Illumination Problem Research Articles

A method to improve corner detectors (Harris, Shi-Tomasi & FAST) using adaptive contrast enhancement filter

A method to improve interested-points detectors in an image that suffers from the problem of illumination was conducted in this paper. Three algorithms are adopted based on Harris, Shi-Tomasi, and FAST algorithms to identify the interested-points in images that are required to match, recognize and track objects in the digital images. Detecting the interested-points in images with bad illumination is one of the most challenging tasks in the field of image processing. The illumination is considered as one of the main causes of damage of the natural images during the acquisition and transition. Detecting the interested-points of these images doesn’t give the desired results, which is why handling this problem for those images is very important. The Adaptive Contrast Enhancement Filter approach is applied for solving this problem.

An improved image registration and fusion algorithm

Under the background of telemedicine, a new registration and mosaic algorithm for medical images is proposed in this paper to solve the problems of electronic noise, uneven illumination and ray scattering in the real-time medical process. The improved Retinex algorithm by trilateral filter and homomorphic filtering algorithm can enhance the image effectively in preprocessing. The improved phase correlation algorithm based on log polar transformation was used to calculate parameters, such as rotation, scaling and translation. Then, the SUSAN corner matching points were extracted in overlapping positions, the improved KD tree was used for enhancing matching efficiency. Later, matching points were purified by the improved RANSAC algorithm. Finally, images were processed by Laplacian pyramid decomposition algorithm to make the image joint seemed smooth and natural. The results of experiments and evaluation criteria confirm that the new method has high robustness in the process of medical image registration and stitching in the network.

Nv-Net: Efficient infrared image segmentation with convolutional neural networks in the low illumination environment

Infrared image segmentation is an essential problem in computer vision, especially when images suffer from the weak illumination and low-resolution problems. In this paper, we propose a novel fully convolutional neural network model for the low-resolution infrared images in weak illumination natural environments. First, the Nv-Net network is designed to segment the infrared images by introducing an enforcement layer in the front end of the framework. Then, a weighted-sigmoid-cross-entropy loss function is introduced to calculate the error between the prediction of the network and the ground-truth. To accelerate the network convergence, mean-variance normalization preprocessing is adopted. Moreover, a low illumination image dataset (LII) is built to train and test our model. The robustness and effectiveness of the proposed Nv-Net method are examined on the low illumination images with the mixed noises. Experimental results demonstrate that the proposed method has the flexibility to segment the arbitrary input images on several public datasets, such as the LII dataset, PASCAL VOC, and ADE20K. Compared with other state-of-the-art methods, the proposed Nv-Net method achieves the best segmentation performance in the low illumination environment.

Automatic melanoma diagnosis framework based on common image feature learning

Automatic melanoma diagnosis based on image processing can give more objective results. To facilitate examination for patients at home, we propose a new automatic melanoma diagnosis framework based on common images. Firstly, we use illumination assessment based on variational framework for Retinex (VFR) to filter the images with illumination problem caused by variation of capturing cameras viewpoint and ambient light. Secondly, the GrabCut algorithm based on colour difference is used to segment lesion area. It can complete segmentation automatically and efficiently. Thirdly, we use convolutional neural network (CNN) to extract high-level features and choose support vector machine (SVM) classifier to complete melanoma classification. Compared to hand-craft features, CNN can acquire deep information of images. Because of the lack of medical images, the SVM classifier is better than other classifiers. Finally, we validated our approach from different perspectives and the accuracy is increased by about 5% over other methods.

Automatic melanoma diagnosis framework based on common image feature learning

Automatic melanoma diagnosis based on image processing can give more objective results. To facilitate examination for patients at home, we propose a new automatic melanoma diagnosis framework based on common images. Firstly, we use illumination assessment based on variational framework for Retinex (VFR) to filter the images with illumination problem caused by variation of capturing cameras viewpoint and ambient light. Secondly, the GrabCut algorithm based on colour difference is used to segment lesion area. It can complete segmentation automatically and efficiently. Thirdly, we use convolutional neural network (CNN) to extract high-level features and choose support vector machine (SVM) classifier to complete melanoma classification. Compared to hand-craft features, CNN can acquire deep information of images. Because of the lack of medical images, the SVM classifier is better than other classifiers. Finally, we validated our approach from different perspectives and the accuracy is increased by about 5% over other methods.

