking (SOT) by NL descriptions task, which requires spatial localizations of a target object in a video sequence. We propose two novel approaches. The first is a tracking-by-detection approach, which performs object detection in the video sequence via similarity matching between potential objects' pooled visual representations and NL descriptions. The second approach uses a novel Siamese Natural Language Region Proposal Network with a depth-wise cross correlation operation to replace the visual template with a language template in Siamese trackers, e.g. SiamFC, SiamRPN++, etc., and achieves state-of-the-art on standard single object tracking by NL benchmarks. Second, based on experimental results and findings from the SOT by NL task, we propose the Tracked-object Retrieval by NL (TRNL) descriptions task and collect the CityFlow-NL Benchmark for it. CityFlow-NL contains more than 6,500precise NL descriptions of tracked vehicle targets, making it the first densely annotated dataset of tracked-objects paired with NL descriptions. To highlight the novelty of our dataset, we propose two models for the retrieval by NL task: a single-stream model based on cross-modality similarity matching and a quad-stream retrieval model that models the similarity between language features and visual features, including local visual features, frame-level features, motions, and relationships between visually similar targets. We release the CityFlow-NL Benchmark together with our models as challenges in the 5th and the 6th AI City Challenge. Lastly, we focus on the most challenging yet practical task of Spatio-Temporal Video Grounding (STVG), which aims to spatially and temporally localize a target in videos with NL descriptions. We propose new evaluation protocols for the STVG task to adapt to the new challenges of CityFlow-NL that are not well-represented in prior STVG benchmarks. Three intuitive and novel approaches to the STVG task are proposed and studied in this thesis, i.e. Multi-Object Tracking (MOT) + Retrieval by NL approach, Single Object Tracking (SOT) by NL based approach, and a direct localization approach that uses a transformer network to learn a joint representation from both the NL and vision modalities.