Pub Date : 2021-11-26DOI: 10.1109/ICIIP53038.2021.9702633
Prafulkumar Kharade, Priyanka Priyadarshini Padhi, M. Vivek, P. S. Reddy, B. Prajwal
Electricity is a basic necessity for most appliances in modern machinery. There are varieties of applications that are dependent on electricity without which they are of no use. In day-to-day life, electricity is continuously modernizing and improving in the market. As the technologies are moving towards automation and automatic machines, the necessity of load shedding comes when the demand capacity is more than that of power generation capacity. Industries and companies are manufacturing modern circuits that help simplify lifestyle. The model is designed in such a way that it provides a very stable and efficient load shedding technique that takes over the manual operation of ON/OFF with respect to real-time. The Real-time clock DS1302 is interfaced with Arduino Uno. Our motto in this design is to program and execute the operation of load shedding automatically with an electrical load numerous times. By implementing this design one can overcome the challenges of manual action and operation of ON/OFF.
{"title":"Automatic Load shedding Time management using Arduino","authors":"Prafulkumar Kharade, Priyanka Priyadarshini Padhi, M. Vivek, P. S. Reddy, B. Prajwal","doi":"10.1109/ICIIP53038.2021.9702633","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702633","url":null,"abstract":"Electricity is a basic necessity for most appliances in modern machinery. There are varieties of applications that are dependent on electricity without which they are of no use. In day-to-day life, electricity is continuously modernizing and improving in the market. As the technologies are moving towards automation and automatic machines, the necessity of load shedding comes when the demand capacity is more than that of power generation capacity. Industries and companies are manufacturing modern circuits that help simplify lifestyle. The model is designed in such a way that it provides a very stable and efficient load shedding technique that takes over the manual operation of ON/OFF with respect to real-time. The Real-time clock DS1302 is interfaced with Arduino Uno. Our motto in this design is to program and execute the operation of load shedding automatically with an electrical load numerous times. By implementing this design one can overcome the challenges of manual action and operation of ON/OFF.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120966709","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 : 2021-11-26DOI: 10.1109/ICIIP53038.2021.9702564
Arpan Dam, Ashish Phophalia, V. Jain
Decision tree is one of the commonly used machine learning algorithm. Random Forest (RF) is an ensemble of such decision trees. The construction of optimal Decision Tree and hence Random Forest is NP Hard when data is large. The Bayesian statistics have been used in the past for various machine learning and pattern recognition problems. The Bayesian statistics provide a tool to construct Random Forest when no prior information for data is available. Here a forest is generated based on Bayesian statistics where numerous trees are sampled given the prior distribution without the use of training data, and after that weighted ensemble is performed. In the past, it has been used for classification problems. In this paper, we are proposing construction of RF under Bayesian framework using Tree Strength concept. Also, we extend our proposal to regression problems. The proposal is evaluated on UCI data sets for both classification and regression task and found satisfactory results.
{"title":"A Novel Bayesian Approach for Construction of Random Forest","authors":"Arpan Dam, Ashish Phophalia, V. Jain","doi":"10.1109/ICIIP53038.2021.9702564","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702564","url":null,"abstract":"Decision tree is one of the commonly used machine learning algorithm. Random Forest (RF) is an ensemble of such decision trees. The construction of optimal Decision Tree and hence Random Forest is NP Hard when data is large. The Bayesian statistics have been used in the past for various machine learning and pattern recognition problems. The Bayesian statistics provide a tool to construct Random Forest when no prior information for data is available. Here a forest is generated based on Bayesian statistics where numerous trees are sampled given the prior distribution without the use of training data, and after that weighted ensemble is performed. In the past, it has been used for classification problems. In this paper, we are proposing construction of RF under Bayesian framework using Tree Strength concept. Also, we extend our proposal to regression problems. The proposal is evaluated on UCI data sets for both classification and regression task and found satisfactory results.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125794947","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}
Coronavirus Disease or COVID-19 pandemic has taken over the world by storm. It has horrifying effect on the health of the people. Continuously rising number of COVID-19 cases has and still creating huge stress on the governing bodies of all countries, and they are finding it hard to find solution for the situation. This project's goal is to explore machine learning and develop a COVID-19 model that can predict number of cases with high accuracy. The proposed study employs SVR and PR models to forecast the number of recovered cases, confirmed cases, deaths, and daily case count. The data is collected from the 1st of March to the 30th of April 2020. The confirmed number of cases as of April 30th were 35043, with 1147 total deaths and 8889 recovered patients. The model was created in Python 3.8.5. We will look at various machine learning prediction algorithms and compare them. In conclusion, supervised learning algorithms proved to be better than unsupervised learning algorithms. These prediction models can help us to brace for another COVID-19 wave and to ensure the availability of the required resources.
