Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170195
P. Suhas Reddy, Jayanth Anala, V. Krishnamurthy, B Surendiran, R. Sujithra @ Kanmani
The Model-View-Controller (MVC) design pattern is widely used in software engineering for developing user interfaces. While MVC offers many benefits, handling data in a way that is efficient and effective can be a challenge. One approach to optimising the performance of MVC applications is converting lists to dictionaries. This paper discusses the benefits and drawbacks of this approach and presents the findings of recent research on this topic. The main advantage of converting lists to dictionaries is that it can improve the performance of MVC applications by offering faster access times and making code easier to read and maintain. However, there are drawbacks to this approach, such as increased memory usage and slower performance for certain operations. Several studies have been conducted on the performance of MVC applications when using lists versus dictionaries, with varying results. This paper overviews this research and highlights the implications for MVC development.
{"title":"Performance Improvement of Model View Controller based Applications through Linda’s-Key","authors":"P. Suhas Reddy, Jayanth Anala, V. Krishnamurthy, B Surendiran, R. Sujithra @ Kanmani","doi":"10.1109/IConSCEPT57958.2023.10170195","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170195","url":null,"abstract":"The Model-View-Controller (MVC) design pattern is widely used in software engineering for developing user interfaces. While MVC offers many benefits, handling data in a way that is efficient and effective can be a challenge. One approach to optimising the performance of MVC applications is converting lists to dictionaries. This paper discusses the benefits and drawbacks of this approach and presents the findings of recent research on this topic. The main advantage of converting lists to dictionaries is that it can improve the performance of MVC applications by offering faster access times and making code easier to read and maintain. However, there are drawbacks to this approach, such as increased memory usage and slower performance for certain operations. Several studies have been conducted on the performance of MVC applications when using lists versus dictionaries, with varying results. This paper overviews this research and highlights the implications for MVC development.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125247930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170238
S. Ajakwe, Dong‐Seong Kim, Jae Min Lee
The importance of a cyber-edge and cognitive artificial intelligence (AI)-based security strategy to boost autonomous underwater navigation and aerial mobility and prevent hetero-geneous reprisal attacks cannot be overemphasized. This paper proposes a split of super-resolution (SR) to reconstruct the channel state information (CSI) through self-supervised learning for a multiple-input-multiple-output (MIMO) system. Unlike existing designs, this study used a split of SR into two disjoint sub-blocks through transfer learning to improve the CSI detailed structures in the reconstruction process. The simulation results show that the proposed system significantly improved the quality of the CSI after reconstruction compared to the existing system in terms of cosine similarity $rho$ of 95.2% and normalized mean square error (NMSE) of −16.33 at different compression rates for both indoor and outdoor environments, which is essential for a MIMO system in improving performance, coverage, reliability, and user experience in 5G and 6G networks.
{"title":"CogNet: Cognitive Super Resolution Network for Persistent End-to-End Mobility Communication in MIMO Systems","authors":"S. Ajakwe, Dong‐Seong Kim, Jae Min Lee","doi":"10.1109/IConSCEPT57958.2023.10170238","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170238","url":null,"abstract":"The importance of a cyber-edge and cognitive artificial intelligence (AI)-based security strategy to boost autonomous underwater navigation and aerial mobility and prevent hetero-geneous reprisal attacks cannot be overemphasized. This paper proposes a split of super-resolution (SR) to reconstruct the channel state information (CSI) through self-supervised learning for a multiple-input-multiple-output (MIMO) system. Unlike existing designs, this study used a split of SR into two disjoint sub-blocks through transfer learning to improve the CSI detailed structures in the reconstruction process. The simulation results show that the proposed system significantly improved the quality of the CSI after reconstruction compared to the existing system in terms of cosine similarity $rho$ of 95.2% and normalized mean square error (NMSE) of −16.33 at different compression rates for both indoor and outdoor environments, which is essential for a MIMO system in improving performance, coverage, reliability, and user experience in 5G and 6G networks.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131243698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170113
Ramanuj Bhattacharjee, K. Suganya Devi, S. Vijaykanth
To improve the chances of survival for a patient with laryngeal cancer, early detection is crucial. Currently, the standard diagnostic method involves an endoscopic examination of the larynx, followed by a biopsy and histological analysis by an oncologist, which can be subject to variability due to subjective evaluation. Therefore, there is a need for a faster and more accurate detection system that can replace the current manual examination. Recent research has shown that Deep Learning technology can assist in identifying laryngeal cancer, including precancerous and cancerous tumors, from endoscopic pictures. However, endoscopic image processing is a challenging task due to the highly dynamic nature of the endoscopic video, spectrum fluctuations, and numerous image interferences. To address this challenge, a Deep Ensemble Learning approach using convolutional neural networks (CNNs) and an effective image segmentation technique has been proposed. The suggested model has an overall accuracy of 98.12%.
