Application and Analysis of Computer Vision Algorithms in Graphics and Image Processing

Computer Vision Algorithms (CVA) are widely used in several applications ranging from security to industrial processes monitoring. In recent years, an interesting emerging application of CVAs is related to the automatic defect detection in some production processes for which quality control is typically performed manually, thus increasing speed and reducing the risk for the operators. The main drawback of using CVAs is represented by their dependence on numerous parameters, making the tuning to obtain the best performance of the CVAs a difficult and extremely time-consuming activity. In addition, the performance evaluation of a specific parameter setting is obtained through the application of the CVA to a test set of images thus requiring a long computing time. Therefore, the problem falls into the category of expensive Black-Box functions optimization. We describe a simple approximate optimization approach to define the best parameter setting for a CVA used to determine defects in a real-life industrial process. The algorithm computationally proved to obtain good selections of parameters in relatively short computing times when compared to the manually determined parameter values.

Problem of determining the distance between locomotive and railcar from a video image is considered. The camera is located on an unmanned locomotive. Several algorithms of computer vision have been analyzed and tested. The search for a track to the railcar or safe distance detection methods were developed using Canny edge detector and Hough transformation. The difficulty in applying the algorithm for track detection is found, determined by the presence of turns and railway switches. A scheme for computing the Inverse Perspective Mapping of an image is considered. Neural network algorithms and Haar cascades are used to search for images of railcars. A conclusion is made about the need to apply hybrid algorithms to this problem.

BackgroundTraditional diagnostic tools for scoliosis screening necessitate a substantial number of specialized personnel and equipment, leading to inconvenience that can result in missed opportunities for early diagnosis and optimal treatment. We have developed a deep learning-based image segmentation model to enhance the efficiency of scoliosis screening.MethodsA total of 350 patients with scoliosis and 108 healthy subjects were included in this study. The dataset was created using their bare back images and standing full-length anteroposterior spinal X-rays. An attention mechanism was incorporated into the original U-Net architecture to build a Dual AttentionUNet model for image segmentation. The entire dataset was divided into the training (321 cases), validation (46 cases), and test (91 cases) sets in a 7:1:2 ratio. The training set was used to train the Dual AttentionUNet model, and the validation set was used to fine-tune hyperparameters and prevent overfitting during training. The performance of the model was evaluated in the test set. After automatic segmentation of the back contour, a back asymmetry index was calculated via computer vision algorithms to classify scoliosis into different severities. The accuracy of classifications was statistically compared to those of three clinical experts.ResultsFollowing the segmentation of bare back images and the application of computer vision algorithms, the Dual AttentionUNet model achieved an accuracy, precision, and recall rate of over 90% in predicting severe scoliosis. Notably, the model achieved an AUC value of 0.93 in identifying whether the subjects had scoliosis, which was higher than the 0.92 achieved by the deputy chief physician. In identifying severe scoliosis, their AUC values were 0.95 and 0.96, respectively.ConclusionThe Dual AttentionUNet model, based on only bare back images, achieved accuracy and precision comparable to clinical physicians in determining scoliosis severity. Radiation-free, cost-saving, easy-to-operate and noninvasive, this model provides a novel option for large-scale scoliosis screening.

Material characterization has been proved to be the most intuitive approach to understand the chemical composition, structure, and microstructure of materials, which is the basis of material design. One of the most important steps in material design is to extract the characteristics from an image, and find their associations with the material structure and properties. Therefore, in recent years, with the rapid development of machine vision algorithms, characterization images have attracted attention in the field of material characterization. Researchers use computer vision algorithms, such as image denoising and enhancement, to preprocess the representation image, image segmentation and classification to detect and separate each microstructure from the characterization image, and quantitatively analyze the properties of materials. Herein, the application of computer vision algorithms in material image representation is summarized and discussed. The latest and valuable views for experts and scholars in both computer vision and material grounds are presented. Thus, this review provides guidance for material exploration and promotes the developments of artificial intelligence in the field of materials.

Evaluation of spiral computed tomography data is important to improve the diagnosis of gunshot wounds and the development of further surgical tactics. The aim of the work is to improve the results of the diagnosis of foreign bodies in the lungs by using computer vision algorithms. Image gradation correction, interval segmentation, threshold segmentation, three-dimensional wave method, principal components method are used as a computer vision device. The use of computer vision algorithm allows to clearly determine the size of the foreign body of the lung with an error of 6.8 to 7.2%, which is important for in-depth diagnosis and development of further surgical tactics. Computed vision techniques increase the detail of foreign bodies in the lungs and have significant prospects for the use of spiral computed tomography for in-depth data processing. Keywords: computer vision, spiral computed tomography, lungs, foreign bodies.

