Contrast Enhancement Algorithm Research Articles

Classification of Digital Mammograms Into Masses and Non-Masses using Texture Combination Features and SVM

This paper presents a framework for grouping of mammogram images into carcinogenic and non- carcinogenic images. In this paper, image is enhanced using nonlinear contrast enhancement algorithm and then segmented using internal and external mask segmentation. The features used in the proposed work are based on the texture feature which means that the segmentation results will have minimal impact on the classification results of mammograms into masses and non – masses. The features used are Contrast, Energy, Homogeneity, Entropy, Mean Intensity, Standard Deviation, Taxonomic distinctness, Taxonomic distance and learning takes place by Support Vector Machine. The algorithm was applied on Mammographic Image Analysis Society database and when compared with contemporary techniques , the results were improved.

A novel enhanced cuckoo search algorithm for contrast enhancement of gray scale images

A good contrast image has a significant role in different image processing applications and computer vision algorithms. One of the most common contrast enhancement approaches is histogram equalization (HE) that enhances the contrast of an image globally. However, it gives rise to some over-enhanced regions, loss of detail information, and enhancement of noise. In order to improve the performance of the HE algorithm, local HE and adaptive HE algorithms have been proposed but with limited success. Recently, an evolutionary algorithm named cuckoo search (CS) algorithm has been employed for automatic image contrast enhancement showing promising performance. In this paper, we propose a novel enhanced cuckoo search (ECS) algorithm for image contrast enhancement. In addition, we propose a new range of search space for the parameters of the local/global enhancement (LGE) transformation that need to be optimized. The proposed ECS algorithm is applied to several low contrast test images and its performance is compared with that of the CS algorithm. Next, we compare the performance of the ECS algorithm with artificial bee colony algorithm using the proposed LGE transformation and a global transformation. In the last stage of performance evaluation, the ECS algorithm is compared with several image enhancement algorithms, namely, HE, CLAHE, Particle Swarm Optimization (PSO), CS, modified CS and CS-PSO algorithms. In all cases, we have shown the superiority of the ECS algorithm in terms of several performance measures.

Power reduction and contrast enhancement based on scene reconstruction for organic light emitting diode displays

A power reduction and contrast enhancement algorithm based on scene reconstruction for an organic light-emitting diode display is presented. The process of energy saving can be regarded as the extraction of image features and reconstruction of a scene to cater to human visual perception. In the proposed algorithm, some characteristics such as skin color, local variance, and brightness value are adopted to describe image features and are combined into a contour-preserving attenuation model. According to this model, reconstruction of a scene is accomplished through changing the value of the brightness reasonably while saving energy. Finally, enhancement of the image is guaranteed by the process of compensating for the brightness. Experimental results show that the proposed algorithm provides better visual quality than former algorithms and can reach an appropriate energy saving ratio.

Optimized self-adapting contrast enhancement algorithm for wafer contour extraction

The aim is to design a self-adapting contrast enhancement algorithm that can remove the background noise and divide the foreground and background very well. For the self-adapting contrast enhancement algorithm, we looked for all background RGB pixel values, and found the minimum values in the RGB components so that ∂=255/min(Ipixel(R, G, B)). The results were compared to classical contrast enhancement techniques. Five steps to extract the wafer contour, respectively, were the preservation filter, self-adapting contrast enhancement, closing morphological operation, image binarization based on the Otsu method and using the first derivative extract contour. The results of contour extraction were compared with the traditional Canny, Sobel and Scharr algorithms using different parameter values. The experiment results showed that the self-adapting contrast enhancement algorithm could remove the background noise effectively compared to traditional methods. In comparison with the Canny, Sobel and Scharr algorithms, the first derivative after the original image filtering by optimized self-adapting contrast enhancement algorithm was better at extracting wafer contours. Therefore, we concluded that the wafer self-adapting contrast enhancement algorithm method was correct and feasible. The theories in this paper could be applied to image processing in the agricultural, industrial, and military fields.

