Pub Date : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00130
R. Bharathi, N. Ashwini, R. Bhagya, G. Bhagya, Rameez Pathan, Sambedh Kandel
A thorough analysis is required for assessment of structural health of road infrastructures. A Computer Vision Technology based analysis of images will help us for better management of roads/ pavements in long run. A Convolutional Neural Networks (CNN) based Deep Learning algorithm can be constructed, which can take in an input image used for pavement classification. In this paper, a python based algorithm is proposed and it is simulated for experimental results using automated system software which detects the cracks on the road. The approach used in this paper is mainly based on full surface reconstruction in 3D pavement. The automated method achieves same accuracy with a reduced cost when compared to manual computation.
{"title":"Crack Detector Automation for Roads by Deep Learning","authors":"R. Bharathi, N. Ashwini, R. Bhagya, G. Bhagya, Rameez Pathan, Sambedh Kandel","doi":"10.1109/INDIACom51348.2021.00130","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00130","url":null,"abstract":"A thorough analysis is required for assessment of structural health of road infrastructures. A Computer Vision Technology based analysis of images will help us for better management of roads/ pavements in long run. A Convolutional Neural Networks (CNN) based Deep Learning algorithm can be constructed, which can take in an input image used for pavement classification. In this paper, a python based algorithm is proposed and it is simulated for experimental results using automated system software which detects the cracks on the road. The approach used in this paper is mainly based on full surface reconstruction in 3D pavement. The automated method achieves same accuracy with a reduced cost when compared to manual computation.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128749016","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00009
N. Sharma, M. Mangla, S. Mohanty, Suneeta Satpathy
The manuscript aims to present a project enabling one to control electronic devices though hand gestures and convert one's hand into a wand. All the remote-controlled devices like your television sets, home theatre systems, air conditioners, cars, fans, lights, and other everyday electrical appliances can be controlled just with a flick of the hand. For this, the project uses a smart combination of Inertial Measurement Units (IMUs) and Machine Learning (ML) to identify the control target and command action by intuitive gestures. The control commands are forwarded through home wi-Fi. The product is completely customizable and hence one can easily configure that how one's hand gesture will control a device. Also, one can train it to understand custom hand gestures. The project enables user to have a consistent interaction experience everywhere. This project can be considered as a boon to elderly population who often have a tough time handling several remotes with several buttons on each remote. Hence, the project leads to a seamless experience for them while adapting to the technological advancements unknowingly.
{"title":"A Gesture based Remote Control for Home Appliances","authors":"N. Sharma, M. Mangla, S. Mohanty, Suneeta Satpathy","doi":"10.1109/INDIACom51348.2021.00009","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00009","url":null,"abstract":"The manuscript aims to present a project enabling one to control electronic devices though hand gestures and convert one's hand into a wand. All the remote-controlled devices like your television sets, home theatre systems, air conditioners, cars, fans, lights, and other everyday electrical appliances can be controlled just with a flick of the hand. For this, the project uses a smart combination of Inertial Measurement Units (IMUs) and Machine Learning (ML) to identify the control target and command action by intuitive gestures. The control commands are forwarded through home wi-Fi. The product is completely customizable and hence one can easily configure that how one's hand gesture will control a device. Also, one can train it to understand custom hand gestures. The project enables user to have a consistent interaction experience everywhere. This project can be considered as a boon to elderly population who often have a tough time handling several remotes with several buttons on each remote. Hence, the project leads to a seamless experience for them while adapting to the technological advancements unknowingly.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120850091","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00082
Urvashi Mishra
Gurmukhi Language is a dominating language in northern states. Many documents written in this dialect become the subject matter of judicial scrutiny, where again much is left to conjectural analysis. It is a humble effort to devise scientific technology and tools for application to verify Gurmukhi handwriting - one disputed to be verified along with the genuine and admitted one. The rules and technology applied in English language is far less useful for the reason of its 35 original letters-consonants covered in three zones but more of them in upper and middle one; and frequent use of 11 diacritics - 9 of them being applied in the upper two zones of the writing. Accordingly, the paper makes a forensic analysis of two zones of writing because of their dominant use. Again, the relativity and aspect ratio methods of handwriting verification are worth bringing satisfactory results in determining genuineness of a handwritten document in Gurmukhi script subject to the judicial scrutiny. The researcher illustrates the application of relativity and aspect ratio along study of two zones of Gurmukhi language resulting in identifying the similarity or marked difference of the two writings.