{"title":"Global Prediction of COVID-19 Cases and Deaths using Machine Learning","authors":"Sumit Bhardwaj, Harshit Bhardwaj, Jyoti Bhardwaj, Punit Gupta","doi":"10.1109/ICIIP53038.2021.9702560","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702560","url":null,"abstract":"Coronavirus Disease or COVID-19 pandemic has taken over the world by storm. It has horrifying effect on the health of the people. Continuously rising number of COVID-19 cases has and still creating huge stress on the governing bodies of all countries, and they are finding it hard to find solution for the situation. This project's goal is to explore machine learning and develop a COVID-19 model that can predict number of cases with high accuracy. The proposed study employs SVR and PR models to forecast the number of recovered cases, confirmed cases, deaths, and daily case count. The data is collected from the 1st of March to the 30th of April 2020. The confirmed number of cases as of April 30th were 35043, with 1147 total deaths and 8889 recovered patients. The model was created in Python 3.8.5. We will look at various machine learning prediction algorithms and compare them. In conclusion, supervised learning algorithms proved to be better than unsupervised learning algorithms. These prediction models can help us to brace for another COVID-19 wave and to ensure the availability of the required resources.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123559532","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 : 2021-11-26DOI: 10.1109/ICIIP53038.2021.9702555
D. Shanthi
The importance on computer software has increased in recent decades. As computing systems become more numerous, complex, and deeply embedded in modern society, the need for systematic software development approaches tends to grow. System development problems that cause delays, increased costs, and/or failure to meet user needs are known as software crises. A systematic way to improve the quality of software by improving the development process can be incorporated into this challenging task. To predict software reliability, we proposed the Evolutionary Machine Learning algorithms ACOT, PSO, and a hybrid of ACOT and PSO. A comparison of our results with existing machine learning approaches such as neural networks and decision trees was also proposed. We used Root Mean Square Error and Normalized Root Mean Square Error to collect three software failure datasets to reinforce the demand besides software reliability.
{"title":"Ensemble Approach of ACOT and PSO for Predicting Software Reliability","authors":"D. Shanthi","doi":"10.1109/ICIIP53038.2021.9702555","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702555","url":null,"abstract":"The importance on computer software has increased in recent decades. As computing systems become more numerous, complex, and deeply embedded in modern society, the need for systematic software development approaches tends to grow. System development problems that cause delays, increased costs, and/or failure to meet user needs are known as software crises. A systematic way to improve the quality of software by improving the development process can be incorporated into this challenging task. To predict software reliability, we proposed the Evolutionary Machine Learning algorithms ACOT, PSO, and a hybrid of ACOT and PSO. A comparison of our results with existing machine learning approaches such as neural networks and decision trees was also proposed. We used Root Mean Square Error and Normalized Root Mean Square Error to collect three software failure datasets to reinforce the demand besides software reliability.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127030654","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 : 2021-11-26DOI: 10.1109/ICIIP53038.2021.9702636
Madhusmita Sarma, A. K. Talukdar, K. K. Sarma
COVID-19 pandemic is spreading continuously causing serious health problems. Wearing face mask is one of the prominent precautions people can easily follow. In this paper, we have built a model for face-mask detection system using deep learning technique that uses Histogram of Oriented Gradients (HOG) based features for face detection and Convolutional Neural Network (CNN) for detecting whether the person is wearing face mask or not. The model has also the capability of detecting whether the wearer is wearing the face mask properly or not. This model has been trained with 3650 images using python script in Google Colab environment applying Keras and TensorFlow. After a number of trials we have found that our model gives best result with 50 epochs. We have found training and validation accuracy 94.59% and 98.51% respectively. The model has been tested with real time inputs. From the experimental results it has been found that the proposed model is capable of detection faces with-mask and without-mask with 97% accuracy.