Design and development of centred-light photobioreactor for microalgae cultivation system

The cultivation of microalgae within a controlled condition allows the production of biomass with lower contamination and suitable for high value pharmaceutical products. The controlled environment for microalgae growing can be accomplished by utilizing photobioreactor as a platform for introducing the basic needs needed by microalgae to grow effectively. However, due to some problems of high cost, low illumination and complicated cultivation systems which referring to available photobioreactors had contributed to low biomass production. This study deals with designing a new lab scale photobioreactor for overcoming the problems contributed by the available photobioreactors. During the developing process of the photobioreactor, the user needs are identified, and the most suitable concept based on the user needs was generated. The concept was then fabricated to prototype and its performance was validated. A centred-light photobioreactor was successfully developed for lab scale usage and being tested by cultivating Chlorella vulgaris species. A maximum of 0.281 g/L cell concentration was achieved using white light source during cultivation of Chlorella vulgaris.

ПРОБЛЕМАТИКА «СПОГАДІВ ІЗ ПОДОРОЖІ ДО СИБІРУ Й ПЕРЕБУВАННЯ В БЕРЕЗОВІ ТА САРАТОВІ» ЄВИ ФЕЛІНСЬКОЇ

E. Felinska’s choice of genealogical definitions for her works “Memories of a Journey to Siberia...” is due to the peculiarities of the reflection of the past, which differ from each other by the methodological approach in the interpretation of the problem, the properties of reflection of the temporal space, text (nature, world, time space, form, texture, etc.), emotional expression of the author’s recollections. The memoir genre provides a thorough comprehension of events and images of a larger period of time from the perspective of a mature author, which aims to leave a trace in history and relay your own experience to posterity. The memoir genre is characterized by a shorter time distance, and, as a rule, they are written under the first and strongest impressions of a particular event, so they have a high level of reflexivity. In the case of E. Felinska, the event that served as an intention was the exile to Siberia and later a stay in Saratovhe issues presented on the pages of “Memories of a Journey to Siberia...” by the outstanding Volynsky woman are conditionally combined into existential and socio-cultural and historical complexes. For “Memories of a Journey to Siberia...” ‒ the problems are the existential complex, which includes questions concerning the existence of man, his place in the world, the limits that can reach his mind, as well as all dimensions of loneliness, which E. Felinska felt in her own experience. The existential dimension corresponds to the system of problems of artistic illumination caused by the author’s existence in different cultural paradigms ‒ alien Siberian and Volyn. The socio-cultural and historical complex of problems is characterized by a high level of objectivity and actual content. The unifying factor behind the issue of “Memories of a Journey to Siberia...” remains the question of preserving Polish national authenticity in all temporal and spatial dimensions.

A Novel Neural Network Method for Face Recognition With a Single Sample Per Person

Face Recognition (FR) problem is one of the significant fields in computer vision. FR is used to identify the faces that appear over distributed cameras over the network. The problem of face recognition can be divided into two categories, the first is recognition with more than one sample per person, which can be called traditional face recognition problem. The second is the recognition of faces using only a Single Sample Per Person (SSPP). The efficiency of face recognition systems decreases because of limited references especially (SSPP) and faces taken in the Operational Domain (OD) different from faces in the Enrollment Domain (ED) in illumination, pose, low-resolution, and blurriness. This paper proposed a method that deals with all problems related to face recognition with SSPP. 3D face reconstruction is used to increase the reference gallery set with different poses and generate a design domain dictionary to overcome the problem of limited reference. Besides, the design domain dictionary is used to feed different deep learning models. Face illumination transfer techniques are utilized to overcome the illumination problem. Labeled Faces in the Wild (LFW) dataset is used to train Super-Resolution Generative Adversarial Network (SRGAN) to overcome the low-resolution problem. Deblur Generative Adversarial Network (DeblurGAN) is trained on the LFW dataset to overcome the problem of blurriness. The proposed method is evaluated using the Chokepoint dataset and COX-S2V dataset. The final results confirm an overall enhancement in accuracy compared to techniques that use SSPP for face recognition (generic learning and face synthesizing approaches). Also, the proposed method outperforms of Traditional and Deep Learning (TDL) method accuracy, which uses SSPP for face recognition.

On the illumination of a class of convex bodies

We study Boltyanski’s illumination problem (or Hadwiger's covering problem) for the class of convex bodies in $\mathbb{R}^n$ consisting of convex hulls of a pair of compact convex sets contained in two parallel hyperplanes of $\mathbb{R}^n$. This special case of the problem is completely solved when $n=3$.