{"title":"Detecting Laryngeal Cancer Lesions From Endoscopy Images Using Deep Ensemble Model","authors":"Ramanuj Bhattacharjee, K. Suganya Devi, S. Vijaykanth","doi":"10.1109/IConSCEPT57958.2023.10170113","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170113","url":null,"abstract":"To improve the chances of survival for a patient with laryngeal cancer, early detection is crucial. Currently, the standard diagnostic method involves an endoscopic examination of the larynx, followed by a biopsy and histological analysis by an oncologist, which can be subject to variability due to subjective evaluation. Therefore, there is a need for a faster and more accurate detection system that can replace the current manual examination. Recent research has shown that Deep Learning technology can assist in identifying laryngeal cancer, including precancerous and cancerous tumors, from endoscopic pictures. However, endoscopic image processing is a challenging task due to the highly dynamic nature of the endoscopic video, spectrum fluctuations, and numerous image interferences. To address this challenge, a Deep Ensemble Learning approach using convolutional neural networks (CNNs) and an effective image segmentation technique has been proposed. The suggested model has an overall accuracy of 98.12%.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"273 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131560302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170474
P. Aruna, V. Vasan Prabhu, V. Krishnakumar
In this paper, modeling and estimating the parameters of the Enhanced Self-Correcting (ESC) model of a lithium-ion cell is presented so that the behaviour of the cell can be better understood with high fidelity. When the lithium-ion cell is used as battery pack in Electric Vehicle (EV), it is critical to have reliable temperaturedependent parameters to forecast aging and to determine how the cell responds to different operating scenarios of EV. This study is significant because it takes into account the voltage hysteresis effect, which is necessary for precise estimation of State of Charge (SOC) and State of Health (SOH) in order to forecast EV range. Open circuit voltage testing and dynamic testing at various temperatures are used in this paper to determine the parameters of the ESC model. The simulations are done using MATLAB and the results are obtained with high accuracy.
{"title":"Modeling and Estimation of Enhanced Self Correcting Model Parameters of Lithium Ion Cell","authors":"P. Aruna, V. Vasan Prabhu, V. Krishnakumar","doi":"10.1109/IConSCEPT57958.2023.10170474","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170474","url":null,"abstract":"In this paper, modeling and estimating the parameters of the Enhanced Self-Correcting (ESC) model of a lithium-ion cell is presented so that the behaviour of the cell can be better understood with high fidelity. When the lithium-ion cell is used as battery pack in Electric Vehicle (EV), it is critical to have reliable temperaturedependent parameters to forecast aging and to determine how the cell responds to different operating scenarios of EV. This study is significant because it takes into account the voltage hysteresis effect, which is necessary for precise estimation of State of Charge (SOC) and State of Health (SOH) in order to forecast EV range. Open circuit voltage testing and dynamic testing at various temperatures are used in this paper to determine the parameters of the ESC model. The simulations are done using MATLAB and the results are obtained with high accuracy.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133977526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170546
N. Usha Bhanu, C. Saravanakumar
The growing demand of high-resolution video on portable devices, the applications require higher coding efficiency, high throughput and low power for handling heterogenous types of video signals. This paper presents a survey on possibility of applying Machine Learning (ML) models in H.265/ HEVC video encoder unit. Higher computational complexity with respect to motion estimation, coding, and parallel processing architectures are required for HEVC. The existing HEVC algorithms are based on spatial temporal relationship which requires dynamic video sequences handling for fast changes in scenes. This paper focuses on the possible realization of machine learning algorithms for Rate Control (RC) in video sequences, Coding Unit (CU) depth decision, Neural network-based Motion Estimation and Compensation, adaptive de-blocking filter for reducing blocking artifacts and task driven semantic coding for real time video applications. The algorithms are surveyed with respect to the learning process used in various units of HEVC encoders and summarized in terms of parameters achieved and datasets used in the existing literature.