{"title":"Forensic Analysis of Gurmukhi Letters based on Zone Division for Verification","authors":"Urvashi Mishra","doi":"10.1109/INDIACom51348.2021.00082","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00082","url":null,"abstract":"Gurmukhi Language is a dominating language in northern states. Many documents written in this dialect become the subject matter of judicial scrutiny, where again much is left to conjectural analysis. It is a humble effort to devise scientific technology and tools for application to verify Gurmukhi handwriting - one disputed to be verified along with the genuine and admitted one. The rules and technology applied in English language is far less useful for the reason of its 35 original letters-consonants covered in three zones but more of them in upper and middle one; and frequent use of 11 diacritics - 9 of them being applied in the upper two zones of the writing. Accordingly, the paper makes a forensic analysis of two zones of writing because of their dominant use. Again, the relativity and aspect ratio methods of handwriting verification are worth bringing satisfactory results in determining genuineness of a handwritten document in Gurmukhi script subject to the judicial scrutiny. The researcher illustrates the application of relativity and aspect ratio along study of two zones of Gurmukhi language resulting in identifying the similarity or marked difference of the two writings.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121368525","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00026
Neeraj Kumar, M. M. Tripathi
The Development scenario for renewable energy across the globe is changing rapidly in terms of capacity addition and grid interconnection. The impact of wind energy on electricity price is significant and it is an important task for power system planners to forecast the price in light of its variability. The impact of wind energy penetration on electricity price using Support Vector Regression (SVR) and Deep Neural Network (DNN) has been investigated for the Austria Electricity market. From the evaluation metrics calculation, it is observed that the DNN model performs better over SVR for the available dataset. The MAPE Value for DNN model was found 5.384 for the available dataset.
{"title":"Impact Analysis of wind Energy on Electricity Price using Deep Neural Network","authors":"Neeraj Kumar, M. M. Tripathi","doi":"10.1109/INDIACom51348.2021.00026","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00026","url":null,"abstract":"The Development scenario for renewable energy across the globe is changing rapidly in terms of capacity addition and grid interconnection. The impact of wind energy on electricity price is significant and it is an important task for power system planners to forecast the price in light of its variability. The impact of wind energy penetration on electricity price using Support Vector Regression (SVR) and Deep Neural Network (DNN) has been investigated for the Austria Electricity market. From the evaluation metrics calculation, it is observed that the DNN model performs better over SVR for the available dataset. The MAPE Value for DNN model was found 5.384 for the available dataset.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"33 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116303934","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00157
Mohd Tajammul, R. Parveen, I. Tayubi
Cloud computing is a technique that enables the users to access applications to infrastructure through subscription methods on remote location. Cloud computing, being collective technique, possesses features of various technologies like Virtual Private Network (VPN), distributed technology, parallel computing, grid computing as well as ubiquitous computing. Cloud storage is the infrastructure offered by the cloud computing in order to facilitate users to upload and access their data on cloud space. Due to multitenancy of cloud storage, the data uploaded on it is the more prone to security breaches. To secure the data on cloud, cryptographic technique is used which works like safeguard against data leakage. This research work focuses on cryptographic algorithms from most basic to advance and also presents their comparative analysis. Moreover, the paper focuses on the nature of the algorithms in context of cloud that is homogeneous and heterogeneous nature. In the cloud computing, homogeneous nature algorithm is used only if the encryptors and decryptors both are same while heterogeneous refers to the situation in which encryptors and decryptors are different entities.
{"title":"Comparative Analysis of Security Algorithms used in Cloud Computing","authors":"Mohd Tajammul, R. Parveen, I. Tayubi","doi":"10.1109/INDIACom51348.2021.00157","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00157","url":null,"abstract":"Cloud computing is a technique that enables the users to access applications to infrastructure through subscription methods on remote location. Cloud computing, being collective technique, possesses features of various technologies like Virtual Private Network (VPN), distributed technology, parallel computing, grid computing as well as ubiquitous computing. Cloud storage is the infrastructure offered by the cloud computing in order to facilitate users to upload and access their data on cloud space. Due to multitenancy of cloud storage, the data uploaded on it is the more prone to security breaches. To secure the data on cloud, cryptographic technique is used which works like safeguard against data leakage. This research work focuses on cryptographic algorithms from most basic to advance and also presents their comparative analysis. Moreover, the paper focuses on the nature of the algorithms in context of cloud that is homogeneous and heterogeneous nature. In the cloud computing, homogeneous nature algorithm is used only if the encryptors and decryptors both are same while heterogeneous refers to the situation in which encryptors and decryptors are different entities.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121506553","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00153
Aman Kumar, M. Sipani, Puneeta Marwaha
ECG or electrocardiogram assesses an individual's cardiac rhythm as a signal. This signal is the significant result of repolarisation and depolarisation of heart's four chambers, through which voltage can be interpreted over time. The presumption of this paper is the implementation of supervised deep learning to identify the visualisation and illustration of labelled rhythmic aberrations. The proposed technique uses a series of one dimensional convolutional paired with set of multilayer perceptron to classify and detect the most common arrhythmias. The model was trained with 75% of the data available which was first sampled, and then, tested on the natural distribution of data. The accuracy of model proved to be very efficient after the implementation of the model trained by using supervised deep learning and some techniques of signal processing. Thus, providing an accuracy of 98.3% with a tolerance value of 0.0040, iterating over multiple number of iterations. Future scope of this proposition includes different processing techniques with slight adjustments within the model and its architecture.
