Non-uniform Illumination Problem Research Articles

Fractional and B-COSFIRE filter based approach for efficient segmentation of retinal blood vessels

The morphological structure of retinal blood vessels plays an important role in diagnosing ophthalmic diseases such as glaucoma and diabetic retinopathy. Diabetic retinopathy is one of the leading causes of blindness worldwide. Because of the need to examine a large number of individuals on a daily basis, it is indeed challenging for ophthalmologists to analyze the complex retinal vasculature of every outpatient. Automated segmentation of retinal blood vessels can be of significant aid in this labor-intensive process. This work proposes an unsupervised approach for retinal blood vessel segmentation. Here, we enhance the performance of the B-COSFIRE filters for segmentation of the retinal vasculature by denoising a retinal image using a fractional filter derived from a left/forward weighted fractional integral prior to the vascular enhancement by B-COSFIRE filters. Also, we utilize hysteresis thresholding rather than a single global threshold to obtain the final segmented vessels enhanced by the B-COSFIRE filters. This helps to avoid the problem of nonuniform illumination and poor contrast in retinal images.

EFFICIENT RETINAL IMAGE ENHANCEMENT USING MORPHOLOGICAL OPERATIONS

Manual analysis of retinal images is a complicated and time-consuming task for ophthalmologists. Retinal images are susceptible to non-uniform illumination, poor contrast, transmission error, and noise problems. For the detection of retinal abnormalities, an efficient technique is required that can identify the presence of retinal complications. This paper proposes a methodology to enhance retinal images that use morphological operations to improve the contrast and bring out the fine details in the suspicious region. The enhancement plays a vital role in detecting abnormalities in the retinal images. Luminance gain metric ([Formula: see text] is obtained from Gamma correction on luminous channel of [Formula: see text]*[Formula: see text]*[Formula: see text] (hue, saturation, and value) color model of retinal image to improve luminosity. The efficiency and strength of the proposed methodology are evaluated using the performance evaluation parameters peak signal to noise ratio (PSNR), mean square error (MSE), mean absolute error (MAE), feature structural similarity index metric (FSIM), structural similarity index metric (SSIM), spectral residual index metric (SRSIM), Reyligh feature similarity index metric (RFSIM), absolute mean brightness error (AMBE), root mean square error (RMSE), image quality index (IQI), and visual similarity index (VSI). It has been revealed from the results and statistical analysis using the Friedman test that the proposed method outperforms existing state-of-the-art enhancement techniques.

Underwater image enhancement method with non-uniform illumination based on Retinex and ADMM

In order to solve the image blurring and distortion problem caused by underwater non-uniform and low illumination, this paper proposes an underwater image enhancement algorithm based on the Retinex theory and the Alternating Direction Method of Multipliers (ADMM). Firstly, the L component of the original image in the Lab space is extracted as the initial illumination map, and an Augmented Lagrange Multiplier (ALM) framework is constructed based on the ADMM to optimize the initial illumination map in order to obtain an accurate illumination image. In addition, the illumination map is further corrected in the luminance region with the Gamma Correction. Secondly, combined with the color constancy characteristics in the Retinex theory, the reflected image of the object is obtained. Finally, the bilateral filter is picked to suppress the underwater noise and obtain a more detailed enhanced image. The experimental results show that the underwater image enhancement algorithm can effectively solve the non-uniform illumination problem caused by natural light or artificial light source and improve the underwater image quality, thus having a better performance than other algorithms.

Face detection in still images under occlusion and non-uniform illumination

Face detection is important part of face recognition system. In face recognition, face detection is taken not so seriously. Face detection is taken for granted; primarily focus is on face recognition. Also, many challenges associated with face detection, increases the value of TN (True Negative). A lot of work has been done in field of face recognition. But in field of face detection, especially with problems of face occlusion and non-uniform illumination, not so much work has been done. It directly affects the efficiency of applications linked with face detection, example face recognition, surveillance, etc. So, these reasons motivate us to do research in field of face detection, especially with problems of face occlusion and non-uniform illumination. The main objective of this article is to detect face in still image. Experimental work has been conducted on images having problem of face occlusion and non-uniform illumination. Experimental images have been taken from public dataset AR face dataset and Color FERET dataset. One manual dataset has also been created for experimental purpose. The images in this manual dataset have been taken from the internet. This involves making the machine intelligent enough to acquire the human perception and knowledge to detect, localize and recognize the face in an arbitrary image with the same ease as humans do it. This article proposes an efficient technique for face detection from still images under occlusion and non-uniform illumination. The authors have presented a face detection technique using a combination of YCbCr, HSV and L × a × b color model. The proposed technique improved results in terms of Accuracy, Detection Rate, False Detection Rate and Precision. This technique can be useful in the surveillance and security related applications.