{"title":"Investigations of Machine Learning Algorithms for High Efficiency Video Coding (HEVC)","authors":"N. Usha Bhanu, C. Saravanakumar","doi":"10.1109/IConSCEPT57958.2023.10170546","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170546","url":null,"abstract":"The growing demand of high-resolution video on portable devices, the applications require higher coding efficiency, high throughput and low power for handling heterogenous types of video signals. This paper presents a survey on possibility of applying Machine Learning (ML) models in H.265/ HEVC video encoder unit. Higher computational complexity with respect to motion estimation, coding, and parallel processing architectures are required for HEVC. The existing HEVC algorithms are based on spatial temporal relationship which requires dynamic video sequences handling for fast changes in scenes. This paper focuses on the possible realization of machine learning algorithms for Rate Control (RC) in video sequences, Coding Unit (CU) depth decision, Neural network-based Motion Estimation and Compensation, adaptive de-blocking filter for reducing blocking artifacts and task driven semantic coding for real time video applications. The algorithms are surveyed with respect to the learning process used in various units of HEVC encoders and summarized in terms of parameters achieved and datasets used in the existing literature.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134318393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170410
Sumanth Reddy Poluri, Venkata Krishna Reddy Tiyyagura, K. S. Sri
An accurate model for DBSCAN (Outlier detection and removal). And implementing KNN by predicting the suitable k value. While SMOTE-ENN is used to balance the training dataset. Gradient boosting is a technique where new models are made and used to forecast the residuals or error, then the scores are added to find the presence or absence of disease. And implementing KNN by predicting the suitable k value. The model was built using few publicly accessible datasets, Statlog, heart failure clinical records datasets and Cleveland. These respective models output was compared to Each other respectively.
{"title":"Heart Disease Prediction Based On Machine Learning","authors":"Sumanth Reddy Poluri, Venkata Krishna Reddy Tiyyagura, K. S. Sri","doi":"10.1109/IConSCEPT57958.2023.10170410","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170410","url":null,"abstract":"An accurate model for DBSCAN (Outlier detection and removal). And implementing KNN by predicting the suitable k value. While SMOTE-ENN is used to balance the training dataset. Gradient boosting is a technique where new models are made and used to forecast the residuals or error, then the scores are added to find the presence or absence of disease. And implementing KNN by predicting the suitable k value. The model was built using few publicly accessible datasets, Statlog, heart failure clinical records datasets and Cleveland. These respective models output was compared to Each other respectively.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134554233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170710
S. Karthika Shree, Vaishali Vijayarajan, B. Sathya Bama, S. Mohammed Mansoor Roomi
Milk has been an essential part of our food culture as it contains important micronutrients and macronutrients. Milk is contaminated by the addition of water and preservatives. Traditionally, screening of milk quality was performed using human-based methods which have limitations such as being labor-intensive, time-consuming, and expensive. Therefore, non-destructive testing of milk quality using Hyperspectral imaging (HSI) is implemented. Compared to manual milk quality tests, HSI (Hyperspectral image) is faster and does not involve destructive methods. Pasteurized milk and vendor milk are used for sample preparation whereas water, Ammonium sulphate, and Ammonium chloride are chosen as adulterants. Therefore, the database is generated by capturing the images of milk samples with three different types of adulterants that are mixed with milk (Water, Ammonium Sulphate, and Ammonium Chloride) using the Resonon Hyperspectral camera (pika L, 400–1000 nm). Further, they are classified into three class classifications depending on the level of adulterants added. The problem of feature redundancy and noise is solved by using PCA-based Explained variance. On choosing ROI, the mean spectral curve is obtained and the optimal wavelength is chosen for extracting features and trained through machine learning classifiers like Ensemble, K-nearest neighbor, and Support Vector Machine for the three-class classification problem out of which the K-nearest neighbor, classifier reported the highest accuracy of 87%, 85%, 88% for vendor milk adulterant level classification and 84%, 87%, 85% for pasteurized milk adulterant level classification.