{"title":"A Deep Learning Approach for the Classification of Arrhythmias in ECG Signal","authors":"Aman Kumar, M. Sipani, Puneeta Marwaha","doi":"10.1109/INDIACom51348.2021.00153","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00153","url":null,"abstract":"ECG or electrocardiogram assesses an individual's cardiac rhythm as a signal. This signal is the significant result of repolarisation and depolarisation of heart's four chambers, through which voltage can be interpreted over time. The presumption of this paper is the implementation of supervised deep learning to identify the visualisation and illustration of labelled rhythmic aberrations. The proposed technique uses a series of one dimensional convolutional paired with set of multilayer perceptron to classify and detect the most common arrhythmias. The model was trained with 75% of the data available which was first sampled, and then, tested on the natural distribution of data. The accuracy of model proved to be very efficient after the implementation of the model trained by using supervised deep learning and some techniques of signal processing. Thus, providing an accuracy of 98.3% with a tolerance value of 0.0040, iterating over multiple number of iterations. Future scope of this proposition includes different processing techniques with slight adjustments within the model and its architecture.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114686907","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00125
Bhuvanesh Singh, D. Sharma
Social media platforms play a significant role in spreading news in the current digital era. However, they have also been spreading fake images. Forged images posted on social media platform such as Twitter create misrepresentation and generate harmful user emotions. Thus, detecting fake images over social media platforms has become a critical need of time. Deep learning convolutional networks can learn the intrinsic feature set of images and can detect forged images. This paper proposes a convolutional neural network to spot fake images shared over social media platforms. High pass filters from image processing are used in the first layer for weight initialization. This helps the neural network converge faster and achieve better accuracy. Interpretability is a common concern in deep learning models. The proposed framework employs Gradient-weighted Class Activation Mapping to generate heatmaps and localize the image's manipulated area. The model is verified against the publicly available CASIA dataset. An accuracy of 92.3% is achieved, which is better than the other previous models. From the social media perspective, the model is verified against the latest Twitter dataset. The experiment proves that convolutional neural networks perform well in detecting forged images over social media platforms, and interpretability can be achieved.
{"title":"Image Forgery over Social Media Platforms - A Deep Learning Approach for its Detection and Localization","authors":"Bhuvanesh Singh, D. Sharma","doi":"10.1109/INDIACom51348.2021.00125","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00125","url":null,"abstract":"Social media platforms play a significant role in spreading news in the current digital era. However, they have also been spreading fake images. Forged images posted on social media platform such as Twitter create misrepresentation and generate harmful user emotions. Thus, detecting fake images over social media platforms has become a critical need of time. Deep learning convolutional networks can learn the intrinsic feature set of images and can detect forged images. This paper proposes a convolutional neural network to spot fake images shared over social media platforms. High pass filters from image processing are used in the first layer for weight initialization. This helps the neural network converge faster and achieve better accuracy. Interpretability is a common concern in deep learning models. The proposed framework employs Gradient-weighted Class Activation Mapping to generate heatmaps and localize the image's manipulated area. The model is verified against the publicly available CASIA dataset. An accuracy of 92.3% is achieved, which is better than the other previous models. From the social media perspective, the model is verified against the latest Twitter dataset. The experiment proves that convolutional neural networks perform well in detecting forged images over social media platforms, and interpretability can be achieved.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124435735","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00112
S. K. Muttoo, Shikha Badhani
Malware creators have been very opportunistic in creating novel malware by leveraging the vulnerabilities which can be either at system level or environmental level. Covid-19 pandemic was the next opportunity for them. Novel malwares were seen exploiting the new normal lifestyle during the Covid-19 pandemic. In this paper, we explore the malwares that were observed specially during the Covid-19 pandemic and then present an analysis of malware detection techniques with a focus on these Covid-19-themed malwares. This study aims to set a baseline for cyber security researchers exploring the malwares that surged during the Covid-19 pandemic and the malware detection techniques.