L's approach: illumination pattern estimation technique for optical microscopy

We propose a novel solution to the correction of illumination nonuniformity without removing the imaging sample. Calibration of the spatial illumination pattern in reflectance microscopy is challenging due to the fact that the illumination source is colocated with the objective lens and therefore cannot be observed directly. Our proposed methodology overcomes this by collecting three spatially translated images in a strategic way. We prove that 'log-illumination pattern' recovery can be reformulated as a deconvolution of log-ratio of captured images, and develop an efficient, noise-robust implementation. Experiments with simulated and reflectance microscopy data verify the effectiveness of our proposed approach. LAY DESCRIPTION: The proposed technique overcomes a common problem of nonuniform illumination in microscopy. For the case of reflectance microscopy, we show that a few images with large amounts of overlap can be used to recover the illumination pattern. In conjunction with an image formation model, the recovered illumination pattern may be used to correct the images captured under similar illuminationconditions.

An Optimized Approach for Underwater Image Dehazing and Colour Correction

Underwater image processing is essential to meet sustainable development goals. Underwater images are susceptible to colour loss, blurriness and are hazy in nature due to presence of suspended particles. Backscattering leads to haze content in image whereas absorption causes colour distortion. Due to scattering, absorption effects and varying wavelength of different colours, there is a problem of poor visibility, non-uniform illumination and colour fading. That’s why, for real time applications, underwater images demand high level colour correction and dehazing to ensure feature extraction, visibility enhancement, edge contrast improvement and preservation of image characteristics. Requirement is to design suitable underwater image processing technique that adapts according to perceived environment with different noise levels and non-uniform illumination. Algorithm should be efficient and possess higher functionality to enhance real-world ocean environment images.

Dark Channel Applied for Reduction of the Effects of Non-uniform Illumination in Image Binarization

Non-uniform illumination is a common issue in images acquired in uncontrolled environments. Elimination or reduction of the non-uniform illumination problem is required in order to get an accurate image binarization. This paper introduces the combination of the dark channel and the atmospheric scattering model along with the k-means segmentation to reduce the effects of non-uniform illumination conditions in image binarization. The results show the effectiveness and robustness of this approach.

A Hybrid Proposed Fundus Image Enhancement Framework for Diabetic Retinopathy

Diabetic retinopathy (DR) is a complication of diabetes and is known as visual impairment, and is diagnosed in various ethnicities of the working-age population worldwide. Fundus angiography is a widely applicable modality used by ophthalmologists and computerized applications to detect DR-based clinical features such as microaneurysms (MAs), hemorrhages (HEMs), and exudates (EXs) for early screening of DR. Fundus images are usually acquired using funduscopic cameras in varied light conditions and angles. Therefore, these images are prone to non-uniform illumination, poor contrast, transmission error, low brightness, and noise problems. This paper presents a novel and real-time mechanism of fundus image enhancement used for early grading of diabetic retinopathy, macular degeneration, retinal neoplasms, and choroid disruptions. The proposed system is based on two folds: (i) An RGB fundus image is initially taken and converted into a color appearance module (called lightness and denoted as J) of the CIECAM02 color space model to obtain image information in grayscale with bright light. Afterwards, in step (ii), the achieved J component is processed using a nonlinear contrast enhancement approach to improve the textural and color features of the fundus image without any further extraction steps. To test and evaluate the strength of the proposed technique, several performance and quality parameters—namely peak signal-to-noise ratio (PSNR), contrast-to-noise ratio (CNR), entropy (content information), histograms (intensity variation), and a structure similarity index measure (SSIM)—were applied to 1240 fundus images comprised of two publicly available datasets, DRIVE and MESSIDOR. It was determined from the experiments that the proposed enhancement procedure outperformed histogram-based approaches in terms of contrast, sharpness of fundus features, and brightness. This further revealed that it can be a suitable preprocessing tool for segmentation and classification of DR-related features algorithms.