A dual-cue network for multispectral photometric stereo

Estimating pixel-wise surface normal from a single image is a challenging task but offers great values to computer vision and robotics applications. By using the spectrally and spatially variant illumination, multispectral photometric stereo can produce pixel-wise surface normal from just one image. But multispectral photometric stereo methods may encounter the tangle problem of illumination, surface reflectance and camera response, which lead to an under-determined system. Existing approaches rely on either extra depth information or material calibration strategies, assuming a Lambertian surface condition which limits their application in practical systems. Previous learning-based methods employ fully-connected or CNN architectures to estimate surface normal. Compared with fully-connected framework, CNN takes advantage of the information embedded in the neighborhood of a surface point, but losing high-frequency surface normal details. In this paper, we present a new method that addresses this task by designing two stacked deep network. We first apply a CNN-based structural cue network to approximate coarse surface normal on small patches. Then, we use a pixel level fully-connected photometric cue network to further refine surface normal details and correct errors from the first step. The fused network is robust to non-Lambertian surfaces and complex illumination environments, such as ambient light and variant light directions. Experimental results show that our dual-cue fused network outperforms existing methods.

Adaptive Binarization of QR Code Images for Fast Automatic Sorting in Warehouse Systems

As the fundamental element of the Internet of Things, the QR code has become increasingly crucial for connecting online and offline services. Concerning e-commerce and logistics, we mainly focus on how to identify QR codes quickly and accurately. An adaptive binarization approach is proposed to solve the problem of uneven illumination in warehouse automatic sorting systems. Guided by cognitive modeling, we adaptively select the block window of the QR code for robust binarization under uneven illumination. The proposed method can eliminate the impact of uneven illumination of QR codes effectively whilst meeting the real-time needs in the automatic warehouse sorting. Experimental results have demonstrated the superiority of the proposed approach when benchmarked with several state-of-the-art methods.

From spherical to Euclidean illumination

In this note we introduce the problem of illumination of convex bodies in spherical spaces and solve it for a large subfamily of convex bodies. We derive from it a combinatorial version of the classical illumination problem for convex bodies in Euclidean spaces as well as a solution to that for a large subfamily of convex bodies, which in dimension three leads to special Koebe polyhedra.

Radiative Transfer in Half Spaces of Arbitrary Dimension

We solve the classic albedo and Milne problems of plane-parallel illumination of an isotropically-scattering half-space when generalized to a Euclidean domain for arbitrary A continuous family of pseudo-problems and related H functions arises and includes the classical 3D solutions, as well as 2D “Flatland” and rod-model solutions, as special cases. The Case-style eigenmode method is applied to the general problem and the internal scalar densities, emerging distributions, and their respective moments are expressed in closed-form. Universal properties invariant to dimension d are highlighted and we find that a discrete diffusion mode is not universal for d > 3 in absorbing media. We also find unexpected correspondences between differing dimensions and between anisotropic 3D scattering and isotropic scattering in high dimension.

A new TLD target tracking method based on improved correlation filter and adaptive scale

Target tracking is a popular but challenging problem in computer vision field. Due to many disturbing factors such as position transformation, illumination, and occlusion, it is difficult to achieve continuous target tracking. On the basis of the above analyses, a novel target tracking method based on correlation filters is proposed in this paper. This method uses the improved Tracking–Learning–Detection (TLD) tracking framework which combines the tracker with the detector through the learning mechanism. In the TLD tracking framework, the Spatially Regularized Discriminatively Correlation Filters tracker is used and improved. In addition, the adaptive tracking scale is realized according to the confidence of the searching area. The experimental results show that the proposed algorithm can effectively deal with the attitude change and the illumination problem so that it has better robustness and stability for target continuous tracking.

Identifying the Faces from Poor Quality Image / Video

Face biometric is becoming more popular because of its wide range of applications in authorizing the person either from an image or from the video sequence. The bottleneck in face recognition is Pose angle variation, varying light condition, Partial Occlusion, Blur in the image or Noise. The proposed method first removes the noise from the image using Adaptive Median Filter (AMF) then Discrete Cosine Transform(DCT) is applied to normalize the illumination problem. The algorithm is further used to remove the motion blur using Lucy Richardson’s method by calculating the Point Spread Function (PSF). The Pose variation problem is then addressed with Global Linear Regression(GLR). Then the Principal Component Analysis(PCA) and Linear Discriminant Analysis(LDA) are applied to the normalized image to get the feature vector. This combined feature score is used to recognize the image using K-Nearest Neighbor (K-NN). The result shows a maximum accuracy of 92% and 87.5% with Pose angle variation between (0°, 22°) and (22°, 40°) respectively. The pose variation greater than this shows an average accuracy of 77.5%. The result also shows a maximum computation speed of 0.018 Seconds.

