Uneven Lighting Research Articles

Cursive Text Recognition in Natural Scene Images Using Deep Convolutional Recurrent Neural Network

Text recognition in natural scene images is a challenging problem in computer vision. Different than the optical character recognition (OCR), text recognition in natural scene images is more complex due to variations in text size, colors, fonts, orientations, complex backgrounds, occlusion, illuminations and uneven lighting conditions. In this paper, we propose a segmentation-free method based on a deep convolutional recurrent neural network to solve the problem of cursive text recognition, particularly focusing on Urdu text in natural scenes. Compared to the non-cursive scripts, Urdu text recognition is more complex due to variations in the writing styles, several shapes of the same character, connected text, ligature overlapping, stretched, diagonal and condensed text. The proposed model gets a whole word image as an input without pre-segmenting into individual characters, and then transforms into the sequence of the relevant features. Our model is based on three components: a deep convolutional neural network (CNN) with shortcut connections to extract and encode the features, a recurrent neural network (RNN) to decode the convolutional features, and a connectionist temporal classification (CTC) to map the predicted sequences into the target labels. To increase the text recognition accuracy further, we explore deeper CNN architectures like VGG-16, VGG-19, ResNet-18 and ResNet-34 to extract more appropriate Urdu text features, and compare the recognition results. To conduct the experiments, a new large-scale benchmark dataset of cropped Urdu word images in natural scenes is developed. The experimental results show that the proposed deep CRNN network with shortcut connections outperform than other network architectures. The dataset is publicly available and can be downloaded from <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://data.mendeley.com/datasets/k5fz57zd9z/1</uri> .

Rough Set and Otsu Approach based Hybrid Image Classification under Uneven Lighting Conditions

Rough Set and Otsu Approach based Hybrid Image Classification under Uneven Lighting Conditions

Research on the Application of Artificial Intelligence Technology in Computer Graphics Processing

In structured light geometric reconstruction, due to the complexity of shooting methods and scene lighting conditions, the resulting images may be lack of image details due to uneven light. For this reason, the article proposes a Retinex algorithm with colour restoration and colour saturation correction strategy based on HSV colour space transformation based on artificial intelligence technology. Then distinguish whether it is a bright area according to the threshold value, and modify the insufficient transmittance estimation of the bright area. Finally, the intensity component and saturation value are restored in the HIS colour space, and the histogram is used to stretch the intensity component.

GMM Based Adaptive Thresholding for Uneven Lighting Image Binarization

GMM Based Adaptive Thresholding for Uneven Lighting Image Binarization

Evaluation of Natural Lighting System of Lecture Building

Visual comfort is one of the most important things that building need. A building with a proper passive design obtains fulfill the users visual comfort through natural lighting  on the other hand, a passive design that is less precise always requires energy to achieve the users visual comfort. Lecture building is one of the buildings that is effectively used 8 hours a day and 5 days on a week. The high operating hours cause visual comfort in the building becomes very important. The purpose of this study is to determine the performance of the building passive design in terms of lighting to comprehend various visual problems in the building. The method used in this research is quantitative comparative by comparing the value of  building lighting. Through the results of field measurements, building modeling simulations with Ecotect software, and SNI 03-6197-2000 parameter  several problems were found in the building's natural lighting system such as inadequacy of lighting on the facade with a southwest orientation, enormous lighting on the facade with a northeast orientation, uneven lighting causing various visual discomforts.

A new image processing strategy for surface crack identification in building structures under non‐uniform illumination

Crack detection in building structures is an important approach to evaluating the safety of these structures. However, in some cases under special circumstances, it is very difficult to identify all features of cracks by visual inspection. To tackle this problem and offer a higher potential for practical implementations, developing an automatic crack detection method seems essential. This paper establishes a novel algorithm for surface crack detection in building walls based on image processing techniques to enhance crack visibility. One of the most prevalent issues in surface crack detection from digital crack images is non-uniform illumination of background which makes narrow and tiny cracks indistinguishable. In this regard, an integrated approach, combining adaptive image threshold using local first-order statistics, contrast-limited adaptive histogram equalization, and noise filtering using non-linear diffusion filtering, is proposed to extract the whole skeleton of the crack from digital crack images with non-uniform illumination. Several realistic crack images, suffering from noise and uneven lighting of background, are processed through the proposed algorithm to demonstrate the robustness and high accuracy of the method.

