Non-uniform Illumination Research Articles

Hybrid Feature Extractor Using Discrete Wavelet Transform and Histogram of Oriented Gradient on Convolutional-Neural-Network-Based Palm Vein Recognition.

Biometric recognition techniques have become more developed recently, especially in security and attendance systems. Biometrics are features attached to the human body that are considered safer and more reliable since they are difficult to imitate or lose. One of the popular biometrics considered in research is palm veins. They are an intrinsic biometric located under the human skin, so they have several advantages when developing verification systems. However, palm vein images obtained based on infrared spectra have several disadvantages, such as nonuniform illumination and low contrast. This study, based on a convolutional neural network (CNN), was conducted on five public datasets from CASIA, Vera, Tongji, PolyU, and PUT, with three parameters: accuracy, AUC, and EER. Our proposed VeinCNN recognition method, called verification scheme with VeinCNN, uses hybrid feature extraction from a discrete wavelet transform (DWT) and histogram of oriented gradient (HOG). It shows promising results in terms of accuracy, AUC, and EER values, especially in the total parameter values. The best result was obtained for the CASIA dataset with 99.85% accuracy, 99.80% AUC, and 0.0083 EER.

Non-uniform illumination correction algorithm for cytoendoscopy images based on illumination model

Non-uniform illumination correction algorithm for cytoendoscopy images based on illumination model

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.

Monitoring and Diagnostic Method for Maintaining the Operation Parameters of a Solar Module under Non-Uniform Illumination

The most well-known methods for diagnosing solar modules are considered; it is shown that the described diagnostic methods do not allow identifying defects that develop over a long time. The operation of photovoltaic cells under non-uniform illumination is analyzed. It has been shown that the operation of solar modules under non-uniform illumination can lead to thermal damage to semiconductor materials and deterioration in the module energy characteristics due to the fact that some of the photovoltaic cells located at reduced energy illumination become a parasitic load for more illuminated photovoltaic cells included in such module. An analytical equation has been obtained in explicit form for the full current-voltage characteristic of a photovoltaic cell using the Lambert W-function in forward and reverse bias, which makes it possible to study the connections of photovoltaic cells as a part of a solar module under non-uniform energy illumination, where the reverse branch of the current-voltage characteristic is important. The analytical equation makes it possible to predict the behavior of photovoltaic cells and solar modules composed of them under various operating modes, including identifying the degradation process. An electronic measuring device has been developed and manufactured that makes it possible to measure the light and dark current-voltage characteristics of a photovoltaic cell, including the negative branch, in automatic mode. This reduces measurement time and the influence of external experimental conditions when obtaining the current-voltage characteristics of the photovoltaic cell. A method for constructing solar modules from photovoltaic cells under conditions of their operation under non-uniform lighting has been proposed. As a result of such selection, reliability is increased and an increase in the efficiency of the solar module in shading mode, composed of series-connected photovoltaic cells selected in this way, is achieved.

Video-based HR measurement using adaptive facial regions with multiple color spaces

Driven by the desire for feasible and convenient healthcare, non-contact heart rate (HR) monitoring based on consumer-grade cameras has gained significant recognition among researchers. However, this technology suffers from performance reliability and consistency in realistic situations of motion artifacts, illumination variations, and skin tones, limiting it to emerge as an alternative to conventional methods. Considering these challenges, this paper suggests an effective technique for HR measurement from facial RGB videos. The face being the region of interest (ROI) is divided into several small sub-ROIs of even size. A group of quality sub-ROIs is formed and weighted based on the fundamental periodicity coefficient to handle spatial non-uniform illumination and facial motions. Five different color spaces are considered, and the most suitable color component from each space is chosen to alleviate the influence of temporal illumination variation and other factors. The resultant color signals are denoised using the ensemble empirical mode decomposition and integrated using the principal component analysis to derive a pulsating component representing the blood volumetric changes for HR computation. Experiments are conducted over three standard datasets, namely PURE, UBFC, and COHFACE. The obtained mean absolute error values are 1.16 beats per minute (bpm), 1.56 bpm, and 2.10 bpm for PURE, UBFC, and COHFACE datasets, respectively, indicating the performance of the technique well above the clinically acceptable threshold. In comparison, the technique showed performance superiority over the state-of-art methods. These outcomes substantiate the potential of alternative color spaces for accurate and reliable HR monitoring from facial videos in challenging scenarios.