{"title":"Deep Learning Based Face Mask Detection System for COVID-19 Control","authors":"Madhusmita Sarma, A. K. Talukdar, K. K. Sarma","doi":"10.1109/ICIIP53038.2021.9702636","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702636","url":null,"abstract":"COVID-19 pandemic is spreading continuously causing serious health problems. Wearing face mask is one of the prominent precautions people can easily follow. In this paper, we have built a model for face-mask detection system using deep learning technique that uses Histogram of Oriented Gradients (HOG) based features for face detection and Convolutional Neural Network (CNN) for detecting whether the person is wearing face mask or not. The model has also the capability of detecting whether the wearer is wearing the face mask properly or not. This model has been trained with 3650 images using python script in Google Colab environment applying Keras and TensorFlow. After a number of trials we have found that our model gives best result with 50 epochs. We have found training and validation accuracy 94.59% and 98.51% respectively. The model has been tested with real time inputs. From the experimental results it has been found that the proposed model is capable of detection faces with-mask and without-mask with 97% accuracy.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123036687","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 : 2021-11-26DOI: 10.1109/ICIIP53038.2021.9702551
Subhangi Adhikary, A. K. Talukdar, Kandarpa Kumar Sarma
Indian Sign Language (ISL) is a form of communication used in India by the speech and hearing impaired community. It conveys linguistic information through gestures of the hands, arms, face, and head. However, the gestures used may not always be directly related to the referent term, resulting in a significant communication gap. Hence there is a need for a translator that can translate ISL into text or speech. The proposed system aims to recognize signs of ISL and translate them into texts that can be easily read. The ISL recognition system is based on Google’s MediaPipe as a feature extractor and Random Forest Classifier is used for classification. An accuracy of 97.4% is achieved. The results show that the integration of MediaPipe with ML algorithms may be effectively employed to correctly recognise signs of ISL.
{"title":"A Vision-based System for Recognition of Words used in Indian Sign Language Using MediaPipe","authors":"Subhangi Adhikary, A. K. Talukdar, Kandarpa Kumar Sarma","doi":"10.1109/ICIIP53038.2021.9702551","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702551","url":null,"abstract":"Indian Sign Language (ISL) is a form of communication used in India by the speech and hearing impaired community. It conveys linguistic information through gestures of the hands, arms, face, and head. However, the gestures used may not always be directly related to the referent term, resulting in a significant communication gap. Hence there is a need for a translator that can translate ISL into text or speech. The proposed system aims to recognize signs of ISL and translate them into texts that can be easily read. The ISL recognition system is based on Google’s MediaPipe as a feature extractor and Random Forest Classifier is used for classification. An accuracy of 97.4% is achieved. The results show that the integration of MediaPipe with ML algorithms may be effectively employed to correctly recognise signs of ISL.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128462341","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 : 2021-11-26DOI: 10.1109/ICIIP53038.2021.9702634
ShivaniRana, Shruti Jain, Rakesh Kanji
Recent advances in MEMS technology had given rise to the sensor devices capable of being operated in any type of environment for monitoring and observing some phenomenon. In spite of having the broad perspective to be used in a variety of applications, sensor nodes lacks in their limited energy resources. The hierarchical routing protocols provide a way to preserve individual node energy by reducing the communication between the nodes and the sink directly. In this work, various protocols are studied and analyzed for energy consumption of nodes with concern to the network life. The performance of Low-Energy Adaptive Clustering Hierarchy (LEACH) and multi-chain Power Efficient Gathering for Sensor Information System(PEGASIS) are analyzed and compared to have a look at how much they contribute to the network lifetime extension. After their comparative analysis, some improvement in multi-chain PEGASIS is presented with the concept of sink mobility resulting in 300% more network lifetime than LEACH and 150% more operative rounds than in PEGASIS.