Contrast Enhancement via Dual Graph Total Variation-Based Image Decomposition

Images captured in low lighting environment suffer from both low luminance contrast and noise corruption. However, most existing contrast enhancement algorithms only consider contrast boosting, which tends to reveal or amplify noise that is originally not visible in the dark areas. In this paper, we propose a joint contrast enhancement and denoising algorithm, which is based on structure/texture layer decomposition via minimization of dual forms of graph total variation (GTV). Specifically, the structure layer is expected to be generally smoothing but with sharp edges at the foreground background boundaries, for which we propose a quadratic form of GTV (QGTV) as the prior that promotes signal smoothness along graph structure. For the texture layer, a re-weighted GTV (RGTV) is tailored to noise removal while preserving true image details. We provide theoretical analysis about the filtering behavior of these two priors. Furthermore, a boost factor is derived per patch via optimal contrast-tone mapping to improve the overall brightness level of the patch. Finally, an optimization objective function is formulated, which casts image decomposition, brightness boosting, and noise reduction into a unified optimization framework. We further propose a fast approach to efficiently solve the optimization and provide analysis about the convergency. The experimental results show that the proposed method outperforms the state-of-the-art works in subjective, objective, and statistical quality evaluation.

Work memories in Super 8: Searching a frame quality metric for movie restoration assessment

Abstract This paper describes the digital acquisition and restoration of a Super 8 documentary on the origins of citizens’ awareness on paper recycling in the city of Brescia, Lombardy, northern Italy. This film is currently stored in Fondazione ASM archives, and its acquisition is part of a larger project of preservation of industrial memories in Italy. Here we describe the tools used for the acquisition and the post-processing with a Spatial Colour Algorithm (SCA) for unsupervised colour and contrast enhancement. This method provides a semi-automatic image restoration, whose quality has been tested through different evaluations. In this paper, some advantages of the use of SCAs in the restoration pipeline are presented, together with a preliminary discussion on the problem of assessing frame restoration results. To this aim, we present objective vs. subjective evaluation, and some issues associated with this complex task. The most used full-reference and no-reference metrics have been used, together with alternative low-level descriptors. Data and examples are presented and discussed.

Multispectral image processing algorithms for enhanced vision systems in the Arctic

The issues of enhanced vision multispectral systems application for robotic complexes control in the Arctic are considered. The existing contrast enhancement methods are observed. Probability characteristics of images being subject to contrast enhancement parameters are estimated. Based on these characteristics, the authors concluded that image areas requiring the greatest contrast enhancement are the areas with low saturation and magnitude gradients, at certain brightness values. Image quality improvement method is proposed. It performs processing only in the areas where it is necessary to enhance the contrast, practically without affecting the most homogeneous or structured image parts. The processed image saturation remains due to the processing of both luminance channel and saturation channel. The algorithm proposed also provides contrast enhancement of shaded image areas. The calculated values of various objective image quality indices indicate that the contrast enhancement algorithm proposed provides better results than known approaches. In addition, different spectral range image fusion algorithm ensuring visibility in the presence of interfering factors is proposed. It differs from known methods by adaptive weight adjustment in different areas of image. The example confirming the effectiveness of the fusion method proposed is shown. For its comparison with known methods, the values of fusion objective quality indices are calculated. The fusion algorithm proposed is shown to surpass known methods by various quality assessments. The conclusion about the expediency of using the algorithms developed in technical vision systems of robotic complexes in the Arctic is made.

A novel joint histogram equalization based image contrast enhancement

The limitation to the most commonly used histogram equalization (HE) technique is the inconsideration of the neighborhood info near each pixel for contrast enhancement. This gives rise to noise in the output image. To overcome this effect, a novel joint histogram equalization (JHE) based technique is suggested. The focus is to utilize the information among each pixel and its neighbors, which improves the contrast of an image. The suggested method is developed in a truly two-dimensional domain. The joint histogram is constructed using the original image and its average image. Further, it does not require a target uniform distribution for generating the output. The two-dimensional cumulative distribution function (CDF) is utilized as a mapping function to get the output pixel intensity. Extensive experiments are performed using 300 test images from BSD database. The experimental analysis indicates that the procedure produces better results than the state-of-the-art HE based contrast enhancement algorithms. More significantly, it produces the best results even for images having a narrow dynamic range. The implementation simplicity of the proposed algorithm may attract researchers to explore the idea for new applications in image processing.