Multiple damage segmentation and extraction of wind turbine blades surface under complex background based on SKRT approach

Machine vision detection technology has been widely used in detecting wind turbine blade surface damage, but the complex background often has a significant impact on blade damage detection. Aiming at the complex background blade images caused by various natural background features, complex blade surface features, low contrast features, non-uniform illumination, weather conditions, and other factors, the work proposes an SKRT segmentation method based on K-means clustering and adaptive threshold fusion to segment and extract multiple damage features on the surface of wind turbine blades with complex backgrounds. Firstly, an single-scale retinex(SSR) algorithm is adopted to enhance the contrast between surface damage and image background in the research. Then the image is roughly segmented by K-means clustering to remove most of the background features, and the background mask is replaced with the peak of the remaining feature image pixels to solve the problem of wrong segmentation. Finally, making use of the adaptive threshold local segmentation method to accurately segment the blade surface damage. The experimental results show that the proposed SKRT segmentation method can significantly improve the segmentation accuracy of wind turbine blade surface damage with complex background, and the accuracy, intersection over union, and F-measure value are increased by 37.20%, 35.71%, and 28.69%, respectively. The method performs better robustness to multiple damage feature segmentation.

TSSFN: Transformer-based self-supervised fusion network for low-quality fundus image enhancement

Fundus images are used to assist the diagnoses of ocular diseases, and a high-quality fundus image with more details makes clinical diagnostic results more reliable. However, the quality of fundus images is often unsatisfactory due to the turbidity of refractive medium and the doctor-patient cooperation. To enhance the low-quality fundus images, a transformer-based self-supervised network is proposed. During the training phase, an encoder-decoder-based network is introduced. To counteract the drawbacks of establishing long-term dependencies in the convolutional neural network (CNN), the encoder composed of vision transformer and CNN is proposed so that the global and local information of fundus images is fully extracted. On this basis, three reconstruction tasks with self-supervised constraints are designed to enable the network to extract features from different degenerated images. During the testing phase, a low-quality fundus image is decomposed into three feature layers of reverse, illumination, and detail, and then the multi-layer features are fused via the network. To demonstrate the effectiveness of the proposed method, the non-uniform illumination and blurry fundus images are tested. The average scores of NIQE on underexposed, blurred, and overexposed fundus images are 3.03, 2.98, and 2.80, respectively. The average scores of BRISQUE on underexposed, blurred, and overexposed fundus images are 40.32, 40.55, and 39.76, respectively. The average score of subjective evaluation by three ophthalmologists is 61.17%. Compared with the existing methods, the proposed method achieves the superior performance in both subjective and objective evaluations.

Unsupervised image enhancement under non-uniform illumination based on paired CNNs

This paper presents two CNN-based systems for unsupervised image enhancement under non-uniform illumination. The core of the systems is constituted by the difference of a pair of CNNs. Each CNN is composed of two convolutional layers of neurons with exponential activation function and logarithmic activation function. A weighted sum of the non-reference loss functions is used to train the paired CNNs. It includes an entropy enhancement function and a Bézier loss function to ensure global and local enhancement complementarily. It also includes a white balance loss function to remove color cast in raw images, and a gradient improvement loss function to compensate for the high frequency degradation . In addition, it includes an SSIM (structural similarity index) loss functions to ensure image fidelity. In addition to the basic system, CNNOD, an augmented version called CNNOD+ is developed, which features an information fusion/combination module with a power-law network for gamma correction. The experimental results on two benchmark datasets are discussed to demonstrate that the proposed systems outperform the state-of-the-art methods in terms of enhancement quality, model complexity, and convergence efficiency.

Quantifying the Effect of Light Intensity Uniformity on the Crop Yield by Pea Microgreens Growth Experiments

Differences in individual plant growth are affected by the spatial variation of light intensity, reducing the homogeneity of microgreen crops. Identifying the tradeoffs between light uniformity and crop quality is challenging due to the confounding effect of nonuniform illuminance with other noise factors. This study presents the results of hydroponic pea (Pisum sativum, L.) growth experiments aimed at quantifying the effect of photon irradiance variations. By adjusting the power of LED luminaires, we established one uniformly illuminated zone and two non-uniformly illuminated zones. Germinated seeds with 6 cm-long radicles were transplanted to cultivation trays with known light intensity in predetermined positions. Plants were cut 12 days after the start of light treatment and measured for fresh weight and shoot height. Our findings revealed no significant difference between the crop yield on trays having the same average PPFD but different light uniformity. However, correlation analysis of individual measurement data showed that local PPFD differences explained 31% of the fresh weight variation, and the rest was attributed to noise in the germination and growth processes. We also discuss the implications of our findings for the design and optimization of vertical farms.