Remote Sensing Image Haze Removal Using Gamma-Correction-Based Dehazing Model

Haze is evident in most remote sensing (RS) images, particularly for the RS scenes captured in inclement weather, which severely hinders image interpretation. In this paper, two simple yet effective visibility restoration formulas are proposed for RGB-channel RS (RRS) images and multi-spectral RS (MSRS) images, respectively. More specifically, a robust gamma-correction-based dehazing model (RGDM) is first defined, which can better address the non-uniform illumination problem in hazy images. Then, the scene albedo restoration formula (SARF) used for the RRS images is obtained by imposing the existing prior knowledge on this RGDM, which enables us to simultaneously eliminate the interferences of haze and non-uniform illumination. In subsequence, according to Rayleigh’s law, an expanded restoration formula (E-SARF) is further developed for MSRS data. Using the proposed E-SARF, the spatially varying haze in each band can be thoroughly removed without using any extra information. The experiments are conducted on the challenging RRS and MSRS images, including images with non-uniform illumination, non-uniform haze distribution, and heavy haze. The results reveal that the SARF and the E-SARF are superior to most other state-of-the-art techniques in terms of both the recover quality and the implementation efficiency.

Nonuniform Illumination Correction Algorithm for Underwater Images Using Maximum Likelihood Estimation Method

Scattering and absorption of light is main reason for limited visibility in water. The suspended particles and dissolved chemical compounds in water are also responsible for scattering and absorption of light in water. The limited visibility in water results in degradation of underwater images. The visibility can be increased by using artificial light source in underwater imaging system. But the artificial light illuminates the scene in a nonuniform fashion. It produces bright spot at the center with the dark region at surroundings. In some cases imaging system itself creates dark region in the image by producing shadow on the objects. The problem of nonuniform illumination is neglected by the researchers in most of the image enhancement techniques of underwater images. Also very few methods are discussed showing the results on color images. This paper suggests a method for nonuniform illumination correction for underwater images. The method assumes that natural underwater images are Rayleigh distributed. This paper used maximum likelihood estimation of scale parameter to map distribution of image to Rayleigh distribution. The method is compared with traditional methods for nonuniform illumination correction using no-reference image quality metrics like average luminance, average information entropy, normalized neighborhood function, average contrast, and comprehensive assessment function.

Quality Analysis of Indian Basmati Rice Grains using Top-Hat Transformation

is one of the most important cereal grains. Rice is a good source of complex carbohydrates and is rich in several other essential nutrients. The paper presents a solution for quality analysis of Indian Basmati rice grains using Top-hat Transformation. In this paper the problem of Non-uniform Illumination for quality assessment is defined which show their effects in the process of extracting objects from the background and cause segmentation errors. The proposed method for quality assessment of Indian Basmati rice grains using Top-hat Transformation which achieves high degree of accuracy in correcting the effects of the Non-uniform Illumination than Computer Vision Inspection. The proposed method based on Morphological features is developed for counting the number of Indian Basmati rice grains with Normal grains, Long grains and Small grains. Keywords-hat Transformation, Quality, Morphological operations, Basmati rice grains, Parameters

Optimization and enhancement of H&E stained microscopical images by applying bilinear interpolation method on lab color mode

BackgroundHematoxylin & Eosin (H&E) is a widely employed technique in pathology and histology to distinguish nuclei and cytoplasm in tissues by staining them in different colors. This procedure helps to ease the diagnosis by enhancing contrast through digital microscopes. However, microscopic digital images obtained from this technique usually suffer from uneven lighting, i.e. poor Koehler illumination. Several off-the-shelf methods particularly established to correct this problem along with some popular general commercial tools have been examined to find out a robust solution.MethodsFirst, the characteristics of uneven lighting in pathological images obtained from the H&E technique are revealed, and then how the quality of these images can be improved by employing bilinear interpolation based approach applied on the channels of Lab color mode is explored without losing any essential detail, especially for the color information of nuclei (hematoxylin stained sections). Second, an approach to enhance the nuclei details that are a fundamental part of diagnosis and crucially needed by the pathologists who work with digital images is demonstrated.ResultsMerits of the proposed methodology are substantiated on sample microscopic images. The results show that the proposed methodology not only remedies the deficiencies of H&E microscopical images, but also enhances delicate details.ConclusionsNon-uniform illumination problems in H&E microscopical images can be corrected without compromising crucial details that are essential for revealing the features of tissue samples.