{"title":"Milk Quality Inspection Using Hyperspectral Imaging","authors":"S. Karthika Shree, Vaishali Vijayarajan, B. Sathya Bama, S. Mohammed Mansoor Roomi","doi":"10.1109/IConSCEPT57958.2023.10170710","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170710","url":null,"abstract":"Milk has been an essential part of our food culture as it contains important micronutrients and macronutrients. Milk is contaminated by the addition of water and preservatives. Traditionally, screening of milk quality was performed using human-based methods which have limitations such as being labor-intensive, time-consuming, and expensive. Therefore, non-destructive testing of milk quality using Hyperspectral imaging (HSI) is implemented. Compared to manual milk quality tests, HSI (Hyperspectral image) is faster and does not involve destructive methods. Pasteurized milk and vendor milk are used for sample preparation whereas water, Ammonium sulphate, and Ammonium chloride are chosen as adulterants. Therefore, the database is generated by capturing the images of milk samples with three different types of adulterants that are mixed with milk (Water, Ammonium Sulphate, and Ammonium Chloride) using the Resonon Hyperspectral camera (pika L, 400–1000 nm). Further, they are classified into three class classifications depending on the level of adulterants added. The problem of feature redundancy and noise is solved by using PCA-based Explained variance. On choosing ROI, the mean spectral curve is obtained and the optimal wavelength is chosen for extracting features and trained through machine learning classifiers like Ensemble, K-nearest neighbor, and Support Vector Machine for the three-class classification problem out of which the K-nearest neighbor, classifier reported the highest accuracy of 87%, 85%, 88% for vendor milk adulterant level classification and 84%, 87%, 85% for pasteurized milk adulterant level classification.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124449499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170617
Akhil Nair, R. Charan, Hari Krishna S, G. Rohith
Monitoring attendance is an essential administrative function in all educational institutions and organizations. A well-structured framework will facilitate the expansion of institutions. It reduces the instructors’ time and effort by assisting both students and teachers in improving attendance. The existing conventional physical classroom system is insecure, disruptive to teaching, and time-consuming to gather and store student attendance, which hampers the educational activities. The proposed system is a hybridized framework of face detection and recognition, and ID card detection and card text verification that adds to the two level authentication system. At the first level, the proposed system recognizes the individual, authenticates it with database data, and detects the ID card using deep Hog based ResNet feature extraction syttem. At the second level, YoloV7 based Easy OCR reads the details and marks the concerned individual as present. This hybridized framework is accurate in identifying the persons irrespective of the illumination conditions and an efficient attendance system.
