published_or_final_version / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy

This thesis proposes to learn the absent cognitive element in conventional scene categorization methods: sub-scenes, and use them to better categorize and understand scenes. In scene categorization, it has been observed that the problem of ambiguity occurs when treating the scene as a whole. Scene ambiguity arises from when a similar set of sub-scenes are arranged differently to compose different scenes, or when a scene literally contains several categories. However, these ambiguities can be discerned by the knowledge of sub-scenes. Thus, it is worthy to study sub-scenes and use them to better understand a scene. The proposed research firstly considers an unsupervised method to segment sub-scenes. It emphasizes on generating more integral regions instead of over-segmented regions usually produced by conventional segmentation methods. Several properties of sub-scenes are explored such as proximity grouping, area of influence, similarity and harmony based on psychological principles. These properties are formulated into constraints that are used directly in the proposed framework. A self-determined approach is employed to produce a final segmentation result based on the characteristics of each image in an unsupervised manner. The proposed method performs competitively against other state-of-the-art unsupervised segmentation methods with F-measure of 0.55, Covering of 0.51 and VoI of 1.93 in the Berkeley segmentation dataset. In the Stanford background dataset, it achieves the overlapping score of 0.566 which is higher than the score of 0.499 of the comparison method. To segment and label sub-scenes simultaneously, a supervised approach of semantic segmentation is proposed. It is developed based on a Hierarchical Conditional Random Field classification framework. The proposed method integrates contextual information into the model to improve classification performance. Contextual information including global consistency and spatial context are considered in the proposed method. Global consistency is developed based on generalizing the scene by scene types and spatial context takes the spatial relationship into account. The proposed method improves semantic segmentation by boosting more logical class combinations. It achieves the best score in the MSRC-21 dataset with global accuracy at 87% and the average accuracy at 81%, which out-performs all other state-of-the-art methods by 4% individually. In the Stanford background dataset, it achieves global accuracy at 80.5% and average accuracy at 71.8%, also out-performs other methods by 2%. Finally, the proposed research incorporates sub-scenes into the scene categorization framework to improve categorization performance, especially in ambiguity cases. The proposed method encodes the sub-scene in the way that their spatial information is also considered. Sub-scene descriptor compensates the global descriptor of a scene by evaluating local features with specific geometric attributes. The proposed method obtains an average categorization accuracy of 92.26% in the 8 Scene Category dataset, which outperforms all other published methods by over 2% of improvement. It evaluates ambiguity cases more accurately by discerning which part exemplifies a scene category and how those categories are organized. / published_or_final_version / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy

University of Macau / Faculty of Science and Technology / Department of Computer and Information Science

University of Macau / Faculty of Science and Technology / Department of Computer and Information Science

University of Macau / Faculty of Science and Technology / Department of Computer and Information Science

University of Macau / Faculty of Science and Technology / Department of Computer and Information Science

University of Macau / Faculty of Science and Technology / Department of Computer and Information Science

This dissertation examines the suitability of Display-Processor (DP) image computers for image enhancement and restoration tasks. Because the major architectural feature of the DP devices is their ability to rapidly evaluate finite impulse response (FIR) convolutions, much of the study focusses on the use of spatial-domain FIR convolutions to approximate Fourier-domain filtering. When the enhancement task requires the evaluation of only a single convolution, it is important that the FIR kernel used to implement the convolution is designed so that the resulting output is a good approximation of the desired output. A Minimum-Mean-Squared-Error design criterion is introduced for the purpose of FIR kernel design and its usefulness is demonstrated by showing some results of its use. If the restoration or enhancement task requires multiple convolutions in an iterative algorithm, it is important to understand how the truncation of the kernel to a finite region of support will affect the convergence properties of an algorithm and the output of the iterative sequence. These questions are examined for a limited class of nonlinear restoration algorithms. Because FIR convolutions are most efficiently performed on computing machines that have limited precision and are usually limited to performing fixed-point arithmetic, the dissertation also examines the effects of roundoff error on output images that have been computed using fixed point math. The number of bits that are needed to represent the data during a computation is algorithm dependent, but for a limited class of algorithms, it is shown that 12 bits are sufficient. Finally, those architectural features in a DP that are necessary for useful enhancement and restoration operations are identified.

No description available.

Digital image feature detectors often comprise two stages of processing: an initial filtering phase and a secondary search stage. The initial filtering is designed to accentuate specific feature characteristics or suppress spurious components of the image signal. The second stage of processing involves searching the results for various criteria that will identify the locations of the image features. The local energy feature detection scheme combines the squares of the signal convolved with a pair of filters that are in quadrature with each other. The resulting local energy value is proportional to phase congruency which is a measure of the local alignment of the phases of the signals constituent Fourier components. Points of local maximum phase alignment have been shown to correspond to visual features in the image. The local energy calculation accentuates the location of many types of image features, such as lines, edges and ramps and estimates of local energy can be calculated in multidimensional image data by rotating the quadrature filters to several orientations. The second stage search criterion for local energy is to locate the points that lie along the ridges in the energy map that connect the points of local maxima. In three dimensional data the relatively higher energy values will form films between connecting laments and tendrils. This thesis examines the use of recursive spatial domain filtering to calculate local energy. A quadrature pair of filters which are based on the first derivative of the Gaussian function and its Hilbert transform, are rotated in space using a kernel of basis functions to obtain various orientations of the filters. The kernel is designed to be separable and each term is implemented using a recursive digital filter. Once local energy has been calculated the ridges and surfaces of high energy values are determined using a flooding technique. Starting from the points of local minima we perform an ablative skeletonisation of the higher energy values. The topology of the original set is maintained by examining and preserving the topology of the neighbourhood of each point when considering it for removal. This combination of homotopic skeletonisation and sequential processing of each level of energy values, results in a well located, thinned and connected tracing of the ridges. The thesis contains examples of the local energy calculation using steerable recursive filters and the ridge tracing algorithm applied to two and three dimensional images. Details of the algorithms are contained in the text and details of their computer implementation are provided in the appendices.