Numerical and Experimental Studies of Mixing Enhancement and Flame Stabilization in a Meso-Scale TPV Combustor With a Porous-Medium Injector and a Heat-Regeneration Reverse Tube

Understanding the flow dynamics, chemical kinetics, and heat transfer mechanism within a miniature thermophotovoltaic (TPV) combustor is essential for the development of devices for combustion-based power microelectromechanical systems, which may have a much higher energy density than that of conventional batteries. In this study, methods for enhancing the intensity and uniformity of the combustion chamber wall (emitter) illumination through the design of combustion and thermal management of the combustor in a miniature TPV system are proposed, discussed, and demonstrated. The proposed miniature TPV system consists of a swirling combustor with the combustion chamber wall acting as the emitter, a heat-regeneration reverse tube, and mixing-enhancing porous-medium fuel injection, which improves the low nonuniform illumination or incomplete combustion problems associated with conventional miniature TPV systems. Experiments and numerical simulations are performed to analyze the details of the flame structure and flame stabilization mechanism inside the meso-scale combustor with and without a reverse tube. Results indicate that the proposed swirling combustor with a heat-regeneration reverse tube and porous medium can improve the intensity and uniformity of the combustion chamber (emitter) illumination and can increase the surface temperature of the chamber wall. From the systematic numerical and experimental analysis, suitable operational parameters for the meso-scale TPV combustor are suggested, which may be used as a guideline for meso-scale TPV combustor design.

Study a New Approach to Uniform Indoor Illumination from Natural Light

To solve the problem of nonuniform indoor illumination by sunlight and to meet the need of energy conservation, we design a kind of cuneiform light guide plate to transmit sunlight from outside to rooms relying on the law of total reflection. Theoretical deductions and numerical simulations are used to obtain a preliminary plan, and some issues on applications and feasibility are discussed.

Numerical Studies of the Combustion of Methane-Air Mixture in a Meso-Scale TPV Combustor with a Heat-Regeneration Reverse Tube and a Porous-Medium Injector

The major objective of this paper is to develop a miniature combustor applied in a portable thermophotovoltaic (TPV) power generation system. The proposed miniature TPV system consists of a swirling combustor with the infrared thermal tube (ZrO2) acting as the emitter, a heat-regeneration reverse tube, and mixing-enhancing porous-medium fuel injection, which improves the low non-uniform illumination or incomplete combustion problems associated with conventional miniature TPV systems. A two-step global reaction mechanism was used to compute the chemical reactions of the reacting flows. Numerical simulations are performed to analyze the details of the flame structure and flame stabilization mechanism inside the meso-scale combustor with and without a reverse tube. In addition, these thermal conditions have strong effects on the combustion especially when the chamber dimension goes small and the ratio of surface area to volume becomes larger. Such as larger heat loss through the chamber wall to the ambient, may lead to the thermal quenching of meso-scale combustion. Therefore, the effect of various heat transfer conditions at chamber wall, e.g. with different wall heat conductivity on the combustion is delineated and discussed by numerical simulation. Results indicate that the proposed swirling combustor with a heat-regeneration reverse tube and porous medium can improve the intensity and uniformity of the combustion chamber (emitter) illumination, and can increase the surface temperature of the chamber wall. Correspondingly, the simulation results also indicated that the stable combustion in a meso-scale TPV combustor may be sustained through to control mass flow rate, heat loss conditions and maintaining proper thermal condition. Consequently, through such systematic numerical analysis, proper operational parameters for the meso-scale TPV combustor are suggested, which may be used as the guideline for meso-scale TPV combustor design.

Support-vector-machine-based method for automated steel bridge rust assessment

Abstract Computerized methods have been used for structure health monitoring and defect recognition in the civil engineering field for many years. However, there are still non-uniform illumination problems that require more research efforts to resolve. In view of this, a new support-vector-machine-based rust assessment approach (SVMRA) is developed in this research for steel bridge rust recognition. SVMRA combines Fourier transform and support vector machine to provide an effective method for non-uniformly illuminated rust image recognition. After comparison with the popular simplified K-means algorithm (SKMA) and BE-ANFIS, it is shown that the proposed SVMRA performs more effectively in dealing with non-uniform illumination and rust images of red- and brown-color background over SKMA and BE-ANFIS.

