No description available.

In this thesis, we present a strongly coupled data fusion architecture within a Bayesian framework for modeling the bi-directional influences between the scene and object classification mechanisms. A number of psychophysical studies provide experimental evidence that the object and the scene perception mechanisms are not functionally separate in the human visual system. Object recognition facilitates the recognition of the scene background and also knowledge of the scene context facilitates the recognition of the individual objects in the scene. The evidence indicating a bi-directional exchange between the two processes has motivated us to build a computational model where object and scene classification proceed in an interdependent manner, while no hierarchical relationship is imposed between the two processes. We propose a strongly coupled data fusion model for implementing the feedback relationship between the scene and object classification processes. We present novel schemes for modifying the Bayesian solutions for the scene and object classification tasks which allow data fusion between the two modules based on the constraining of the priors or the likelihoods. We have implemented and tested the two proposed models using a database of natural images created for this purpose. The Receiver Operator Curves (ROC) depicting the scene classification performance of the likelihood coupling and the prior coupling models show that scene classification performance improves significantly in both models as a result of the strong coupling of the scene and object modules. / ROC curves depicting the scene classification performance of the two models also show that the likelihood coupling model achieves a higher detection rate compared to the prior coupling model. We have also computed the average rise times of the models' outputs as a measure of comparing the speed of the two models. The results show that the likelihood coupling model outputs have a shorter rise time. Based on these experimental findings one can conclude that imposing constraints on the likelihood models provides better solutions to the scene classification problems compared to imposing constraints on the prior models. / We have also proposed an attentional feature modulation scheme, which consists of tuning the input image responses to the bank of Gabor filters based on the scene class probabilities estimated by the model and the energy profiles of the Gabor filters for different scene categories. Experimental results based on combining the attentional feature tuning scheme with the likelihood coupling and the prior coupling methods show a significant improvement in the scene classification performances of both models.

Recent research has enabled reconstruction of a scene from multiple images. These algorithms rely on assumptions that the scene does not change drastically from one photo to the next. Construction photographs, in particular, pose challenges for the existing algorithms. I propose a novel image-based reconstruction algorithm that overcomes these limitations and reconstructs a 4D indoor Manhattan model using construction photographs. Finally, I present a novel user interface that combines image-based rendering and intuitive 4D navigation controls to observe and explore the resulting reconstruction.

The 3D shape and position of objects inside the human body are commonly detected using Computed Tomography (CT) scanning. CT is an expensive diagnostic option in economically disadvantaged areas and the radiation dose experienced by the patient is significant. In this dissertation, we present a technique for reconstructing the 3D shape and position of bullets from multiple X-rays. This technique makes us of ubiquitous X-ray equipment and a small number of X-rays to reduce the radiation dose. Our work relies on Image Segmentation and Volume Reconstruction techniques. We present a method for segmenting bullets out of X-rays, based on their signature in intensity profiles. This signature takes the form of a distinct plateau which we model with a number of parameters. This model is used to identify horizontal and vertical line segments within an X-Ray corresponding to a bullet signature. Regions containing confluences of these line segments are selected as bullet candidates. The actual bullet is thresholded out of the region based on a range of intensities occupied by the intensity profiles that contributed to the region. A simple Volume Reconstruction algorithm is implemented that back-projects the silhouettes of bullets obtained from our segmentation technique. This algorithm operates on a 3D voxel volume represented as an octree. The reconstruction is reduced to the 2D case by reconstructing a slice of the voxel volume at a time. We achieve good results for our segmentation algorithm. When compared with a manual segmentation, our algorithm matches 90% of the bullet pixels in nine of the twelve test X-rays. Our reconstruction algorithm produces an acceptable results: It achieves a 70% match for a test case where we compare a simulated bullet with a reconstructed bullet.

No description available.

No description available.

No description available.

No description available.

No description available.

This thesis summarises research on the improved design, integration and expansion of past cortex-like computer vision models, following biologically-inspired methodologies. By adopting early theories and algorithms as a building block, particular interest has been shown for algorithmic parameterisation, feature extraction, invariance properties and classification. Overall, the major original contributions of this thesis have been: 1. The incorporation of a salient feature-based method for semantic feature extraction and refinement in object recognition. 2. The design and integration of colour features coupled with the existing morphological-based features for efficient and improved biologically-inspired object recognition. 3. The introduction of the illumination invariance property with colour constancy methods under a biologically-inspired framework. 4. The development and investigation of rotation invariance methods to improve robustness and compensate for the lack of such a mechanism in the original models. 5. Adaptive Gabor filter design that captures texture information, enhancing the morphological description of objects in a visual scene and improving the overall classification performance. 6. Instigation of pioneering research on Spiking Neural Network classification for biologically-inspired vision. Most of the above contributions have also been presented in two journal publications and five conference papers. The system has been fully developed and tested in computers using MATLAB under a variety of image datasets either created for the purposes of this work or obtained from the public domain.