A new approach of contrast enhancement for Medical Images based on entropy curve

X-ray, MRI, and CT scan images etc, are widely used for the detection of various prevalent diseases. The efficient identification of the disease depends very much on the quality of the image. Sometimes due to environmental conditions such as insufficient and nonuniform illumination, shacking and movement of objects or the imaging device, and some other fault in the device, the resultant image may have low contrast and the presence of noise or artifacts. In such situation, a contrast enhancement algorithm that can efficiently improve the contrast without increasing noise and artifacts can play an important role. In this article, we propose a simple yet efficient method for these types of images by using the image’s entropy curve and homomorphic filtering. It enhances the contrast of medical images without increasing the content of noise and artifacts. Also, the performance of the proposed method is evaluated by a complete qualitative and quantitative analysis.

Label-free grain segmentation for optical microscopy images via unsupervised image-to-image translation

Grain boundaries play an important role in governing the mechanical and physical properties of polycrystalline materials. Therefore, quantitative analysis of grain structure is an important prerequisite for establishing structure-property relationships. However, this quantitative analysis is hampered by the low contrast and non-uniform illumination of optical microscopy images. Although previous studies have used neural networks to detect grain boundaries in optical micrographs, their practical applications have been restricted due to labeling costs for supervised learning and their sensitivity to defects present in a grain structure image. In this paper, we approach grain boundary detection as a real-to-virtual (R2V) translation problem, mapping a single real microstructure to virtual microstructures. With this perspective, our framework benefits from two learning schemes: unsupervised learning and physics-inspired learning. Extensive experiments demonstrate the superiority and generality of our framework. We expect that our approach will facilitate the use of data-driven techniques in the field of quantitative microstructure analysis.

Study, modeling and simulation of photovoltaic panels under uniform and nonuniform illumination conditions

In this work we studied the behavior of the photovoltaic panels in a uniform and non uniform illumination conditions on the module surface. For this a group of UDTS50 PV panels was modeled and simulated under Matlab/Simulink environment toward discuss and compare the external characteristics in the two studied situations. The simulation results obtained shows well the effect of the shadow in a photovoltaic installation, which requires particular precautions in order to guarantee the maximum power possible under all operation conditions.

Computational analysis and optimization of daylight collector geometry for removal of hotspots in circular mirror light pipe

The illuminance patterns formed on the various surfaces of a tubular daylight guidance system (TDGS) were numerically measured and calculated for the beam sunlight input. For this study, the TDGS comprises a revolved parabolic profiled daylight collector geometry and a vertical MLP system for daylight guidance. TDGS is basically a non-imaging optical system that is designed to efficiently transmit available sunlight across the MLP (mirror light pipe) length. But while doing so the problematic hotspots are observed mainly on the diffuser placed at the exit aperture of cylindrical MLP which further results in non-uniform illumination in the daylit room. In this work, the use of a prismatic casing arranged sideways to the parabolic profiled collector and a sloped diffuser as a top cover shows a significant reduction in the hotspot problem on the exit aperture of MLP without compromising light transmission in TDGS. The ‘non-uniformity’ index value, Ir signifying the ratio of maximum illuminance to average illuminance on the diffuser surface dropped considerably for the proposed design signifying an increase in uniformity on the exit aperture of MLP. For 1 m long MLP (aspect ratio = 2.5), the maximum value of Ir was ∼ 19 and ∼ 37 for TDGS with dome collector and TDGS with parabolic collector having plane cover (TSA) respectively on midday timings of 21st June while for the proposed design the value was Ir < 5. For 2 m long MLP (aspect ratio = 5), the value was Ir < 4 much lower in comparison to Ir of ∼ 20 and ∼ 36 for TS with dome collector and TSA respectively. A considerable decrease in the severity of hotspots was realized from the results. The proposed collector design was also tested for the illuminance values on the work plane of the simulated room under beam sunlight, diffuse skylight, and overcast sky conditions. No compromise in the average illuminance values was observed when compared to the parabolic collector with transparent casing. Moreover, the proposed design gave enhanced values of illuminance under low altitude beam sunlight as well as under diffuse skylight for various timings of the day. Performance under the overcast sky was found slightly lesser in comparison to conventional collector designs though nominal levels of illuminance were observed for all the configurations of collectors due to the very less magnitude of light availability.