Enhancement of underwater optical images based on background light estimation and improved adaptive transmission fusion

Underwater optical imaging technology plays a vital role in humans' underwater activities. However, the serious quality degradation of underwater optical images hinders further development of such technology. This phenomenon is mainly caused by the absorption and scattering of light in the underwater medium. The blurred image formation model is widely used in the field of optical images and depends on two optical parameters: background light (BL) and the transmission map (TM). Therefore, we propose an underwater optical image enhancement method in the context of underwater optical image restoration and color correction. First, BL estimation based on the gray close operation, which can avoid the influence of white objects while accurately calculating BL, is proposed. Then, an improved adaptive transmission fusion (IATF) method is proposed, and the adjusted reversed saturation map (ARSM) method is applied to compensate for and refine the estimated TMs to obtain the final TMs. This paper also proposes a new underwater light attenuation prior (NULAP) method. Finally, to enhance color saturation and edge details, a statistical colorless slant correction fusion smoothing filter method is proposed. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods for dehazing, color and detail enhancement, and (uneven) light intensity.

Contrast and Luminance Enhancement Technique for Fundus Images Using Bi-Orthogonal Wavelet Transform and Bilateral Filter

For the identification of retinal diseases, optical images from the low power microscopic fundus camera have been used extensively by ophthalmologists. Uneven lighting and poor image contrast, however, may lead to reduced image quality, making it hard for ophthalmologists to analyze the diseases and can also lead to misinterpretation. This paper proposes a combination of the technique of Bi-orthogonal Wavelet Transform and Bilateral filtering (BWTBF) to uniformly improve visual clarity in the image field. BWT splits the image into subbands of low and high frequency, and bilateral filtering eliminates the high-frequency noise and preserves the image’s edge information. Gamma correction also tends to increase the luminance, and Contrast-Limited Adaptive Histogram Equalization (CLAHE) increases the image’s entire local contrast. Parameters such as Mean, Entropy, and Enhancement Measure (MSE) are used to evaluate this method, and the measured values are higher than the values of existing methods that confirm the efficacy of the proposed method.

3D global mapping of large-scale unstructured orchard integrating eye-in-hand stereo vision and SLAM

Large-scale, high-accuracy, and adaptive three-dimensional (3D) perception are the basic technical requirements for constructing a practical and stable fruit-picking robot. The latest vision-based fruit-picking robots have been able to adapt to the complex background, uneven lighting and low color contrast of the orchard environment. However, most of them have, until now, been limited to a small field of view or rigid sampling manners. Although the simultaneous localization and mapping (SLAM) methods have the potential to realize large scale sensing, it was critically revealed in this study that the classic SLAM pipeline is not completely adapted to orchard picking tasks. In this study, the eye-in-hand stereo vision and SLAM system were integrated to provide detailed global map supporting long-term, flexible and large-scale orchard picking. To be specific, a mobile robot based on eye-in-hand vision was built and an effective hand-eye calibration method was proposed; a state-of-the-art object detection network was trained and used to establish a dynamic stereo matching method adapted well to complex orchard environments; a SLAM system was deployed and combined with the above eye-in-hand stereo vision system to obtain a detailed, wide 3D orchard map. The main contribution of this work is to build a new global mapping framework compatible to the nature of orchard picking tasks. Compared with the existing studies, this work pays more attention to the structural details of the orchard. Experimental results indicated that the constructed global map achieved both large-scale and high-resolution. This is an exploratory work providing theoretical and technical references for the future research on more stable, accurate and practical mobile fruit picking robots.