{"title":"An Analysis of Malware Detection and Control through Covid-19 Pandemic","authors":"S. K. Muttoo, Shikha Badhani","doi":"10.1109/INDIACom51348.2021.00112","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00112","url":null,"abstract":"Malware creators have been very opportunistic in creating novel malware by leveraging the vulnerabilities which can be either at system level or environmental level. Covid-19 pandemic was the next opportunity for them. Novel malwares were seen exploiting the new normal lifestyle during the Covid-19 pandemic. In this paper, we explore the malwares that were observed specially during the Covid-19 pandemic and then present an analysis of malware detection techniques with a focus on these Covid-19-themed malwares. This study aims to set a baseline for cyber security researchers exploring the malwares that surged during the Covid-19 pandemic and the malware detection techniques.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124148606","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00095
S. Kaur, Gaganpreet Kaur
Cloud technology is a shared pool of configurable computer system resources and higher-level services that can be rapidly provisioned with minimal management effort over the internet. It has enormous advantages but also has many security risks. Cloud users require understanding emerging threats, vulnerabilities, and plan possible countermeasures before transferring their computing, storage, and application to remote locations. Due to its rising threats, identification of the vulnerabilities and most appropriate solution directives to strengthen security in the cloud environment becomes paramount for all operations in it. In our study, we have scrutinized the threats along with vulnerable area and classified them based on three domains from the perspective of users. To mitigate the threats, possible existing countermeasures are listed against each threat in this paper.
{"title":"Threat and Vulnerability Analysis of Cloud Platform: A User Perspective","authors":"S. Kaur, Gaganpreet Kaur","doi":"10.1109/INDIACom51348.2021.00095","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00095","url":null,"abstract":"Cloud technology is a shared pool of configurable computer system resources and higher-level services that can be rapidly provisioned with minimal management effort over the internet. It has enormous advantages but also has many security risks. Cloud users require understanding emerging threats, vulnerabilities, and plan possible countermeasures before transferring their computing, storage, and application to remote locations. Due to its rising threats, identification of the vulnerabilities and most appropriate solution directives to strengthen security in the cloud environment becomes paramount for all operations in it. In our study, we have scrutinized the threats along with vulnerable area and classified them based on three domains from the perspective of users. To mitigate the threats, possible existing countermeasures are listed against each threat in this paper.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126447495","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 : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00027
Sanskruti Patel
Artificial Intelligence and deep learning models have evolved rapidly in the last decade and successfully applied to face recognition, autonomous driving, satellite imaging, robotics, and many more. Computer vision tasks often require adequate segmentation of an image that helps to understand the patterns and information. The adequate segmentation makes the analysis of each part of an image easier. Traditional segmentation techniques are often applied for image segmentation, but they are less efficient than deep learning techniques. Using deep learning approaches, it is possible to obtain hierarchical feature representations directly from the images, and hence, it eliminates the requirement of handcrafted features. This paper covers the fundamentals of image segmentation and deep learning, deep learning models for image segmentation, some successful implementations of deep learning models for image segmentation, and available open and benchmark datasets for image segmentation tasks.
{"title":"Deep Learning Models for Image Segmentation","authors":"Sanskruti Patel","doi":"10.1109/INDIACom51348.2021.00027","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00027","url":null,"abstract":"Artificial Intelligence and deep learning models have evolved rapidly in the last decade and successfully applied to face recognition, autonomous driving, satellite imaging, robotics, and many more. Computer vision tasks often require adequate segmentation of an image that helps to understand the patterns and information. The adequate segmentation makes the analysis of each part of an image easier. Traditional segmentation techniques are often applied for image segmentation, but they are less efficient than deep learning techniques. Using deep learning approaches, it is possible to obtain hierarchical feature representations directly from the images, and hence, it eliminates the requirement of handcrafted features. This paper covers the fundamentals of image segmentation and deep learning, deep learning models for image segmentation, some successful implementations of deep learning models for image segmentation, and available open and benchmark datasets for image segmentation tasks.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127987821","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：