Binarization of Low-Quality Barcode Images Captured by Mobile Phones Using Local Window of Adaptive Location and Size

It is difficult to directly apply existing binarization approaches to the barcode images captured by mobile device due to their low quality. This paper proposes a novel scheme for the binarization of such images. The barcode and background regions are differentiated by the number of edge pixels in a search window. Unlike existing approaches that center the pixel to be binarized with a window of fixed size, we propose to shift the window center to the nearest edge pixel so that the balance of the number of object and background pixels can be achieved. The window size is adaptive either to the minimum distance to edges or minimum element width in the barcode. The threshold is calculated using the statistics in the window. Our proposed method has demonstrated its capability in handling the nonuniform illumination problem and the size variation of objects. Experimental results conducted on 350 images captured by five mobile phones achieve about 100% of recognition rate in good lighting conditions, and about 95% and 83% in bad lighting conditions. Comparisons made with nine existing binarization methods demonstrate the advancement of our proposed scheme.

Illumination adjustment for bridge coating images using BEMD-Morphology Approach (BMA)

Image recognition methods have been applied to infrastructure surface coating assessment for more than a decade. However, non-uniform illumination, such as shades and highlights, is still a big challenge to date. To tackle the non-uniform illumination problem in infrastructure surface coating assessment, the BEMD-Morphology Approach (BMA) is proposed in this paper. Basically, non-uniform illumination problems can be classified into two categories: shades and highlights. The proposed BEMD-Morphology Approach (BMA) adopts the Bidimensional Empirical Mode Decomposition (BEMD) to mitigate the effect of shades and uses morphological processing to detect highlight spots and replace them with non-highlight neighboring pixels. With BEMD and morphological processing, the non-uniform illumination problem in infrastructure surface coating assessment (e.g., steel bridge coating assessment) could be better handled and more accurate assessment results could be generated. At last, the performance of BMA is evaluated using the K-Means algorithm, one of the most popular image recognition methods, to show the effectiveness of BMA.

Box-and-Ellipse-Based ANFIS for Bridge Coating Assessment

In the late 1990s, image processing was first applied to steel bridge coating assessment in the United States. Yet, there has not been any robust method that could solve nonuniform illumination problems to date. In this regard, this paper aims to develop an approach that handles nonuniform illumination in rust image recognition. The proposed approach also contributes to rust intensity recognition and process automation. This paper adopts the a∗ b∗ color configuration (of the L∗ a∗ b∗ color space) which is shown to be the best coordinate system for rust recognition by the proposed method. Different rust colors are regarded as relating to different degrees of rust intensity. Due to the difficulty of defining light rust colors, the adaptive-network-based fuzzy inference system (ANFIS) is used as the framework for the box-and-ellipse-based ANFIS (BE-ANFIS). Illumination adjustment is used to overcome the nonuniform illumination problem. The proposed BE-ANFIS is trained using 120 rust images of the size of 256...

Automated bridge coating defect recognition using adaptive ellipse approach

Image processing has been used for assessment of infrastructure surface coating conditions for years. In North America, civil engineers have utilized image recognition for steel bridge coating inspection since late 1990s. However, there is still no robust method to overcome the non-uniform illumination problem for infrastructure surface coating defect recognition to date. Therefore, this paper aims to develop a new approach to tackle the non-uniform illumination problem for rust image recognition. This paper starts with an investigation of 14 color spaces in order to find out the best color configuration for non-uniformly illuminated rust image segmentation. Then, the identified best color configuration a⁎b⁎, which has a moderate ability to filter light, is utilized to develop the proposed adaptive ellipse approach (AEA). In AEA, a rust image is partitioned into three parts: background, rust, and mild-rust-color spots. The main idea is to identify the mild-rust-color spots properly using an adaptive ellipse. Illumination adjustment is also adopted in this approach to overcome the non-uniform illumination problem. Finally, the performance of the AEA-based a⁎b⁎ configuration is compared to the K-Means method, one of the most popular and effective image recognition approaches, to show the effectiveness of the proposed AEA approach.