The detection and tracking of cars is a significant and useful aspect of traffic surveillance systems, which is essential for the efficient management of traffic and the security of drivers and passengers. The primary...
详细信息
In this article implementation process of the camera from the integrated field-programmable gate array or FPGA for problems of identification of the vehicles used on the automated points of weight and dimensional cont...
详细信息
ISBN:
(纸本)9781665400756
In this article implementation process of the camera from the integrated field-programmable gate array or FPGA for problems of identification of the vehicles used on the automated points of weight and dimensional control by search of edges of the object in the detector Sobelya method is considered. In development process in the verilog language the main parts of interaction of the camera with the personal computer, for carrying out binarization of the image and also for its frequency filtering were described. The Fourier transform involves a large number of operations, which requires a large amount of computing power. To get around this limitation, the article discusses fast Fourier transform algorithms.
Shape recognition in images represents one of the complex and hard-solving problems in computer vision due to its nonlinear, stochastic and incomplete nature. Classical imageprocessing techniques have been normally u...
详细信息
Shape recognition in images represents one of the complex and hard-solving problems in computer vision due to its nonlinear, stochastic and incomplete nature. Classical imageprocessing techniques have been normally used to solve this problem. Alternatively, shape recognition has also been conducted through metaheuristic algorithms. They have demonstrated to have a competitive performance in terms of robustness and accuracy. However, all of these schemes use old metaheuristic algorithms as the basis to identify geometrical structures in images. Original metaheuristic approaches experiment several limitations such as premature convergence and low diversity. Through the introduction of new models and evolutionary operators, recent metaheuristic methods have addressed these difficulties providing in general better results. This paper presents a comparative analysis on the application of five recent metaheuristic schemes to the shape recognition problem such as the Grey Wolf Optimizer (GWO), Whale Optimizer Algorithm (WOA), Crow Search Algorithm (CSA), Gravitational Search Algorithm (GSA) and Cuckoo Search (CS). Since such approaches have been successful in several new applications, the objective is to determine their efficiency when they face a complex problem such as shape detection. Numerical simulations, performed on a set of experiments composed of images With different difficulty levels, demonstrates the capacities of each approach. (C) 2020 The Authors. Published by Atlantis Press B.v.
The requirement of imageprocessing is very much required on the present world. Almost in every field it has a huge application. Detecting and recognizing the face is one of the most trending imageprocessingsystems ...
详细信息
Magnetic Resonance image (MRI) brain tumor segmentation is critical and significant in a clinical field that assist in diagnosis, complete growth prediction and tumor mass rates required for patients. The complexity i...
详细信息
ISBN:
(数字)9798331508456
ISBN:
(纸本)9798331508463
Magnetic Resonance image (MRI) brain tumor segmentation is critical and significant in a clinical field that assist in diagnosis, complete growth prediction and tumor mass rates required for patients. The complexity in segmenting brain tumors are challenging due to the various structures, shapes, locations, visual characteristics, frequency, texture and contrast. To overcome this issue, this research proposes a Fossa Optimization Algorithm (FOA) with Convolution Neural Network (CNN) for brain tumor classification. The Geodesic Active Contour (GAC) is used for segmentation which identifies tumor boundaries precisely in noisy and intricate data. FOA utilizes dynamic search strategy by its hunting behavior, balancing exploration and exploitation effectively. Its adaptive step size enables better convergence when avoiding local optima. Furthermore, its ability to capture edges and patterns makes it effective for classification. CNN are better to diverse in scale, noise and rotation because of its shared weights and local connectivity reduce the complexity thereby leading to higher accuracy and quick processing in classification. The FOA-CNN obtains 99.92% accuracy, 99.20% f1-score, 99.07% sensitivity and 99.34% precision for BRATS2020 dataset which is superior than Spatial Transformer Network and Non-local Attention Mechanism (STN-NAM).