Perceptual Quality Assessment of Enhanced Colonoscopy Images: A Benchmark Dataset and an Objective Method

In colonoscopy, the captured images are usually with low-quality appearance, such as non-uniform illumination, low contrast, etc., due to the specialized imaging environment, which may provide poor visual feedback and bring challenges to subsequent disease analysis. Many low-light image enhancement (LIE) algorithms have recently proposed to improve the perceptual quality. However, how to fairly evaluate the quality of enhanced colonoscopy images (ECIs) generated by different LIE algorithms remains a rarely-mentioned and challenging problem. In this study, we carry out a pioneering investigation on perceptual quality assessment of ECIs. Firstly, considering the lack of specific datasets, we collect 300 low-light images with diverse contents during the real-world colonoscopy and conduct rigorous subjective studies to compare the performance of 8 popular LIE methods, resulting in a benchmark dataset (named ECIQAD) for ECIs. Secondly, in view of the distinctive distortion characteristics of ECIs, we propose an effective no-reference Enhanced Colonoscopy Image Quality (ECIQ) method to automatically evaluate the perceptual quality of ECIs via analysis of brightness, contrast, colorfulness, naturalness, and noise. Extensive experiments on ECIQAD demonstrate the superiority of our proposed ECIQ method over 14 mainstream no-reference image quality assessment methods.

Study on the Measurement Method of Wheat Volume Based on Binocular Structured Light

In this paper, we propose a grain volume measurement method based on binocular structured light to address the need for fast and high-precision grain volume measurement in grain stocks. Firstly, we utilize speckle structured light imaging to tackle the image matching problem caused by non-uniform illumination in the grain depot environment and the similar texture of the grain pile surface. Secondly, we employ a semi-global stereo matching algorithm with census transformation to obtain disparity maps in grain bins, which are then converted into depth maps using the triangulation principle. Subsequently, each pixel in the depth map is transformed from camera coordinates to world coordinates using the internal and external parameter information of the camera. This allows us to construct 3D cloud data of the grain pile, including the grain warehouse scene. Thirdly, the improved European clustering method is used to achieve the segmentation of the three-dimensional point cloud data of the grain pile and the scene of the grain depot, and the pass-through filtering method is used to eliminate some outliers and poor segmentation points generated by segmentation to obtain more accurate three-dimensional point cloud data of the grain pile. Finally, the improved Delaunay triangulation method was used to construct the optimal topology of the grain surface continuous triangular mesh, and the nodes of the grain surface triangular mesh were projected vertically to the bottom of the grain warehouse to form several irregular triangular prisms; then, the cut and complement method was used to convert these non-plane triangular prisms into regular triangular prisms that could directly calculate the volume. The measured volume of the pile is then obtained by calculating the volume of the triangular prism. The experimental results indicate that the measured volume has a relative error of less than 1.5% and an average relative error of less than 0.5%. By selecting an appropriate threshold, the relative standard deviation can be maintained within 0.6%. The test results obtained from the laboratory test platform meet the requirements for field inspection of the granary.

FishSeg: 3D Fish Tracking Using Mask R-CNN in Large Ethohydraulic Flumes

To study the fish behavioral response to up- and downstream fish passage structures, live-fish tests are conducted in large flumes in various laboratories around the world. The use of multiple fisheye cameras to cover the full width and length of a flume, low color contrast between fish and flume bottom and non-uniform illumination leading to fish shadows, air bubbles wrongly identified as fish as well as fish being partially hidden behind each other are the main challenges for video-based fish tracking. This study improves an existing open-source fish tracking code to better address these issues by using a modified Mask Regional-Convolutional Neural Network (Mask R-CNN) as a tracking method. The developed workflow, FishSeg, consists of four parts: (1) stereo camera calibration, (2) background subtraction, (3) multi-fish tracking using Mask R-CNN, and (4) 3D conversion to flume coordinates. The Mask R-CNN model was trained and validated with datasets manually annotated from background subtracted videos from the live-fish tests. Brown trout and European eel were selected as target fish species to evaluate the performance of FishSeg with different types of body shapes and sizes. Comparison with the previous method illustrates that the tracks generated by FishSeg are about three times more continuous with higher accuracy. Furthermore, the code runs more stable since fish shadows and air bubbles are not misidentified as fish. The trout and eel models produced from FishSeg have mean Average Precisions (mAPs) of 0.837 and 0.876, respectively. Comparisons of mAPs with other R-CNN-based models show the reliability of FishSeg with a small training dataset. FishSeg is a ready-to-use open-source code for tracking any fish species with similar body shapes as trout and eel, and further fish shapes can be added with moderate effort. The generated fish tracks allow researchers to analyze the fish behavior in detail, even in large experimental facilities.