Machine learning hyperparameter selection for Contrast Limited Adaptive Histogram Equalization

Contrast enhancement algorithms have been evolved through last decades to meet the requirement of its objectives. Actually, there are two main objectives while enhancing the contrast of an image: (i) improve its appearance for visual interpretation and (ii) facilitate/increase the performance of subsequent tasks (e.g., image analysis, object detection, and image segmentation). Most of the contrast enhancement techniques are based on histogram modifications, which can be performed globally or locally. The Contrast Limited Adaptive Histogram Equalization (CLAHE) is a method which can overcome the limitations of global approaches by performing local contrast enhancement. However, this method relies on two essential hyperparameters: the number of tiles and the clip limit. An improper hyperparameter selection may heavily decrease the image quality toward its degradation. Considering the lack of methods to efficiently determine these hyperparameters, this article presents a learning-based hyperparameter selection method for the CLAHE technique. The proposed supervised method was built and evaluated using contrast distortions from well-known image quality assessment datasets. Also, we introduce a more challenging dataset containing over 6200 images with a large range of contrast and intensity variations. The results show the efficiency of the proposed approach in predicting CLAHE hyperparameters with up to 0.014 RMSE and 0.935 R2 values. Also, our method overcomes both experimented baselines by enhancing image contrast while keeping its natural aspect.

Image contrast enhancement using triple clipped dynamic histogram equalisation based on standard deviation

Many histogram equalisations-based methods have been proposed to be applied in contrast enhancement. However, a few methods that can simultaneously create a natural enhancement in images with low, median, and high brightness ranges are suggested. Here, a robust contrast enhancement algorithm, which is called triple clipped dynamic histogram equalisation based on standard deviation (TCDHE-SD), is proposed. In the proposed method, the histogram of the input image is partitioned into three parts with approximately the same number of pixels based on the standard deviation. Then, the process of histogram clipping is performed on each sub-histogram. After that, all histograms will be mapped to a new dynamic range by means of applying some simple calculations, and finally, the sub-histogram equalisation process will be performed independently. This method is proposed to achieve the multiple purposes of the maximum average information content (entropy), controlling the enhancement ratio and preserving reasonable brightness. It also provides a natural enhancement by generating clear images with maximum details. The performance assessment of the proposed method in terms of entropy as well as visual quality based on the mean opinion score (MOS) indicates a significant advantage of it over the previous ones.

Quadri-Histogram Equalization for infrared images using cut-off limits based on the size of each histogram

In infrared images, the pixels representing the objects are hidden in a large number of background pixels with low contrast. Several effective contrast enhancement techniques exist in the state of the art today, however they cause the noise level added to the images to increase. The improvement of contrast is an indispensable procedure for the analysis of infrared images, due to the scarce temperature difference between the objects and the background, captured by the surveillance systems using infrared sensors. Therefore, a contrast enhancement algorithm for infrared imaging based on histogram equalization using clipping is presented in this article. The proposed algorithm divides the histogram into 4 subhistograms, then each subhistogram is modified with a cut limit based on the size of the subhistogram in order to limit the improvement of the contrast. The experimental results prove that the algorithm improves the contrast of infrared images by 99%, especially the contrast between the objects and the background of the infrared images preserving the mean brightness and decreasing the aggregate noise level of them. With the proposed algorithm, the background of the infrared image is restricted while the objects are visually contrasted.

Quality assessment tool for performance measurement of image contrast enhancement methods

An objective image quality assessment tool is proposed to measure image enhancement quality with emphasis on contrast. In the proposed tool, which is based on maximizing contrast with minimum artefact (MCMA), local and global properties of an image are measured through pixel-wise and histogram-wise features, respectively. To this aim, three sub-measures are introduced, each of which able to detect one contrast-related quality aspect: (i) low dynamic range of image; (ii) histogram shape preservation during image enhancement process; and (iii) local pixel diversity. These sub-measures are combined through a subjective test to adapt them to the mean opinion scores (MOSs) of a diverse set of training contrast-enhanced images. A regression algorithm performs the adaptation by fitting the three sub-measures to the MOS values and finding an optimal linear combination by maximizing the Pearson correlation. In order to evaluate the performance of the MCMA algorithm, another independent, subsequent, subjective test was performed on a set of images enhanced by various known contrast enhancement algorithms to obtain MOS values and to compare them with the output of the proposed MCMA method. The experimental results show that MCMA has the highest correlation to the MOS when compared to the existing tested contrast measurement tools.

