Showing papers on "Histogram equalization published in 2021"

Histogram Equalization Variants as Optimization Problems: A Review

Abstract: In the consumer electronics field, the main challenge in image processing is to preserve the original brightness. Histogram Equalization (HE) is one of the simplest and widely used methods for contrast enhancement. However, HE does not suit into the consumer electronics field as this procedure flattens the histogram by distributing the entire gray levels uniformly. Therefore, several HE variants have been proposed based on proper histogram segmentation, histogram weighting, and range optimization techniques to overcome this flattening effect. However, sometimes these modifications become complex and computationally expensive. Recently, researchers have formulated the HE variants for image enhancement as optimization problems and solved, using Nature-Inspired Optimization Algorithms (NIOA), which starts a new era in the image enhancement field. This study presents an up-to-date review over the application of NIOAs for HE variants in image enhancement domain. The main issues which are involved in the application of NIOAs with HE are also discussed here.

DWFCAT: Dual Watermarking Framework for Industrial Image Authentication and Tamper Localization

Abstract: The image data received through various sensors are of significant importance in Industry 4.0. Unfortunately, these data are highly vulnerable to various malicious attacks during its transit to the destination. Although the use of pervasive edge computing (PEC) with the Internet of Things (IoT) has solved various issues, such as latency, proximity, and real-time processing, but the security and authentication of data between the nodes is still a significant concern in PEC-based industrial-IoT scenarios. In this article, we present “DWFCAT,” a dual watermarking framework for content authentication and tamper localization for industrial images. The robust and fragile watermarks along with overhead bits related to the cover image for tamper localization are embedded in different planes of the cover image. We have used discrete cosine transform coefficients and exploited their energy compaction property for robust watermark embedding. We make use of a four-point neighborhood to predict the value of a predefined pixel and use it for embedding the fragile watermark bits in the spatial domain. Chaotic and deoxyribonucleic acid encryption is used to encrypt the robust watermark before embedding to enhance its security. The results indicate that DWFCAT can withstand a range of hybrid signal processing and geometric attacks, such as Gaussian noise, salt and pepper, joint photographic experts group (JPEG) compression, rotation, low-pass filtering, resizing, cropping, sharpening, and histogram equalization. The experimental results prove that the DWFCAT is highly efficient compared with the various state-of-the-art approaches for authentication and tamper localization of industrial images.

Social Spider Optimization Based Optimally Weighted Otsu Thresholding for Image Enhancement

Abstract: Image enhancement corresponds to processing an image to obtain an image with more perceptual details. In this paper, a social spider optimization (SSO) based scheme is proposed to generate an enhanced image which contains higher contrast and minimum change of entropy with respect to the original image. The proposed method employs histogram equalization with a modified cumulative distribution function to obtain a mapping function. A three-step process is followed to modify the original histogram. The first step is to segment the image histogram into two parts using the Otsu's thresholding method. Then both of the upper and lower histograms are weighted as well as thresholded to control the level of enhancement. The constraint parameters for modification are obtained by SSO. After applying the constrain parameters on the histograms, mean shift correction is performed to ensure there is a minimum level of mean shift from input image to output image. The results indicate that proposed method achieves better color preservation, and balanced contrast enhancement in comparison to existing techniques. The proposed scheme also leads to significant feature enhancement, low contrast boosting, and brightness preservation in the enhanced image, while preserving the natural feel of the original image.

