Improved Partial Differential Equation and Fast Approximation Algorithm for Hazy/Underwater/Dust Storm Image Enhancement

This paper presents an improved and modified partial differential equation (PDE)-based de-hazing algorithm. The proposed method combines logarithmic image processing models in a PDE formulation refined with linear filter-based operators in either spatial or frequency domain. Additionally, a fast, simplified de-hazing function approximation of the hazy image formation model is developed in combination with fuzzy homomorphic refinement. The proposed algorithm solves the problem of image darkening and over-enhancement of edges in addition to enhancement of dark image regions encountered in previous formulations. This is in addition to avoiding enhancement of sky regions in de-hazed images while avoiding halo effect. Furthermore, the proposed algorithm is utilized for underwater and dust storm image enhancement with the incorporation of a modified global contrast enhancement algorithm. Experimental comparisons indicate that the proposed approach surpasses a majority of the algorithms from the literature based on quantitative image quality metrics.

Results of improved fractional/integer order PDE-based binarization model

In this report, we present and compare the results of an improved fractional and integer order partial differential equation (PDE)-based binarization scheme. The improved model incorporates a diffusion term in addition to the edge and binary source terms from the previous formulation. Furthermore, logarithmic local contrast edge normalization and combined isotropic and anisotropic edge detection enables simultaneous bleed-through elimination with faded text restoration for degraded document images. Comparisons of results with state-of-the-art PDE methods show improved and superior results.

Analysis of Multiscale Wavelet-based Fractional Gradient-Anisotropic Diffusion Fusion for single hazy and underwater image enhancement

This report presents the results of a multi-scale wavelet based scheme for single image de-hazing and underwater image enhancement. The scheme is fast and highly localized in addition to global enhancement of hazy images. A PDE-based formulation enables additional versatility as the iterative nature allows more flexibility for various types of images. Visual and objective results from experiments indicate that the proposed approach competes favourably or surpasses most of the state-of-the-art approaches.

Analysis of PDE-based binarization model for degraded document images

This report presents the results of a PDE-based binarization model for degraded document images. The model utilizes an edge and binary source term in its formulation. Results indicate effectiveness for document images with bleed-through and faded text and stains to a lesser extent.

Fractional Multiscale Fusion-based De-hazing

This report presents the results of a proposed multi-scale fusion-based single image de-hazing algorithm, which can also be used for underwater image enhancement. Furthermore, the algorithm was designed for very fast operation and minimal run-time. The proposed scheme is the faster than existing algorithms for both de-hazing and underwater image enhancement and amenable to digital hardware implementation. Results indicate mostly consistent and good results for both categories of images when compared with other algorithms from the literature.

Sky detection and log illumination refinement for PDE-based hazy image contrast enhancement

This report presents the results of a sky detection technique used to improve the performance of a previously developed partial differential equation (PDE)-based hazy image enhancement algorithm. Additionally, a proposed alternative method utilizes a function for log illumination refinement to improve de-hazing results while avoiding over-enhancement of sky or homogeneous regions. The algorithms were tested with several benchmark and calibration images and compared with several standard algorithms from the literature. Results indicate that the algorithms yield mostly consistent results and surpasses several of the other algorithms in terms of colour and contrast enhancement in addition to improved edge visibility.

Analysis of the Entropy-guided Switching Trimmed Mean Deviation-based Anisotropic Diffusion filter

This report describes the experimental analysis of a proposed switching filter-anisotropic diffusion hybrid for the filtering of the fixed value (salt and pepper) impulse noise (FVIN). The filter works well at both low and high noise densities though it was specifically designed for high noise density levels. The filter combines the switching mechanism of decision-based filters and the partial differential equation-based formulation to yield a powerful system capable of recovering the image signals at very high noise levels. Experimental results indicate that the filter surpasses other filters, especially at very high noise levels. Additionally, its adaptive nature ensures that the performance is guided by the metrics obtained from the noisy input image. The filter algorithm is of both global and local nature, where the former is chosen to reduce computation time and complexity, while the latter is used for best results.