Roads are the most commonly used mode of transportation. However, due to the frequent use of roads, it requires an organized assistance. Manually screening the potholes or damaged patches is highly impossible and inac...
详细信息
ISBN:
(纸本)9781665489638
Roads are the most commonly used mode of transportation. However, due to the frequent use of roads, it requires an organized assistance. Manually screening the potholes or damaged patches is highly impossible and inaccurate. This research work investigates the detection of potholes or patches by using a camera. imageprocessing models are used to detect the potholes or patches. The proposed system has been evaluated in a Desktop environment by using the Open Cv library. To perform this task, a smart imageprocessing model with Hough transform are used.
Complete Blood Count is one of the most commonly performed medical laboratory procedure today. It is required to detect various types of diseases. Presently, some small-scale clinics in the country still does the tedi...
详细信息
The issues of intellectual energy tasks, which set the task of data processing, which would allow to build models on the basis of the found interrelations, to describe the peculiarities of the functioning of real powe...
详细信息
Computational models based on deep learning are today integrated in many safety-critical domains. These algorithms, such as deep neural networks (DNNs), are rapidly growing in size, reaching billions or even trillions...
Computational models based on deep learning are today integrated in many safety-critical domains. These algorithms, such as deep neural networks (DNNs), are rapidly growing in size, reaching billions or even trillions of parameters. This factor brings big challenges not only for performance goals but also for dependability aspects such as reliability. The larger the model, the more challenging the reliability assessment becomes. It is now crucial to develop new test approaches supported by acceptable computational costs for the detection of random-hardware faults such as permanent faults, which may change the predictions of DNNs. The aim of this paper is to leverage tensor-related metrics to early detect faulty behaviors during the inference of DNNs. This involves calculating metrics applied to tensors across various domains (such as imageprocessing, audio analysis, and regression) on the Output Feature Maps (OFMs) of a layer. This analysis allows knowing in advance the effect that a permanent fault will have on the output of the DNN application. The effectiveness of the approach has been experimentally demonstrated by means of software fault injection campaigns considering faults affecting weights of Convolutional Neural Networks (CNNs), i.e., ResNet20 and MobileNetv2. The quality of the metrics is discussed in terms of the trade-off between energy consumption and the ability to differentiate between critical and non-critical faults.
veterinary students often face challenges in assessing cow's hoof health due to limited access to live animals and insufficient practical materials, which hinder hands-on experience and impact treatment outcomes. ...
详细信息
ISBN:
(数字)9798331506490
ISBN:
(纸本)9798331506506
veterinary students often face challenges in assessing cow's hoof health due to limited access to live animals and insufficient practical materials, which hinder hands-on experience and impact treatment outcomes. To address these gaps, this study developed WounderCow, a web-based application that integrates imageprocessing, 3D modeling, and AI-driven treatment recommendations. The system allows users to predict cow hoof infections, classify lameness types, assess severity, and receive appropriate treatment recommendations. The development process followed the Agile Scrum framework, with iterative stages focusing on refining key components like imageprocessing, 3D modeling, and AI-driven predictions. After system development, a survey was administered to 53 participants-veterinary students, farmers, and IT professionals-using a four-point Likert scale questionnaire. The results were analyzed to evaluate how well the system met the needs of users. To assess the system's accuracy, a confusion matrix was used to measure precision, recall, and overall accuracy in predicting lameness type, severity, and treatment recommendations. The system was also evaluated against ISO/IEC 25010 standards, ensuring that it met criteria for usability, performance, and reliability. The survey results showed significant satisfaction, with weighted mean scores ranging from 3.29 to 3.45, and 61.9% of respondents strongly agreed that the system improved their ability to assess and treat hoof health issues. The application enables early lameness detection and includes a 3D simulator with step-by-step guidance for hoof scraping and treatment. This study highlights the application's potential to bridge educational gaps while advancing diagnostic and treatment practices for cow hoof conditions.
暂无评论