Dense Prediction and Local Fusion of Superpixels: A Framework for Breast Anatomy Segmentation in Ultrasound Image With Scarce Data

Abstract: Segmentation of the breast ultrasound (BUS) image is an important step for subsequent assessment and diagnosis of breast lesions. Recently, Deep-learning-based methods have achieved satisfactory performance in many computer vision tasks, especially in medical image segmentation. Nevertheless, those methods always require a large number of pixel-wise labeled data that is expensive in medical practices. In this study, we propose a new segmentation method by dense prediction and local fusion of superpixels for breast anatomy with scarce labeled data. First, the proposed method generates superpixels from the BUS image enhanced by histogram equalization, a bilateral filter, and a pyramid mean shift filter. Second, using a convolutional neural network (CNN) and distance metric learning-based classifier, the superpixels are projected onto the embedding space and then classified by calculating the distance between superpixels’ embeddings and the centers of categories. By using superpixels, we can generate a large number of training samples from each BUS image. Therefore, the problem of the scarcity of labeled data can be better solved. To avoid the misclassification of the superpixels, $K$ -nearest neighbor (KNN) is used to reclassify the superpixels within every local region based on the spatial relationships among them. Fivefold cross-validation was taken and the experimental results show that our method outperforms several often used deep-learning methods under the condition of the absence of a large number of labeled data (48 BUS images for training and 12 BUS images for testing).

Detection of COVID-19 from CT Lung Scans Using Transfer Learning.

Abstract: This paper aims to investigate the use of transfer learning architectures in the detection of COVID-19 from CT lung scans. The study evaluates the performances of various transfer learning architectures, as well as the effects of the standard Histogram Equalization and Contrast Limited Adaptive Histogram Equalization. The findings of this study suggest that transfer learning-based frameworks are an alternative to the contemporary methods used to detect the presence of the virus in patients. The highest performing model, the VGG-19 implemented with the Contrast Limited Adaptive Histogram Equalization, on a SARS-CoV-2 dataset, achieved an accuracy and recall of 95.75% and 97.13%, respectively.

Underwater image enhancement using contrast limited adaptive histogram equalization and layered difference representation

Abstract: Underwater images, which have low contrast and visibility as a result of selective attenuation based on the wavelength of the light passing through water, needs some corrections to extract meaningful information from them. In this paper, we aim to combine two different approaches; global and local contrast enhancement techniques, to obtain better visual quality while enhancing image contrasts on underwater images. While global technique (LDR) ensures the overall enhancement of the image, local technique (CLAHE) considers local brightness features of the image in RGB color space. The proposed method also applies local color correction on underwater image. While methods in the literature apply various approaches on the global histogram of channels, our method divides underwater image into non-overlapping sub-blocks and apply histogram equalization on them. The method uses HSV color space and especially S, V components for color correction. The results of the qualitative analysis show that it produces very good images, in contrast, color, and detail compared to other enhancement methods. The proposed method also decreases the effect of under- and over-enhanced areas and the blue-green effect on the output image. However, the visibility of the objects in the images are increased by color correction. For quantitative analysis, the proposed method produces the highest average value of entropy (7.83), EMEE (32.06), EME (40.97), average gradient (152.55), and Sobel count (130393) for 200 underwater images.

Brain Tumor Detection using Deep Learning and Image Processing

Abstract: Brain Tumor Detection is one of the most difficult tasks in medical image processing. The detection task is difficult to perform because there is a lot of diversity in the images as brain tumors come in different shapes and textures. Brain tumors arise from different types of cells and the cells can suggest things like the nature, severity, and rarity of the tumor. Tumors can occur in different locations and the location of tumors can suggest something about the type of cells causing the tumor which can aid further diagnosis. The task of brain tumor detection can become aggravating by the problems which are present in almost all digital images eg. illumination problems. Tumor and non-tumor images can have overlapping image intensities which makes it difficult for any model to make good predictions from raw images. This paper proposes a novel method to detect brain tumors from various brain images by first carrying out different image preprocessing methods ie. Histogram equalization and opening which was followed by a convolutional neural network. The paper also discusses other image preprocessing techniques apart from the ones that are finalized for training and their impact on our dataset. The experimental study was carried on a dataset with different tumor shapes, sizes, textures, and locations. Convolutional Neural Network (CNN) was employed for the task of classification. In our work, CNN achieved a recall of 98.55% on the training set, 99.73% on the validation set which is very compelling.

