Himanshu Singh

A novel gamma correction approach using optimally clipped sub-equalization for dark image enhancement

In this paper, an efficient statistical approach employing a highly adaptive gamma correction based on adaptively clipped and locally equalized histogram using mean-median statistical pair, is presented for the enhancement of low contrast dark images without losing their intrinsic features. For this purpose, linearly stretched intensity range segmentation, first based on median and mean distribution sub-histograms are derived for local equalization after optimal clipping. Later on, non-linear transformational mapping has been imposed by suitable gamma-correction using the required gamma value-set, which itself is derived by cumulative distribution of the intensity values in adaptively equalized histogram. The proposed methodology clearly outperforms the other state-of-the-art methods in terms of complexity as well as quantitative and qualitative performance; and hence, can be appreciably used for a wide and dynamic range of image-database belonging to various domains ranging from biomedical images to remotely sensed satellite images.

Satellite image enhancement using beta wavelet based gamma corrected adaptive knee transformation

In this paper, the gamma corrected adaptive knee transformation, proposed by Monobe et al. is reviewed and improved by exploiting two-dimensional single level Beta wavelet filter for subband decomposition of the low contrast satellite images. For this purpose, the input image is initially decomposed into its subband images such as low-low (LL), low-high (LH), high-low (HL), and high-high (HH)). Then, LL-band coefficients of the input image are transformed to obtain enhanced LL-band by applying gamma corrected adaptive knee transformation. Finally, it is combined with rest of the subbands for desired alias free and distortion less reconstruction of the enhanced image. A comparative study of different wavelet filters has been performed and it is evident that Beta function and its derivatives based wavelet filter outperforms over other wavelet filters.

Swarm intelligence optimized piecewise gamma corrected histogram equalization for dark image enhancement

Abstract In this paper, a highly adaptive swarm intelligence optimized dark image enhancement approach is proposed for remotely sensed satellite images. Here, a weighted summation framework is suggested for imparting “on-demand entropy restoration and contrast enhancement”. This approach utilizes the benefits of both gamma correction and histogram equalization; and hence, overall image enhancement can be appropriately imposed without losing original image features, especially for dark satellite images. For further improvement, gamma correction is also employed in a piecewise manner, separately for dark as well as light pixel values, so that over-saturation and other related unnatural artifacts can be avoided. A suitable entropy and contrast based cost function is utilized, and its maximization is done by employing particle swarm optimization over a three-dimensional search space. The proposed approach is found to be highly appreciable for overall enhancement, preserving all the intrinsic visual details for a wide range of dark image database covering satellite as well as general images.

Regionally equalized and contextually clipped gamma correction approach for dark image enhancement

In this paper, an efficient statistical approach, employing a highly adaptive gamma correction based on regionally distributed and independently equalized histograms for all regions followed by contextual clipping, is presented for overall enhancement of low contrast dark images keeping their intrinsic features preserved. For this purpose, input image is uniformly subdivided into several non-overlapping equal sized regions. A good estimation has been achieved by classifying these regions into three groups namely corner regions, boarder regions as well as inner regions. Further, separate histogram equalization can be performed, followed by individual regions contextual clipping so that unwanted domination of high frequency bins over other bins can be avoided. Later on, a non-linear transformational mapping has been imposed by suitable gamma-correction using required gamma value-set, which itself is derived by cumulative distribution of the intensity values in adaptively equalized histogram. The proposed methodology clearly outperforms other state-of-the-art methods in terms of complexity as well as quantitative and qualitative performance; and hence, can be appreciably used for a wide and dynamic range of image-database which belongs to various domains ranging from biomedical images to remotely sensed satellite images.

A novel optimally gamma corrected intensity span maximization approach for dark image enhancement

In this paper, a highly adaptive swarm intelligence inspired optimally gamma corrected intensity coverage maximization approach has been proposed for quality enhancement of dark and low contrast remotely sensed images. Various image enhancement techniques have been proposed till date, but in case of dark images, most of them are suffering from saturation effects in higher intensity regions along with information loss due to it; and hence, not appreciated very well. Also, most of the available techniques are unable to utilize the entire allowable intensity range, fully and fruitfully. Here, an optimal gamma value set which itself has been derived through optimal weighting of linearly stretched and interim equalized image so that the allowed range can be maximally occupied. Also, highly qualified objective function has been drafted for employing swarm intelligence over a two-dimensional search space. The proposed approach is found highly capable to recover the vast amount of information, along with contrast and sharpness enhancement when compared with other state-of-the-art methodologies, for remotely-sensed as well as general images.

A Sine-Cosine Optimizer-Based Gamma Corrected Adaptive Fractional Differential Masking for Satellite Image Enhancement

The prime objective is to harvest more and more information present in a remotely sensed dark satellite image, captured under poorly illuminated circumstances. For imparting optimal quality enhancement, a recently proposed and highly efficient Sine-Cosine optimizer is employed in association with a novel optimally weighted gamma corrected (GC) fractional differential (FD) order masking framework. Overall texture enhancement is achieved by optimally ordered FD masking along with its optimal augmentation with GC interim channel. Core objective of entropy enhancement is fulfilled by keeping a proper check for over-enhanced or saturated regions through the introduction of penalty term in the employed cost function, for adaptive exploration and identification of missing levels for more optimal redistribution throughout the permissible range; so that natural look can be preserved efficiently. Rigorous experimentation is performed by employing performance evaluation and comparison with preexisting highly appreciated quality enhancement approaches.

Slantlet filter-bank based satellite image enhancement using gamma corrected knee transformation

ABSTRACT In this paper, an efficient and relatively fast approach for satellite image enhancement is proposed. This technique is based on auto-knee transfer function with suitable gamma correction using slantlet transform for two-scale decomposed image. Dark or low contrast, big-data (or large sized) multispectral images can be easily enhanced by proper tuning for the value of gamma-parameter using slantlet transform. Here, sub-band decomposition is achieved by employing single-level slantlet filter-bank, which is just equivalent to second-level sub-band decomposition using discrete wavelet transform) that has been employed initially. For this purpose, main information of the image is concentrated to lowest sub-band, over which gamma correction is applied after computing the knee transfer function adaptively for low quality input image. In addition to this two-scale decomposition-based enhancement, here, gamma-corrected energy redistributed slantlet transform-based textural enhancement framework is also suggested. The experimentation comprised of relative performance evaluation and comparison on the same scale; clearly reflects the outperformance of proposed methodology over various well-known pre-existing state-of-the-art techniques both quantitatively and qualitatively.