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. / © Cranfield University

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.

Electrification (or now rare and obsolete electrization), carried out in Czechoslovakia primarily in the interwar years (1918-1939) has gone down in history as a symbol of the construction of a modern independent Czechoslovak state and its democratic society, encapsulating its overall, predominantly building, ethos. Electrification was based on the expertise, invention and high educational standards of the country's electrical engineering elite that approached this particular task as a fully formed group (especially in the period starting from the last third of the 19th century) and as a particularly excellently organized one in terms of its professional unions, specialist scientific knowledge and potential use of its expertise in industrial plants and production centres for electrification. Its key platform was the Czechoslovak Electrical Engineering Union (Elektrotechnický svaz československý, Czech acronym ESČ, 1919), an association closely cooperating with the state authorities, primarily the Ministry of Public Industry and its State Power Council, with an agency that represented the country's vital standardization base and which soon grew to be the powerful Czechoslovak Standardization Society (Československá normalizační společnost, known under the Czech acronym ČSN, 1920); the ESČ also...