A Novel Contrast Enhancement Technique using Gradient-Based Joint Histogram Equalization

Abstract: Image enhancement by histogram equalization reduces the number of gray levels that lead to information loss and unnatural appearance. This paper aims to improve the contrast and preserve information and edge details by employing gradient-based joint histogram equalization. It is achieved by a multiscale-based dark pass filter, which gives the pixel’s edge information. A joint histogram is computed from the edge information and the gray-level distribution of the low contrast image to develop a discrete function. This discrete function is mapped to uniform distribution to get the final enhanced image. The proposed method is experimented on Kodak, USC-SIPI, and CSIQ databases and analyzed using various performance measures such as Contrast, standard deviation, contrast improvement index, structural similarity index, normalized entropy, and normalized mean brightness error. It is observed that the proposed method provides the highest Contrast values of 86.2, 85.79, and 86.02 in Kodak, USC-SIPI, and CSIQ databases, respectively. Normalized entropy value is found to be highest for the proposed method for all the databases. This is noticed to be 0.89, 0.84, and 0.85 for the databases Kodak, USC-SIPI, and CSIQ, respectively. The degree of the uniform distribution is measured by Kullback–Leibler distance. The proposed method produces more uniformity than other techniques available in the literature for all the three databases.

Triple Clipped Histogram-Based Medical Image Enhancement Using Spatial Frequency

Abstract: In this paper, a novel triple clipped histogram model-based fusion approach has been proposed to improve the basics features, brightness preservation and contrast of the medical images. This incorporates the features of the equalized image and input image together. In the initial step, the low-contrast medical image is equalized using the triple clipped dynamic histogram equalization technique for which the histogram of the input medical image is split into three sections on the basis of standard deviation with almost equal number of pixels. The clipping process of the histogram is performed on every histogram section and mapped to a new dynamic range using simple calculations. In the second step, the sub-histogram equalization process is performed separately. Approximation and detail coefficients of equalized and input images are separated using discrete wavelet transform (DWT). Thereafter, the approximation coefficients are modified using some basic calculation-based fusion which involves singular value decomposition (SVD) and its inverse. Detail coefficients are fused using spatial frequency features. This yields modified approximation and detail coefficients for an enhanced image. Finally, inverse discrete wavelet transform (IDWT) has been applied to the modified coefficients which result in an enhanced image with improved visual quality. These improvements are analyzed qualitatively and quantitatively.

Application of Histogram Equalization for Image Enhancement in Corrosion Areas

Abstract: In this paper, an image enhancement algorithm is presented for identification of corrosion areas and dealing with low contrast present in shadow areas of an image. This algorithm uses histogram equalization processing under the hue-saturation-intensity model. First of all, an etched image is transformed from red-green-blue color space to hue-saturation-intensity color space, and only the luminance component is enhanced. Then, part of the enhanced image is combined with the original tone component, followed by saturation and conversion to red-green-blue color space to obtain the enhanced corrosion image. Experimental results show that the proposed method significantly improves overall brightness, increases contrast details in shadow areas, and strengthens identification of corrosion areas in the image.

Low-light image joint enhancement optimization algorithm based on frame accumulation and multi-scale Retinex

Abstract: It is acknowledged that images taken under low-light conditions are easily affected by low visible light and noise, which can cause important image information loss, low signal-to-noise ratio, blurred edges, and poor subjective vision. Related researchers have targeted some solutions are proposed for the above problems, such as histogram equalization and gamma correction, but all have problems such as edge loss and color distortion. Based on the above problems, this paper proposes a low-light image enhancement optimization algorithm based on frame accumulation and multi-scale R e t i n e x joint processing. First, single-channel image frame accumulation filtering is performed on the low-light image, and then the image is jointly enhanced with the optimized multi-scale R e t i n e x algorithm. The experimental results show that the peak signal-to-noise ratio of the image processed by the joint enhancement optimization algorithm used in this article is increased to 51.2041 dB, which is 15.2633 dB higher than the original image and 1.799 dB higher than the image processed by the traditional M S R C R algorithm, structure similarity increased by 0.12, the enhanced image has higher grayscale resolution and signal-to-noise ratio, while retaining more image edges and detailed texture, reducing color distortion to a certain extent, and the generation of aperture artifacts is weakened. It has a high structural similarity to the original image. The overall quality of the image has been improved to a certain extent, and the subjective and objective evaluations are better than traditional algorithms. Finally, the comparison experiment verifies the effectiveness and practicability of the joint enhancement optimization algorithm in this paper to improve the low-light image quality, Which provides a new pre-processing method for future intelligent target detection, and has important research value.