Adaptive Window Selection for Non-uniform Lighting Image Thresholding

Selection of appropriate size of windows or subimages is the most important step for thresholding images with non-uniform lighting. In this paper, a novel criteria function is developed to partition images into different size of sub images appropriate for thresholding. After the partitioning, each subimage is segmented by Otsu’s thresholding approaches. The performance of the proposed method is validated on benchmark test images with different degree of uneven lighting. Based on the qualitative and quantitative measures, the proposed method is fully automatic, fast and efficient in comparison to many landmark approaches.

Curve‐based crack detection using crack information gain

Crack detection provides valuable information concerning the location, extent, type, and severity for structural health monitoring of civil infrastructures. Due to the influence of uneven lighting and imaging noise, as well as the debris, various textures, and materials of the different civil structure, detecting cracks in the surface images of civil infrastructures remains challenging in that there are many false positives and defragmentation of the crack curve. In this paper, an information-based crack detection method is developed to robustly characterize and detect cracks on a curve-by-curve basis. Crack information gain (CIG) is defined to characterize the information of a local patch's being cracked. With the proposed model of estimating crack depth, the information-based crack descriptor CIG is calculated by statistically modeling the probabilistic distribution of crack depth. Secondly, crack curves of different saliency are progressively detected by iteratively searching the salient string of pixels, regardless of the small gaps between fragments of the crack curve. Finally, crack curves are validated by examining the variation of CIG along the crack curve. The experimental results on a diverse set of images of different civil infrastructures demonstrate the generalizability of the proposed method, and the overall performance on each dataset outperforms the state-of-the-art available methods with 2.9% improvement. The proposed method has potential for the quantitative evaluation of cracks on a meaningful curve basis.

Effects of phosphorus enrichment on the spatial heterogeneity of stream periphyton under uneven light conditions

Spatial variations in light and nutrient availability usually lead to a heterogeneous distribution of periphyton biomass within streams, but the effects of nutrient enrichment on periphyton heterogeneity are still poorly understood. We tested phosphorus enrichment effects on the heterogeneity of periphyton quantity and nutritional quality in an environment with uneven light conditions. Natural periphyton was grown at either high or low P supply in circular running water flumes, each of which was half shaded and half in light. After 3 weeks, periphyton biomass was significantly more heterogeneous at high P than at low P supply, as algal production increased with light only in the P-enriched treatment. However, periphyton C:P ratio was equally homogeneous in both P treatments, despite the light differences within each experimental flume. Although this outcome seems to contrast with the light:nutrient hypothesis, it is likely that high-quantity periphyton patches acquired more P and depleted the available P for the low-quantity patches, leading to an even C:P ratio within each flume. Therefore, in an environment with heterogeneous light availability, nutrient enrichment has the potential to increase the heterogeneity of periphyton quantity without affecting the heterogeneity of periphyton quality, due to periphyton patches not being independent of one another.

Semantic segmentation for multiscale target based on object recognition using the improved Faster-RCNN model

Image semantic segmentation has received great attention in computer vision, whose aim is to segment different objects and provide them different semantic category labels so that the computer can fully obtain the semantic information of the scene. However, the current research mainly focuses on color image data as training, for outdoor scenes and single task semantic segmentation. This paper carries out multi-task semantic segmentation model in the complex indoor environment on joint target detection using RGB-D image information based on the improved Faster-RCNN algorithm, which can simultaneously realize the indoor scene semantic segmentation, target classification and detection multiple visual tasks. In which, in view of the influence of uneven lighting in the environment, the method of fusion of RGB images and depth images is improved. While enhancing the fusion image feature information, it also improves the efficiency of model training. Simultaneously, in order to meet the needs for operating on multi-scale target objects, the non-maximum value suppression algorithm is improved to improve the model’s performance. So as to realize the output of the model’s multi-task information, the loss function has also been redesigned and optimized. The indoor scene semantic segmentation model constructed in this paper not only has good performance and high efficiency, but also can segment the contours of different scale objects clearly and adapt to the indoor uneven lighting environment.

