In the recent era, a boom was observed in the field of information retrieval from images. Digital images with high contrast are sources of abundant information. The gathered information is useful in the precise detection of an object, event, or anomaly captured in an image scene. Existing systems do uniform distribution of intensities and apply intensity histogram equalization. These improve the characteristics of an image in terms of visual appearance. The problem of over enhancement and the increase in noise level produces undesirable visual artefacts. The use of Otsu's single threshold method in existing systems is inefficient for segmenting an image with multiple objects and complex background. Additionally, these are incapable to improve the yield of the maximum entropy and brightness preservation. The aforementioned limitations motivate us to propose an efficient statistical pipelined approach, the Range Limited Double Threshold Weighted Histogram Equalization (RLDTWHE). This approach is an integration of Otsu's double threshold, dynamic range stretching, weighted distribution, adaptive gamma correction, and homomorphic filtering. It provides optimum contrast enhancement by selecting the best appropriate threshold value for image segmentation. The proposed approach is efficient in the enhancement of low contrast medical MRI images and digital natural scene images. It effectively preserves all essential information recorded in an image. Experimental results prove its efficacy in terms of maximum entropy preservation, brightness preservation, contrast enhancement, and retaining the natural appearance of an image.
Coupling kinetic and continuum using data-driven maximum entropy distribution