Non-Uniform-Illumination Image Enhancement Algorithm Based on Retinex Theory

To address the issues of fuzzy scene details, reduced definition, and poor visibility in images captured under non-uniform lighting conditions, this paper presents an algorithm for effectively enhancing such images. Firstly, an adaptive color balance method is employed to address the color differences in low-light images, ensuring a more uniform color distribution and yielding a low-light image with improved color consistency. Subsequently, the image obtained is transformed from the RGB space to the HSV space, wherein the multi-scale Gaussian function is utilized in conjunction with the Retinex theory to accurately extract the lighting components and reflection components. To further enhance the image quality, the lighting components are categorized into high-light areas and low-light areas based on their pixel mean values. The low-light areas undergo improvement through an enhanced adaptive gamma correction algorithm, while the high-light areas are enhanced using the Weber–Fechner law for optimal results. Then, each block area of the image is weighted and fused, leading to its conversion back to the RGB space. And a multi-scale detail enhancement algorithm is utilized to further enhance image details. Through comprehensive experiments comparing various methods based on subjective visual perception and objective quality metrics, the algorithm proposed in this paper convincingly demonstrates its ability to effectively enhance the brightness of non-uniformly illuminated areas. Moreover, the algorithm successfully retains details in high-light regions while minimizing the impact of non-uniform illumination on the overall image quality.

Design of Automatic Number Plate Recognition System for Yemeni Vehicles with Support Vector Machine

Automatic Number Plate Recognition (ANPR) is an important tool in the Intelligent Transport System (ITS). Plate features can be used to provide the identification of any vehicle as they help ensure effective law enforcement and security. However, this is a challenging problem, because of the diversity of plate formats, different scales, rotations and non-uniform illumination and other conditions during image acquisition. This work aims to design and implement an ANPR system specified for Yemeni vehicle plates. The proposed system involves several steps to detect, segment, and recognize Yemeni vehicle plate numbers. First, a dataset of images is manually collected. Then, the collected images undergo preprocessing, followed by plate extraction, digit segmentation, and feature extraction. Finally, the plate numbers are identified using Support Vector Machine (SVM). When designing the proposed system, all possible conditions that could affect the efficiency of the system were considered. The experimental results showed that the proposed system achieved 96.98% and 99.19% of the training and testing success rates respectively.

Surface roughness evaluation based on near point lighting photometric stereo

Surface roughness evaluation is crucial for enhancing surface properties. Traditional offline human-assisted inspection techniques are labor-intensive and time-consuming, hindering manufacturing productivity. Current machine vision-based roughness measurement methods primarily rely on grayscale or color images, neglecting the benefits of 3D morphology's multidimensional information. This results in complex and inaccurate algorithms. To address these issues, we propose an efficient surface roughness evaluation method using Near Point Lighting Photometric Stereo (NPL-PS). Our NPL-PS scheme, configured with one camera and 24 LED point light sources, generates a 3D depth map of the machined surface. Under the classic Lambertian model and camera weak perspective transform, we derive a linearized photometric equation for NPL-PS containing light intensity attenuation. By solving the linear equation using our proposed methods for illumination position calibration and non-uniform illumination correction, we estimate the normal vector corresponding to each pixel. We then use the Frankot-Chellapa algorithm to recover the height map from the vector field. Finally, we extract roughness texture features from the height map using polynomial fitting and quantitatively evaluate the roughness. Our experiments using real surface roughness specimens demonstrate the feasibility and effectiveness of this method compared to traditional methods, laying the foundation for subsequent practical production applications.

Barcode positioning method based on line detection under non-uniform illumination

The positioning problem of the barcode is easily affected by factors such as uneven illumination and complex background. Based on the EDLines line detection algorithm, a positioning algorithm that can deal with the barcode positioning problem under non-uniform lighting conditions is proposed. First, the EDLines algorithm is used to detect the straight-line segment of the image, and the midpoint coordinates of all line segments are extracted. Since the midpoint coordinates near the barcode are relatively densely distributed, the density-based HDBSCAN point clustering algorithm is used for all midpoint coordinates for density clustering. Then a filtering strategy based on the consistency of line segment direction is proposed to preliminarily filter the clustering results, and one or more point clustering results that may belong to the barcode area are obtained. Then the RANSAC algorithm is used to perform line fitting on the point clustering results. The accuracy of the straight-line fitting results is judged by direction consistency screening, and the intersection of the fitted straight line and the straight-line segment to which the centroid belongs is calculated for the results that meet the expectations, and the width of the barcode area is obtained. Finally, the straight-line segment obtained by screening is calculated. The average length and the height of the barcode area are got, to accurately locate the barcode position. Compared with the previous algorithms on the public barcode dataset and the self-made barcode dataset, the algorithm has good positioning accuracy and running speed.