РАСПОЗНАВАНИЕ ШТРИХ-КОДА НА СИЛЬНО ИСКАЖЕННЫХ ИЗОБРАЖЕНИЯХ И ИЗОБРАЖЕНИЯХ С НИЗКИМ РАЗРЕШЕНИЕМ

Almost all products and items that exist on the market today have a unique code or identifier associated with them. We call this special identifier a barcode. Barcode detection is very common and is a necessity today as it makes our job easier. You can simply scan the code and easily get all the product information. Barcodes are still the prevalent machine-readable encoding mechanism for most products and services. At this stage of development, the barcode was quite common. Most items and products present in the household now have their own unique barcodes. They can be scanned and easily get all the necessary information, such as price, product details and description. There are even various apps available to scan the barcode through our phones. This is due to the high-quality pixel cameras that are present in all iPhones, android devices, or windows phones. Today, a wide range of portable devices for general use, such as mobile phones, come with an optical imaging system. Providing these general-purpose portable devices with barcode recognition is a cost-effective alternative to conventional barcode scanners. The equipment is available to billions of people. Combined with new services, this could revolutionize day-to-day shopping, including checking in-store prices, getting product information, accessing product reviews, finding similar products and services, and comparing prices locally. Detecting barcodes in images captured by general-purpose portable devices is particularly challenging due to the limitations of the integrated imaging system and on-device processing capabilities. These devices often have lower quality lens systems and lower resolution imaging circuits when compared to dedicated digital cameras. The optical system is often not designed for shooting close to the lens, resulting in out-of-focus and poorly lit images with rich colors. These limitations often mean that using conventional threshold detection methods cannot create a suitable template for barcode recognition. These limitations need to be considered in an algorithm that can invariably be implemented on a wide variety of portable devices. Barcode reading must be resistant to harsh conditions such as blur, noise, low resolution or low-quality camera lenses, which are very common. Surprisingly, even the most advanced barcode reading algorithms fail when some of these factors come into play. In this article, we present a new approach to barcode image detection. Our algorithm is specially designed to recognize barcodes when an image may be of low resolution, low quality, or suffer from significant blur, defocus, uneven lighting, noise and color saturation. The algorithm is accurate, fast, scalable and can be easily configured to find a valid result within a time constraint. Our algorithm is useful for real-time barcode recognition on handheld devices with limited processing capabilities such as mobile phones.

Multi-classifier Combined Anomaly Detection Algorithm Based On Feature Map In Underground Coal Mine

The detection of abnormal activities in deep learning is of great significance for preventing the occurrence of abnormal disasters in mine production. As the underground scenes of coal mines are characterized by much noise and uneven light, the traditional manual feature extraction method has little obvious effect in the underground and low accuracy of anomaly detection. To solve the above problems, a feature extraction method combining CNN+LSTM is proposed. Secondly, the obtained features are matched by graph structure. Finally, multiple classifiers are used to classify the features before and after matching. In this paper, experiments are carried out in coal mine dataset and UCSDped1 dataset respectively, and comparisons are made with some classical algorithms. Experimental show that the algorithm achieves high recognition accuracy in different abnormal event datasets.

Color Image Processing Under Uncertainty

Most digital images have uncertainties associated with the intensity levels of pixels and/or edges. These uncertainties can be traced back to the acquisition chain, to uneven lighting conditions used during imaging or to the noisy environment. On the other hand, intuitionistic fuzzy hypergraphs are considered a useful mathematical tool for digital image processing since they can represent digital images as complex relationships between pixels and model uncertain or imprecise knowledge explicitly. This paper presents the approach for noisy color image segmentation and edge detection based on intuitionistic fuzzy hypergraphs. First, the RGB image is transformed to the HLS space resulting in three separated components. Then each component is intuitionistically fuzzified based on entropy measure from which an intuitionistic fuzzy hypergraph is generated automatically. The generated hypergraphs will be used for denoising, segmentation, and edges detection. The first experimentations showed that the proposed approach gave good results especially in the case of dynamic threshold.

