| Formatted contents note |
Due to some constraints in imaging techniques and computer graphics, images that<br/>are captured have many problems like distorted edges, presence of noise, artifacts, and oversaturated<br/>colours. Image enhancement plays a significant role in the preservation of edges,<br/>minimization of noise, artifacts, thus have broad applications in domains of image smoothing,<br/>filtering, contrast correction, de-hazing, de-blurring, rain-removal, and super-resolution.<br/>Specifically, edge preservation techniques are considered for image enhancement to improve<br/>the visual quality, which ultimately minimizes noise, artifacts and enhances the quality of<br/>the image.<br/>Existing image enhancement techniques mostly are inaccurate, result in noise, artifacts,<br/>blurred edges, so they do not perform well for different applications. This leads to less<br/>visually pleasing results having low quality. In this thesis, edge preservation techniques for<br/>image enhancement are proposed for different domains, which include image smoothing,<br/>filtering, de-blurring, de-hazing, rain removal, super-resolution, illumination normalization,<br/>low light image enhancement, vessel segmentation, re-colouring, and underwater image enhancement.<br/>Simple to implement techniques are proposed incorporating existing filters like<br/>guided filter, L0 minimization filter etc and machine learning algorithms like PCA, k-means<br/>clustering, etc. in different colour spaces like RGB and YCbCr to preserve edges, minimize<br/>noise, artifacts, contrast correction and produce visually pleasing results. Image is segmented<br/>for smoothing and deblurring, quad-tree decomposition for dehazing, specular band<br/>decomposition for illumination normalization, undergoes DFT for recolouring, and Laplace<br/>decomposition for underwater image enhancement. Operations such as histogram processing,<br/>sharpening, de-noising, morphological operations, arithmetic operations, clustering,<br/>color balancing, and white balancing are also performed to preserve edges and minimize<br/>noise, artifacts. The proposed techniques produce results with minimum noise, artifacts, and<br/>blurred edges.<br/>Visual and quantitative comparison (with state of the art existing techniques) is performed<br/>to verify the significance of the proposed methods. Simulation results reveal that<br/>the proposed techniques are more accurate in edge preservation, minimization of noise, and<br/>artifacts as compared to the state of the art techniques. |