Covid-19 Classification Based on Gray-Level Co-occurrence Matrix and Support Vector Machine

Abstract: Covid-19 is a new epidemic recently. Early diagnosis of related diseases relies on the analysis of the patient’s clinical symptoms and kit testing. To identify this disease efficiently and automatically, we proposed an effective classification system by identifying CT images of chest based on Histogram Equalization (HE), Gray-Level Co-Occurrence Matrix (GLCM) and Support Vector Machine (SVM) algorithm. We collected 148 CT images of healthy people and 148 CT images of patients as our first-hand dataset, the size of which is 512*512*3. To enhance the features of the images, we center cropped the images to 400*400*3. GLCM is an efficient method to extract features focusing on the texture features and SVM can be accurately utilized to classify. In our experiment, we proposed a 10-fold Cross-Validation (CV) to ensure the reliability of experimental results. The results show that the average accuracy of our system is better than other common methods. The performance of our proposed method is effective for Covid-19 identification.

Low dynamic range histogram equalization (LDR-HE) via quantized Haar wavelet transform

Abstract: Conventional contrast enhancement methods stretch histogram bins to provide a uniform distribution. However, they also stretch the existing natural noises which cause abnormal distributions and annoying artifacts. Histogram equalization should mostly be performed in low dynamic range (LDR) in which noises are generally distributed in high dynamic range (HDR). In this study, a novel image contrast enhancement method, called low dynamic range histogram equalization (LDR-HE), is proposed based on the Quantized Discrete Haar Wavelet Transform (HWT). In the frequency domain, LDR-HE performs a de-boosting operation on the high-pass channel by stretching the high frequencies of the probability mass function to the nearby zero. For this purpose, greater amplitudes than the absolute mean frequency in the high pass band are divided by a hyper alpha parameter. This damping parameter, which regulates the global contrast on the processed image, is the coefficient of variations of high frequencies, i.e., standard deviation divided by mean. This fundamental procedure of LDR-HE definitely provides a scalable and controlled dynamic range reduction in the histograms when the inverse operation is done in the reconstruction phase in order to regulate the excessive contrast enhancement rate. In the experimental studies, LDR-HE is compared with the 14 most popular local, global, adaptive, and brightness preserving histogram equalization methods. Experimental studies qualitatively and quantitatively show promising and encouraging results in terms of different quality measurement metrics such as mean squared error (MSE), peak signal-to-noise ratio (PSNR), Contrast Improvement Index (CII), Universal Image Quality Index (UIQ), Quality-aware Relative Contrast Measure (QRCM), and Absolute Mean Brightness Error (AMBE). These results are not only assessed through qualitative visual observations but are also benchmarked with the state-of-the-art quantitative performance metrics.

Detection and classification of lung diseases for pneumonia and Covid-19 using machine and deep learning techniques.