A robust sperm cell tracking algorithm using uneven lighting image fixing and improved branch and bound algorithm

An accurate and robust sperm cells tracking algorithm that is able to detect and track sperm cells in videos with high accuracy and efficiency is presented. It is fast enough to process approximately 30 frames per second. It can find the correct path and measure motility parameters for each sperm. It can also adapt with different types of images coming from different cameras and bad recording conditions. Specifically, a new way is offered to optimize uneven lighting images to improve sperm cells detection which gives us the ability to get more accurate tracking results. The shape of each detected object is used to specify collided sperms and utilized dynamic gates which become bigger and smaller according to the sperm cell's speed. For assigning tracks to the detected sperm cells positions an improved version of branch and bound algorithm which is faster than the normal one is offered. This sperm cells tracking algorithm outperforms many of the previous algorithms as it has lower error rate in both sperm detection and tracking. It is compared with six other algorithms, and it gives lower tracking error rates. This method will allow doctors and researchers to obtain sperm motility data instantly and accurately.

Underwater image enhancement method based on adaptive attenuation-curve prior.

The attenuation (sum of absorption and scattering), which is caused by the dense and non-uniform medium, generally leads to problems of color degradation and detail loss in underwater imaging. In this study, we describe an underwater image enhancement method based on adaptive attenuation-curve prior. This method uses color channel transfer (CCT) to preprocess the underwater images, light smoothing, and wavelength-dependent attenuation to estimate water light and obtain the attenuation ratio between color channels, and estimates and refines the initial relative transmission of the channel. Additionally, the method calculates the attenuation factor and saturation constraints of the three color channels and generates an adjusted reverse saturation map (ARSM) to address uneven light intensity, after which the image is restored through water light and transmission estimation. Furthermore, we applied white balance fusion globally guided image filtering (G-GIF) technology to achieve color enhancement and edge detail preservation in the underwater images. Comparison experiments showed that the proposed method obtained better color and de-hazing effects, as well as clearer edge details, relative to current methods.

A new face detection method based on Faster RCNN

The Non-Maximum Suppression (NMS) method based on Faster RCNN uses hard threshold to identify candidate face frames which to be detected. In complex scenes with partial occlusion of the face and uneven lighting, the phenomenon of missing and false detection of the face is prone to occur. Aiming at this problem, this paper proposes a new face detection method to extract face features through CNN, and generates a large number of face candidate frames which to be detected by the Region Proposal Network (RPN); the hard threshold of NMS is improved by linear weighting method, and the face candidate frame is screened by the linearly weighted NMS. Comparison experiment results show that on the FDDB dataset, the new face detection method in this paper can effectively avoid the false detection and missed detection of multiple faces under partial occlusion and uneven illumination, also has high detection accuracy and robustness.

GLAGC: Adaptive Dual-Gamma Function for Image Illumination Perception and Correction in the Wavelet Domain.

Low-contrast or uneven illumination in real-world images will cause a loss of details and increase the difficulty of pattern recognition. An automatic image illumination perception and adaptive correction algorithm, termed as GLAGC, is proposed in this paper. Based on Retinex theory, the illumination of an image is extracted through the discrete wavelet transform. Two features that characterize the image illuminance are creatively designed. The first feature is the spatial luminance distribution feature, which is applied to the adaptive gamma correction of local uneven lighting. The other feature is the global statistical luminance feature. Through a training set containing images with various illuminance conditions, the relationship between the image exposure level and the feature is estimated under the maximum entropy criterion. It is used to perform adaptive gamma correction on global low illumination. Moreover, smoothness preservation is performed in the high-frequency subband to preserve edge smoothness. To eliminate low-illumination noise after wavelet reconstruction, the adaptive stabilization factor is derived. Experimental results demonstrate the effectiveness of the proposed algorithm. By comparison, the proposed method yields comparable or better results than the state-of-art methods in terms of efficiency and quality.