Multimodal enhancement-fusion technique for natural images.
MetadataShow full item record
This dissertation presents a multimodal enhancement-fusion (MEF) technique for natural images. The MEF is expected to contribute value to machine vision applications and personal image collections for the human user. Image enhancement techniques and the metrics that are used to assess their performance are prolific, and each is usually optimised for a specific objective. The MEF proposes a framework that adaptively fuses multiple enhancement objectives into a seamless pipeline. Given a segmented input image and a set of enhancement methods, the MEF applies all the enhancers to the image in parallel. The most appropriate enhancement in each image segment is identified, and finally, the differentially enhanced segments are seamlessly fused. To begin with, this dissertation studies targeted contrast enhancement methods and performance metrics that can be utilised in the proposed MEF. It addresses a selection of objective assessment metrics for contrast-enhanced images and determines their relationship with the subjective assessment of human visual systems. This is to identify which objective metrics best approximate human assessment and may therefore be used as an effective replacement for tedious human assessment surveys. A subsequent human visual assessment survey is conducted on the same dataset to ascertain image quality as perceived by a human observer. The interrelated concepts of naturalness and detail were found to be key motivators of human visual assessment. Findings show that when assessing the quality or accuracy of these methods, no single quantitative metric correlates well with human perception of naturalness and detail, however, a combination of two or more metrics may be used to approximate the complex human visual response. Thereafter, this dissertation proposes the multimodal enhancer that adaptively selects the optimal enhancer for each image segment. MEF focusses on improving chromatic irregularities such as poor contrast distribution. It deploys a concurrent enhancement pathway that subjects an image to multiple image enhancers in parallel, followed by a fusion algorithm that creates a composite image that combines the strengths of each enhancement path. The study develops a framework for parallel image enhancement, followed by parallel image assessment and selection, leading to final merging of selected regions from the enhanced set. The output combines desirable attributes from each enhancement pathway to produce a result that is superior to each path taken alone. The study showed that the proposed MEF technique performs well for most image types. MEF is subjectively favourable to a human panel and achieves better performance for objective image quality assessment compared to other enhancement methods.