Simultaneous sparse approximation (SSA) seeks to represent a set of dependent signals using sparse vectors with identical supports. The SSA model has been used in various signal and imageprocessing applications invol...
详细信息
ISBN:
(纸本)9781665459068
Simultaneous sparse approximation (SSA) seeks to represent a set of dependent signals using sparse vectors with identical supports. The SSA model has been used in various signal and imageprocessing applications involving multiple correlated input signals. In this paper, we propose algorithms for convolutional SSA (CSSA) based on the alternating direction method of multipliers. Specifically, we address the CSSA problem with different sparsity structures and the convolutional feature learning problem in multimodal data/signals based on the SSA model. We evaluate the proposed algorithms by applying them to multimodal and multifocus image fusion problems.
This position paper provides insights aiming at resolving the most pressing needs and issues of computer vision algorithms. Specifically, these problems relate to the scarcity of data, the inability of such algorithms...
详细信息
With the increase of image data scale, a faster and more efficient image acquisition and processing system is needed. FPGA has good parallel performance, which is very suitable for algorithms dealing with basic parall...
详细信息
This paper introduces the completed project development of a cutting-edge Vision Semantics image Captioner., a comprehensive platform aimed at generating contextually rich descriptions for images. Focused on leveragin...
详细信息
This research paper aims to address the critical need for efficient and accurate identification of chest diseases using chest X-rays through a combination of advanced imageprocessing techniques and machine learning a...
详细信息
ISBN:
(纸本)9798350375480;9798350375497
This research paper aims to address the critical need for efficient and accurate identification of chest diseases using chest X-rays through a combination of advanced imageprocessing techniques and machine learning algorithms. With the growing prevalence of respiratory and cardiovascular conditions worldwide, timely and precise diagnosis is paramount for effective patient care. The study begins with a comprehensive review of existing methodologies and technologies employed in the identification of chest diseases from X-ray images. It critically evaluates the strengths and limitations of current approaches, highlighting the challenges faced in achieving high accuracy, speed, and scalability. To address these issues, the project aims to develop an AI-powered system for medical image analysis. In response to these challenges, our research proposes a novel approach that integrates Inception V3 model and imagenet. We leverage a large dataset of annotated chest X-rays to train a deep neural network capable of recognizing subtle patterns indicative of various diseases, including pneumonia, pneumothorax, lung and cardiac abnormalities. The model is optimized to provide not only accurate diagnoses but also to minimize false positives and negatives. In conclusion, this research contributes to the ongoing efforts in utilizing chest X-ray images for disease identification, presenting a robust and efficient methodology that could revolutionize the current diagnostic landscape. The findings hold promise for the development of automated systems capable of assisting healthcare professionals in the accurate and timely detection of chest diseases, ultimately contributing to enhanced patient care and management.
Breast cancer is a significant global health concern, with early detection being critical for successful treatment and improved patient outcomes. In recent years, machine learning-based imageprocessing techniques hav...
详细信息
ISBN:
(纸本)9798350313987
Breast cancer is a significant global health concern, with early detection being critical for successful treatment and improved patient outcomes. In recent years, machine learning-based imageprocessing techniques have emerged as powerful tools in the field of medical imaging, particularly in breast cancer detection and diagnosis. This research paper explores the application of machine learning algorithms to enhance the accuracy and efficiency of breast cancer detection using various medical imaging modalities, such as mammography, ultrasound, and magnetic resonance imaging (MRI). The study begins by reviewing the current state of breast cancer detection methodologies and highlighting their limitations. It then delves into the utilization of machine learning algorithms, including convolutional neural networks (CNNs), support vector machines (SVMs), and deep learning models, for the automated analysis and interpretation of breast cancer images. Various preprocessing steps, feature extraction techniques, and data augmentation methods are discussed to optimize the performance of these algorithms. Furthermore, the paper examines the integration of machine learning models with radiomics, genomics, and clinical data to create comprehensive breast cancer diagnostic systems. These integrated systems aim to provide more accurate risk assessment, personalized treatment recommendations, and improved patient management. The results of several case studies and clinical trials are presented to demonstrate the effectiveness of machine learning-based imageprocessing techniques in breast cancer detection. These studies illustrate how these techniques can improve sensitivity, specificity, and overall diagnostic accuracy compared to traditional methods. This research underscores the promising role of machine learning-based imageprocessing techniques in advancing breast cancer detection. It highlights the potential for early diagnosis and improved patient care, paving the way for mor
Stellar energy exchange, fundamental to the dynamics of celestial systems, remains a captivating yet challenging area of study in astronomy. This paper introduces an innovative methodology for quantifying stellar ener...
详细信息
In recent times, Internet of Things (IoT) devices is gaining popularity in advanced wireless technology (i.e., 5G). However, in 5G applications (say in edge platform), the IoT devices have limited computation & pr...
详细信息
ISBN:
(纸本)9781665477062
In recent times, Internet of Things (IoT) devices is gaining popularity in advanced wireless technology (i.e., 5G). However, in 5G applications (say in edge platform), the IoT devices have limited computation & processing capabilities which makes it challenging to execute Deep Neural Network (DNN) models on them. To address this, we introduce Split Computing technology, to partition DNN inference layers based on the computational capabilities (such as bandwidth, battery level and processing power, etc.) of IoT and edge (computationally powerful) devices, respectively. To validate split computing, we propose a framework called Distributed Artificial Intelligence (DAI) architecture. We use the architecture for a fitness application (use-case) where we detect the pose of a person for our proposed Quantized Split PoseNet DNN (QSP-DNN) algorithm which partitions the DNN layers among IoT device and edge based on Wi-Fi bandwidth. We perform experiments to validate the QSP-DNN algorithm using DAI architecture. The QSP-DNN with DAI compares split execution (computed among IoT device & edge) for partial offload and full-offload executed on edge device. The result shows that using QSP-DNN in DAI architecture provides split execution performing 20.76 % improvement compared to the full offload case.
In the framework of the digital era, the technology of imageprocessing is one of the technologies that is being used increasingly often in all aspects of modern life. image correction may be handled using algorithms ...
详细信息
image based classification enables the acquisition and transfer of data from manual assembly workstations into a digital environment. Based on the Methods-Time Measurement method, assembly processes are transformed in...
详细信息
ISBN:
(纸本)9783031162817;9783031162800
image based classification enables the acquisition and transfer of data from manual assembly workstations into a digital environment. Based on the Methods-Time Measurement method, assembly processes are transformed into short, discrete basic operations that are recognised by means of imageprocessing and used as input data for a multilayer neural network. A recurrent neural network algorithm is investigated for its applicability in combination with the sensor data. The five basic MTM operations reaching, grasping, bringing, releasing, and positioning are classified and additional influencing factors, as well as the implementation of an object recognition, are investigated. The following paper addresses the question of the extent to which manual assembly processes can be reliably derived from visual sensor data and classified by machine learning algorithms.
暂无评论