Hygienic and environmental problems of energy-saving illumination in urbanization of Crimea

The article considers the problems offloodlights pollution in the territory of Crimea due to the work of illumination led equipment of the key elements of the international transport artery "China-Europe". There was performed a qualitative assessment of characteristics of led floodlights pollution on the example of the sea surface of the transport crossing through the Kerch Strait. Ichthyologists and oceanographers were shown to estimate the amount of phytoplankton biomass based on sunlight illumination. The excess dose of blue light in the spectrum of led lighting was established to have an impact on phytoplankton greater than solar and lunar light, creating preconditions for the increase of biological mass of phytoplankton and consequently to the formation of the "stern stock". Arising from additional phytoplankton biomass can significantly influence on the schedule offish migration in waters of the Kerch Strait, the biomass of mosquitoes and midges, which are prey for amphibians and birds. The decline of the both light pollution and its negative impact on fauna andflora requires the development of semiconductor sources of white light with a biologically adequate spectrum in the framework of the "Lighting of the lighting equipment of Crimea".

Adaptive Single Image Dehazing Using Joint Local-Global Illumination Adjustment

Haze has a serious impact on the outdoor optical imaging systems, and it will result in image blurring, color shift, and saturation reduction. Recently, many single image dehazing algorithms have been proposed for practical applications, such as surveillance. However, since the widely-used global atmospheric light in image dehazing fails to well describe the local illumination differences of images, these algorithms fail to well adapt to scenes with different haze concentrations and lighting conditions. Therefore, this paper proposes an adaptive single image dehazing algorithm using joint local-global illumination adjustment. A local illumination estimation for hazy image is proposed to replace the global atmospheric light constant in the atmospheric scattering model, and it can better adapt to the local differences of image illumination. Correspondingly, the global atmospheric light constant is proposed to be utilized to adaptively compensate the illumination intensity, which may better overcome the dark illumination problem within the dehazed image. The experimental results demonstrate that the proposed algorithm can outperform the state-of-the-art algorithms in terms of not only the dehazing effect but also the adaptability.

Face recognition based on local binary pattern and improved Pairwise-constrained Multiple Metric Learning

During the image acquisition process of face recognition, the obtained face images are affected inevitably by varied illumination and position in different environment. Local Binary Pattern (LBP) operator is used to decrease illumination effectiveness. Improved Pairwise-constrained Multiple Metric Learning method (IPMML) is proposed as a classification metric in our prior work, which solves the misalignment problem in a better way compared with PMML. To solve the high computation complexity of IPMML, Linear Discriminant Analysis (LDA) is performed before IPMML. Thus, a face recognition method based on LBP and IPMML is proposed, which can overcome the illumination and misalignment problems. LBP is selected to extract texture features of face images firstly. Second, LDA is applied to reduce the dimension. Then the fisher features are divided into sub-blocks according to the dimension of features and every block is a column vector. Fourth, a classification metric -- IPMML is used to obtain the optimum Mahalanobis matrix. Fifth, the Mahalanobis matrix is used to compute the final discriminative distance. Finally, the Nearest Neighborhood Classifier (NNC) is applied to classify face images. The experimental results show that the proposed method can achieve high recognition rates and is robust to illumination and facial expression variation, especially for misaligned face images.

A novel design for magneto-optical microscopy and its calibration

Magneto-optical microscopy for superconducting films is always involved with extreme environments, such as high vacuum and cryogenic temperature. In these applications, devices of high spatial resolution and compact focusing are often required. Besides, the calibration process is also of importance for quantitative measurement of magnetic fields. In this paper, we present a comprehensive module design for magneto-optical microscopy based on a combination of an infinity optical system and dynamic sealing technique. This technique gets rid of the limit of distance between the sample and the microscope, and also guarantees no influences of windows on image resolution. In addition, for the problem of uneven illumination, a practical calibration method is presented and verified through experimental results. As a result, the novel module and its calibration method make the technology of magneto-optical microscopy have wide applications.

Artificial Radio Illumination in a Closed Space

The problem of illumination of objects and surfaces by artificial incoherent sources of microwave radiation (radio light lamps based on dynamic chaos generators) in order to observe them using special receiving equipment is considered. A scheme of a receiver is developed and an experimental model of such a receiver with a spatial resolution sufficient for the visualization of a part of the surrounding space in artificial radio light is implemented. Images of a room in radio light are obtained. The feasibility of detecting changes on these images, associated with the emergence of new objects, is shown.