Abstract: Since the arrival of the novel Covid-19, several types of researches have been initiated for its accurate prediction across the world. The earlier lung disease pneumonia is closely related to Covid-19, as several patients died due to high chest congestion (pneumonic condition). It is challenging to differentiate Covid-19 and pneumonia lung diseases for medical experts. The chest X-ray imaging is the most reliable method for lung disease prediction. In this paper, we propose a novel framework for the lung disease predictions like pneumonia and Covid-19 from the chest X-ray images of patients. The framework consists of dataset acquisition, image quality enhancement, adaptive and accurate region of interest (ROI) estimation, features extraction, and disease anticipation. In dataset acquisition, we have used two publically available chest X-ray image datasets. As the image quality degraded while taking X-ray, we have applied the image quality enhancement using median filtering followed by histogram equalization. For accurate ROI extraction of chest regions, we have designed a modified region growing technique that consists of dynamic region selection based on pixel intensity values and morphological operations. For accurate detection of diseases, robust set of features plays a vital role. We have extracted visual, shape, texture, and intensity features from each ROI image followed by normalization. For normalization, we formulated a robust technique to enhance the detection and classification results. Soft computing methods such as artificial neural network (ANN), support vector machine (SVM), K-nearest neighbour (KNN), ensemble classifier, and deep learning classifier are used for classification. For accurate detection of lung disease, deep learning architecture has been proposed using recurrent neural network (RNN) with long short-term memory (LSTM). Experimental results show the robustness and efficiency of the proposed model in comparison to the existing state-of-the-art methods.

No-Reference Image Contrast Evaluation by Generating Bidirectional Pseudoreferences

Abstract: This article proposes a simple yet reliable no-reference image contrast evaluator (NICE) by generating bidirectional pseudoreferences (BPR). Different from the existing no-reference metrics that only operate on the contrast distorted image (CDI) itself, our proposed NICE-BPR measures the deviations of a CDI to its corresponding aggravated and enhanced counterparts (i.e., BPRs) in a hybrid feature space. Given a CDI, we first perform contrast aggravation and contrast enhancement using gamma correction and histogram equalization, respectively. Then, hybrid contrast-aware features are, respectively, extracted from the CDI and its corresponding BPRs via the analysis of histogram, entropy, and structure. The features obtained from the CDI are one-by-one compared with those from the BPRs to derive the bidirectional feature deviation vector. Finally, a quality predictor is built by learning a regression model to fuse the feature vector into a continuous quality score. Extensive experiments on several databases well-demonstrate the superiority of NICE-BPR.

Adaptive Entropy Index Histogram Equalization for Poor Contrast Images

Abstract: Hidden details and lack of image contrast can be attributed to limited user experience, poor device quality, environment settings during image acquisition, and illumination. To address these problems, techniques based on histogram equalization (HE) have been frequently used to reduce these problems and to improve image contrast. However, the resultant images obtained by techniques often appear unnatural possibly due to washed-out effects and unwanted artifacts. This study proposes a new technique called adaptive entropy index histogram equalization (AEIHE) that belongs to the local sub-class of HE-based contrast enhancement techniques. AEIHE initially divides the image into three sub-images to enhance and highlight its local details. Each of these sub-images uses a different contextual region and clip limit based on the richness of their information and their structure, both of which are adaptively determined by AEIHE. A new parameter called Entropy-Index is then used to ensure the high information richness of the resultant sub-image while preserving its structure. AEIHE guarantees the production of an excellent resultant image by combining enhanced sub-images. Quantitative evaluations of 819 images show that AEIHE has successfully produced excellent resultant images with improved contrast, highlighted local details, and minimized effects of artifacts and unwanted noise. Therefore, AEIHE has a high application potential in the medical imaging, machine vision, and industrial domains.

An edge-aware based adaptive multi-feature set extraction for stereo matching of binocular images

Abstract: Object Stereo Vision has conventionally been one of the deeply examined areas in computer vision. Stereo matching is employed in numerous modern applications, including robot navigation, augmented reality, and automotive applications. Even though it has a long research history, it is still challenging for the edges of textureless, discontinues, and occluded regions under radiometric variation. This research article proposes a modified histogram equalization, a novel feature extraction, a spatial gradient model, and matching cost, which is robust and stable to images taken in different radiometric variations. The proposed method reduced the average percentage of bad pixels to 3.35 and reduced the relative mean square error (RMSE) up to 30.08 on the Middlebury dataset for different illumination and exposure values. Quantitative and qualitative evaluation of the proposed method demonstrates significant improvement in increasing PSNR and decreasing bad pixel percentage against radiometric variation and state-of-the-art local stereo matching algorithms.