No-reference quality assessment for contrast-distorted images based on multifaceted statistical representation of structure

In many real-world applications, images are prone to be degraded by contrast distortions during image acquisition. Quality assessment for contrast-distorted images is vital for benchmarking and optimizing the contrast-enhancement algorithms. To this end, this paper proposes a no-reference quality metric for contrast-distorted images based on Multifaceted Statistical representation of Structure (MSS). The “Multifaceted” has two meanings, namely (1) not only the luminance information, but also the chromatic information is used for structure representation. This is inspired by the fact that the chromatic information on the one hand affects the perception of image quality as well, and on the other hand it changes along with the contrast distortions. Therefore, the chromatic information should be integrated with the luminance information for quality assessment of contrast-distorted images, a fact most existing quality metrics overlook; (2) regarding structure representation, three aspects, i.e. spatial intensity, spatial distribution, and orientation of structures are calculated, which is enlightened by the fact that the human visual system (HVS) is sensitive to the three aspects of structures. Specifically, the image is first transformed from RGB to the S-CIELAB color space to obtain a representation that is more consistent with the characteristics of the HVS, as well as to separate the chromatic information from the luminance. Then the statistical structural features are extracted from both luminance and chromatic channels. Finally, the back propagation (BP) neural network is adopted to train a quality prediction model. Experimental results conducted on four public contrast-distorted image databases demonstrate the superiority of the proposed method to the relevant state-of-the-arts.

Automatic microarray image segmentation with clustering-based algorithms

Image segmentation, as a key step of microarray image processing, is crucial for obtaining the spot expressions simultaneously. However, state-of-art clustering-based segmentation algorithms are sensitive to noises. To solve this problem and improve the segmentation accuracy, in this article, several improvements are introduced into the fast and simple clustering methods (K-means and Fuzzy C means). Firstly, a contrast enhancement algorithm is implemented in image preprocessing to improve the gridding precision. Secondly, the data-driven means are proposed for cluster center initialization, instead of usual random setting. The third improvement is that the multi features, including intensity features, spatial features, and shape features, are implemented in feature selection to replace the sole pixel intensity feature used in the traditional clustering-based methods to avoid taking noises as spot pixels. Moreover, the principal component analysis is adopted for various feature extraction. Finally, an adaptive adjustment algorithm is proposed based on data mining and learning for further dealing with the missing spots or low contrast spots. Experiments on real and simulation data sets indicate that the proposed improvements made our proposed method obtains higher segmented precision than the traditional K-means and Fuzzy C means clustering methods.

Ramp Distribution-Based Contrast Enhancement Techniques and Over-Contrast Measure

Our approach to contrast enhancement (CE) of images is based on natural scene statistics (NSS). We show, in this paper, that the average intensity distribution of natural images can be linearly approximated to the ramp distribution in an ordered histogram domain as the contrast increases. Based on this finding, we propose ramp distribution-based global and local CE algorithms. The ramp distribution-based slant thresholding (RDST) algorithm is proposed as a global CE method which uses slant thresholding in an ordered histogram domain to yield a contrast-enhanced image. Also, the ramp distribution-based adaptive slant thresholding (RDAST) algorithm is proposed as a local CE method. It adaptively adjusts a slant angle of the ramp distribution in each block to suppress noise amplification in uniform regions and maximizes contrast in non-uniform regions. The RDAST also employs a scaled global modified histogram to minimize sensitivity to block size changes. Moreover, we propose a metric to measure the amount of over-contrast in an image to evaluate all CE algorithms more correctly. The experimental results show that the proposed algorithms have better or competitive performance as well as computational efficiency.

Modified Local and Global Contrast Enhancement Algorithm for Color Satellite Image

The quality of remotely sensed satellite images depends on the reflected electromagnetic radiation from the earth’s surface features. Lack of consistent and similar amounts of energy reflected by different features from the earth’s surface results in a poor contrast satellite image. Image enhancement is the image processing of improving the quality that the results are more suitable for display or further image analysis. In this paper, we present a detailed model for color image enhancement using the quaternion framework. We introduce a novel quaternionic frequency enhancement algorithm that can combine the color channels and the local and global image processing. The basic idea is to apply the α-rooting image enhancement approach for different image blocks. For this purpose, we split image in moving windows on disjoint blocks. The parameter alfa for every block and the weights for every local and global enhanced image driven through optimization of measure of enhancement (EMEC). Some presented experimental results illustrate the performance of the proposed approach on color satellite images in comparison with the state-of-the-art methods.