This review study looks at two important areas of recent work: improvements in computer vision algorithms and the incorporation of computer graphics into computer vision systems. We explore the development of computer vision in Part 1, highlighting its many uses in various fields as UAV image processing and automobile navigation. Even while real-time processing is essential in many situations, classic local algorithms which are highly valued for their speed often sacrifice image quality in favour of global algorithms. But recent work reveals subtle modifications to matching computations and data gathering techniques that support local algorithms, leading to performance that approaches that of global algorithms with respect to matching rate. In Part 2, an innovative method for combining computer vision and graphics is shown for creating a new telepresence and collaboration platform. Three key features of this system are its smooth integration of the physical and virtual worlds for input and output, its ability to enable remote collaboration between users, and its ability to facilitate interaction between different 3D graphics programs. This system is designed for future high-bandwidth networks and sends real-time fusions of dynamic computer graphics and vision data. This paper highlights the visual dimension and the mutually beneficial relationship between computer graphics and vision for telepresence and collaborative applications. Preliminary studies show promising possibilities for this technology to create immersive spaces suitable for various cooperative tasks across high-bandwidth networks. Our goal in doing this thorough assessment is to clarify the course of these

During the steel pipeline installation, special attention is paid to the butt weld control performed by fusion welding. The operation of the currently popular automated X-ray and ultrasonic testing complexes is associated with high resource and monetary costs. In this regard, this work is devoted to the development of alternative and cost-effective means of preliminary quality control of the work performed based on the visual testing method. To achieve this goal, a hardware platform based on a single board Raspberry Pi4 minicomputer and a set of available modules and expansion cards is proposed, and software whose main functionality is implemented based on the systemic application of computer vision algorithms and machine learning methods. The YOLOv5 object detection algorithm and the random forest machine learning model were used as a defect detection and classification system. The mean average precision (mAP) of the trained YOLOv5 algorithm based on extracted weld contours is 86.9%. A copy of YOLOv5 trained on the images of control objects showed a mAP result of 96.8%. Random forest identifying of the defect precursor based on the point clouds of the weld surface achieved a mAP of 87.5%.

Research on the Application of Computer Vision Algorithms Based on Deep Learning in Image Recognition

The presence of computer vision technology is continually expanding into multiple application domains. An industry and an art form that is particularly attractive for the application of computer vision algorithms is ballet. Due to the well-codified poses, along with the challenges that exist within the ballet domain, automation for the ballet environment is a relevant research problem. The paper proposes a model called BaReCo, which allows for ballet poses to be recognised using computer vision methods. The model contains multiple computer vision pipelines which allows for the comparison of approaches that have not been widely explored in the ballet domain. The results have shown that the top-performing pipelines achieved an accuracy rate of 99.375% and an Equal Error Rate (EER) of 0.119% respectively. The study additionally produced a ballet pose dataset, which serves as a contribution to the ballet and computer vision community. By combining suitable computer vision methods, the study demonstrates that successful recognition of ballet poses can be accomplished.

Low-light images suffer from low contrast and unclear details, which not only reduces the available information for humans but limits the application of computer vision algorithms. Among the existing enhancement techniques, Retinex-based and learning-based methods are under the spotlight today. In this paper, we bridge the gap between the two methods. First, we propose a novel &#x201C;generative&#x201D; strategy for Retinex decomposition, by which the decomposition is cast as a generative problem. Second, based on the strategy, a unified deep framework is proposed to estimate the latent components and perform low-light image enhancement. Third, our method can weaken the coupling relationship between the two components while performing Retinex decomposition. Finally, the RetinexDIP performs Retinex decomposition without any external images, and the estimated illumination can be easily adjusted and is used to perform enhancement. The proposed method is compared with ten state-of-the-art algorithms on seven public datasets, and the experimental results demonstrate the superiority of our method. Code is available at: <uri>https://github.com/zhaozunjin/RetinexDIP</uri>.

Computer vision algorithms have important applications in the fields of image recognition and object detection. With the development of deep learning technology, computer vision algorithms have made significant progress in tasks such as object detection, classification, and positioning. In this study, convolutional neural networks and large-scale data sets are used for training to explore the application of computer vision algorithms in image recognition and object detection. The performance of the algorithm in target recognition and detection tasks is evaluated through feature extraction and model training of image data. The experimental results show that the accuracy rate of this algorithm is between 89% and 97%, and the computer vision algorithm has high accuracy and robustness in image recognition tasks. Through the effective training of deep learning models, the algorithm can automatically identify and classify different objects and scenes in the image.

Application of Computer Vision Algorithms in Software Test Automation

Modern agriculture faces a number of serious challenges, including climate change, soil degradation, water scarcity, biological threats and the negative impact of anthropogenic factors. A special place among these challenges is occupied by field weediness, which requires accurate monitoring and timely response. This study is devoted to the development of a system for automatic recognition and mapping of weeds with high geospatial accuracy based on UAV data. The proposed approach includes the application of computer vision algorithms for weed detection, data augmentation techniques to improve recognition accuracy, and the author’s map splicing method to provide accurate geo-referencing of detected weeds. Experimental tests confirmed the effectiveness of the developed system in the tasks of automatic detection of weeds and creation of geo-referenced maps of their distribution. Implementation of this system will allow agricultural producers to carry out spot treatment of weedy areas, optimize the use of herbicides and increase the efficiency of weed control.

Application of Computer Vision Algorithms for Assessing the Content of Magnetic Nanoparticles Uptaken by Dendritic Cells In-Vitro

Recently we developed flat facet solar concentrators that have low material cost. Each concentrator contains hundreds of components. To obtain low labor cost it is necessary to develop automated methods of components manufacture and assembly. In this paper we consider the problems of the concentrator manufacture. To make the automation algorithms more efficient we use computer vision methods based on neural networks. We developed these methods for handwritten digits and face recognition. Here we apply them to automated manufacture of solar concentrators. Several years ago we developed an algorithm of automatic placement of a pin in a hole. Later a visual based algorithm of component measurement was developed. In this paper we consider the possibilities of application of computer vision algorithms in solar concentrator manufacture.