Image Enhancement Using Exposure and Standard Deviation-Based Sub-image Histogram Equalization for Night-time Images

Abstract: In this paper, a novel exposure and standard deviation-based sub-image histogram equalization technique is proposed for the enhancement of low-contrast nighttime images. Initially, the histogram of the input image is clipped to avoid the over-enhancement. The clipped histogram is partitioned into three sub-histograms depending on the exposure threshold and standard deviation values. After that, the individual sub-histogram is equalized independently. At last, a new enhanced image is produced after combining each equalized sub-images. The simulation results reveal that our proposed method outperforms over other histogram equalized techniques by providing a good visual quality image. The proposed method minimizes the entropy loss and preserves the brightness of the enhanced image efficiently by reducing the absolute mean brightness error (AMBE). It also maintains the structural similarity with the input image and controls the over-enhancement rate effectively.

Importance of Image Enhancement and CDF for Fault Assessment of Photovoltaic Module Using IR Thermal Image

Abstract: Infrared thermography is the science of measuring the infrared energy emitted by an object, translating it to apparent temperature variance, and displaying the result as an infrared image. Significantly, acquiring thermal images delivers distinctive levels of temperature differences in solar panels that correspond to their health status, which is beneficial for the early detection of defects. The proposed algorithm aims to analyze the thermal solar panel images. The acquired thermal solar panel images were segmented into solar cell sizes to provide more detailed information by region or cell area instead of the entire solar panel. This paper uses both the image histogram information and its corresponding cumulative distribution function (CDF), useful for image analysis. The acquired thermal solar panel images are enhanced using grayscale, histogram equalization, and adaptive histogram equalization to represent a domain that is easier to analyze. The experimental results reveal that the extraction results of thermal images provide better histogram and CDF features. Furthermore, the proposed scheme includes the convolutional neural network (CNN) for classifying the enhanced images, which shows that a 97% accuracy of classification was achieved. The proposed scheme could promote different thermal image applications—for example, non-physical visual recognition and fault detection analysis.

RDH-based dynamic weighted histogram equalization using for secure transmission and cancer prediction

Abstract: Image contrast enhancement is a prerequisite and plays a very important role in many image processing field like medical imaging, face recognition, computer-vision, and satellite imaging. In this paper we proposed reversible data hiding based Limited Dynamic Weighted Histogram Equalization techniques for Abnormal Tumor regions which improve the contrast, transmit the hidden secret information, preserve its brightness intensity and original appearance of the image. We have implemented Otsu’s method to segment the input image into two sub-histogram regions of interest (ROI) and non-region of interest; furthermore, the sub-histograms ROI region equalized independently without of over-enhancement and any loss of hidden and diagnostic data. Our proposed method is more efficient to precisely preserve the brightness of the image and extract the secret information with contrast image reversibly; besides, different classifiers are used to classify the brain cancer to check the performance of our proposed method.

Histogram Adjustment of Images for Improving Photogrammetric Reconstruction.

Abstract: The accuracy of photogrammetric reconstruction depends largely on the acquisition conditions and on the quality of input photographs. This paper proposes methods of improving raster images that increase photogrammetric reconstruction accuracy. These methods are based on modifying color image histograms. Special emphasis was placed on the selection of channels of the RGB and CIE L*a*b* color models for further improvement of the reconstruction process. A methodology was proposed for assessing the quality of reconstruction based on premade reference models using positional statistics. The analysis of the influence of image enhancement on reconstruction was carried out for various types of objects. The proposed methods can significantly improve the quality of reconstruction. The superiority of methods based on the luminance channel of the L*a*b* model was demonstrated. Our studies indicated high efficiency of the histogram equalization method (HE), although these results were not highly distinctive for all performed tests.