An Efficient Adaptive Algorithm for Electron Microscopic Image Enhancement and Feature Extraction

In this article, a block-based adaptive contrast enhancement algorithm has been proposed, which uses a modified sigmoid function for the enhancement and features extraction of electron microscopic images. The algorithm is based on a modified sigmoid function that adapts according to the input microscopic image statistics. For feature extraction, the contrast of the image is very important and authentic property by which this article enhances the visual quality of the image. In this work, for better contrast enhancement of image, a block based on input value, combined with a modified sigmoid function that is used as contrast enhancer provides better EMF values for a smaller block size. It provides localized contrast enhancement effects adaptively which is not possible using other existing techniques. Simulation and experimental results demonstrate that the proposed technique gives better results compared to other existing techniques when applied to electron microscopic images. After the enhancement of microscopic images of actinomycetes, various important features are shown, like coil or spiral, long filament, spore and rod shape structures. The proposed algorithm works efficiently for different dark and bright microscopic images.

Global and Adaptive Contrast Enhancement for Low Illumination Gray Images

Aiming at solving the problems of overall darkness, uneven illumination and low contrast of image under low illumination conditions, we present a global and adaptive contrast enhancement algorithm for low illumination gray images in this paper. The proposed algorithm is based on the Bilateral Gamma Adjustment function and combined with the particle swarm optimization (PSO). For the PSO, the gray standard variance is integrated into the evaluation function. To reconcile the dilemma of promoting the gray values of dark areas and suppressing the gray values of local bright areas at the same time, the information of entropy, edge content, and gray standard variance are used as the objective function for each particle to evaluate the gray image enhancement results. Then, the algorithm globally enhances the quality of the image by determining the optimal $\alpha $ value. Meanwhile, the learning factors of the PSO are updated during the iteration of optimization in the proposed algorithm. Compared with histogram equalization (HE), double plateau histogram equalization (DPHE), contrast limited adaptive histogram equalization (CLAHE), linear contrast stretching (LCS), adaptive gamma correction weighting distribution (AGCWD), the traditional PSO and MSF-PSO algorithm, the proposed algorithm significantly enhances the visual effect of the low illumination gray images. The experimental results demonstrate the superior capabilities of the proposed algorithm in enhancing the contrast of the image, such as improving the overall visual effect of the low illumination gray image and avoiding over-enhancement in the local area (s).

Contrast Enhancement of Industrial Radiography Images by Gabor Filtering with Automatic Noise Thresholding

The defect detection procedure of a radiographic image is a very important task. This is because of its importance regarding the safety of different industrial equipment. The defect detection procedures must reveal the defect region with the edges preserved. The radiography images are degraded by different noises caused by photon x-ray scattering, data acquisition and system errors. Due to the noise, radiography experts may encounter certain difficulties when extracting the defect region in the noisy images. This article presents a novel implementation of the Gabor filtering algorithm to improve contrast and denoise radiography images and detect the defects. Gabor filtering with automatic detection of noise level is a powerful contrast enhancement algorithm, but it tends to remove specific details from the processed images passing them off as noise. The performance of the proposed approach, the region defect, is revealed in radiographic images of different welded specimens. Results show major improvement not only in the noise attenuation, but also in the preservation of small details and the defect region.

A Fast Image Contrast Enhancement Algorithm Using Entropy-Preserving Mapping Prior

Contrast enhancement is a crucial image processing step for image quality control. However, images enhanced by conventional contrast enhancement methods can have negative effects on the performance of image quality control. The most commonly observed effects are over- and under-enhancement effects on images, which cause significant loss of fine textures in images. This paper developed a new contrast enhancement algorithm based on an entropy-preserving mapping prior that improves on conventional contrast enhancement methods. By creating a closed-form solution for enhancing the image contrast under this novel prior and learning the coefficients of the solution using an unsupervised learning strategy, an image’s contrast and texture can be effectively recovered. The experimental results verify that our proposed method clearly outperforms the existing state-of-the-art methods in terms of both quantitative estimation and qualitative human visual inspection.