{"title":"A Two-level authentication for Attendance Management System using deep learning techniques","authors":"Akhil Nair, R. Charan, Hari Krishna S, G. Rohith","doi":"10.1109/IConSCEPT57958.2023.10170617","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170617","url":null,"abstract":"Monitoring attendance is an essential administrative function in all educational institutions and organizations. A well-structured framework will facilitate the expansion of institutions. It reduces the instructors’ time and effort by assisting both students and teachers in improving attendance. The existing conventional physical classroom system is insecure, disruptive to teaching, and time-consuming to gather and store student attendance, which hampers the educational activities. The proposed system is a hybridized framework of face detection and recognition, and ID card detection and card text verification that adds to the two level authentication system. At the first level, the proposed system recognizes the individual, authenticates it with database data, and detects the ID card using deep Hog based ResNet feature extraction syttem. At the second level, YoloV7 based Easy OCR reads the details and marks the concerned individual as present. This hybridized framework is accurate in identifying the persons irrespective of the illumination conditions and an efficient attendance system.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131490880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170152
V. Krishnamurthy, B. Jafrin Rosary, G. Oliver Joel, B Surendiran, Sakshi Kumari
This research work aims to create an Augmented Reality (AR) based android app that can project the dimensions of an automobile in the real world and recognize voice commands to operate functions like opening car doors and changing colors. The app uses a combination of augmented reality, machine learning technology, Unity game engine, C# script, Google speech recognition API and Vuforia SDK to superimpose images of the car in the real world and allow control through voice commands. The initial focus is on cars, but the solution can also be used to create AR-enabled brochures for marketing companies to enhance sales and provide customers with a better understanding of the product before purchase.
{"title":"Voice command-integrated AR-based E-commerce Application for Automobiles","authors":"V. Krishnamurthy, B. Jafrin Rosary, G. Oliver Joel, B Surendiran, Sakshi Kumari","doi":"10.1109/IConSCEPT57958.2023.10170152","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170152","url":null,"abstract":"This research work aims to create an Augmented Reality (AR) based android app that can project the dimensions of an automobile in the real world and recognize voice commands to operate functions like opening car doors and changing colors. The app uses a combination of augmented reality, machine learning technology, Unity game engine, C# script, Google speech recognition API and Vuforia SDK to superimpose images of the car in the real world and allow control through voice commands. The initial focus is on cars, but the solution can also be used to create AR-enabled brochures for marketing companies to enhance sales and provide customers with a better understanding of the product before purchase.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134599300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10169970
P. Manojkumar, L. S. Kumar, B. Jayanthi
Computer vision is a recent technological advancement to digitally perceive the real world at an advanced level, through digital images and videos. Object detection is a subset of computer vision which is one of the prominent techniques used for object tracking, automatic driving, anomaly detection, etc. Object detection can be based on either machine learning or deep learning algorithms, it can be used for the localization of the image and classification of elements into diverse classes. This work provides a comparison of the object detection approaches such as Region with Convolutional Neural Network (R-CNN), Fast R-CNN, and You Only Look Once(YOLO) and Single Shot multibox Detector (SSD). The implementation of an object detection technique YOLOv4 and a custom model are done, which recognizes the objects from an input image, webcam image and live stream webcam video.
计算机视觉是最近的一项技术进步，通过数字图像和视频在高级水平上数字化地感知现实世界。目标检测是计算机视觉的一个分支，是用于目标跟踪、自动驾驶、异常检测等领域的重要技术之一。物体检测可以基于机器学习或深度学习算法，它可以用于图像的定位和元素分类到不同的类别。本研究对区域卷积神经网络(R-CNN)、快速R-CNN和You Only Look Once(YOLO) and Single Shot multibox Detector (SSD)等目标检测方法进行了比较。实现了目标检测技术YOLOv4和自定义模型，从输入图像、网络摄像头图像和实时网络摄像头视频中识别目标。
{"title":"Performance Comparison of Real Time Object Detection Techniques with YOLOv4","authors":"P. Manojkumar, L. S. Kumar, B. Jayanthi","doi":"10.1109/IConSCEPT57958.2023.10169970","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10169970","url":null,"abstract":"Computer vision is a recent technological advancement to digitally perceive the real world at an advanced level, through digital images and videos. Object detection is a subset of computer vision which is one of the prominent techniques used for object tracking, automatic driving, anomaly detection, etc. Object detection can be based on either machine learning or deep learning algorithms, it can be used for the localization of the image and classification of elements into diverse classes. This work provides a comparison of the object detection approaches such as Region with Convolutional Neural Network (R-CNN), Fast R-CNN, and You Only Look Once(YOLO) and Single Shot multibox Detector (SSD). The implementation of an object detection technique YOLOv4 and a custom model are done, which recognizes the objects from an input image, webcam image and live stream webcam video.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133888055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：