{"title":"Design of Multi Chain Power Efficient Gathering for Sensor Information System Using Sink Mobility","authors":"ShivaniRana, Shruti Jain, Rakesh Kanji","doi":"10.1109/ICIIP53038.2021.9702634","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702634","url":null,"abstract":"Recent advances in MEMS technology had given rise to the sensor devices capable of being operated in any type of environment for monitoring and observing some phenomenon. In spite of having the broad perspective to be used in a variety of applications, sensor nodes lacks in their limited energy resources. The hierarchical routing protocols provide a way to preserve individual node energy by reducing the communication between the nodes and the sink directly. In this work, various protocols are studied and analyzed for energy consumption of nodes with concern to the network life. The performance of Low-Energy Adaptive Clustering Hierarchy (LEACH) and multi-chain Power Efficient Gathering for Sensor Information System(PEGASIS) are analyzed and compared to have a look at how much they contribute to the network lifetime extension. After their comparative analysis, some improvement in multi-chain PEGASIS is presented with the concept of sink mobility resulting in 300% more network lifetime than LEACH and 150% more operative rounds than in PEGASIS.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130513520","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}
Covid-19 has been a great disaster for the entire world. It is caused by the novel coronavirus, which is highly contagious. Detection of Covid-19 can be done either through saliva or through a CT scan. Given the scale at which this Covid-19 can spread, an automated detection is required which can be adopted at large scale. In this work, we focus on the detection of Covid-19 through CT scan images. Our work evaluates well-known CNN architecture-based models in different experimental settings: fine-tuning, removal of pre-trained layers, and data augmentation. For evaluation, we use the dataset of images comprising Covid-19 CT scans. We analyze the performance of VGG-16, InceptionNet, and ResNet. After rigorous experiments, the InceptionNet model performs the best with 0.99 AUC outperforming the prior work (which claimed 0.98 AUC), with the training accuracy and testing accuracy of 99.94% and 96.43%, respectively. Furthermore, we also perform explainability experiments on both Covid and Non-Covid CT-Scan images.
{"title":"Covid-19 Detection from CT-scan Images: Empirical Evaluation and Explainability","authors":"Prachi Servanshi, Simran Kaur Bindra, Mansi Gera, Rishabh Kaushal","doi":"10.1109/ICIIP53038.2021.9702596","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702596","url":null,"abstract":"Covid-19 has been a great disaster for the entire world. It is caused by the novel coronavirus, which is highly contagious. Detection of Covid-19 can be done either through saliva or through a CT scan. Given the scale at which this Covid-19 can spread, an automated detection is required which can be adopted at large scale. In this work, we focus on the detection of Covid-19 through CT scan images. Our work evaluates well-known CNN architecture-based models in different experimental settings: fine-tuning, removal of pre-trained layers, and data augmentation. For evaluation, we use the dataset of images comprising Covid-19 CT scans. We analyze the performance of VGG-16, InceptionNet, and ResNet. After rigorous experiments, the InceptionNet model performs the best with 0.99 AUC outperforming the prior work (which claimed 0.98 AUC), with the training accuracy and testing accuracy of 99.94% and 96.43%, respectively. Furthermore, we also perform explainability experiments on both Covid and Non-Covid CT-Scan images.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115900137","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 : 2021-11-26DOI: 10.1109/ICIIP53038.2021.9702567
Prakriti Dwivedi, A. Khan, Amit Gawade, Subodh Deolekar
Skin conditions vary widely in terms of its symptoms and criticality which can be persistent or temporary, pain-free or painful, mild or severe and at times situational or genetic in nature. This varying complexity and uncertainty not only make it difficult for a patient to sense it, but also becomes a daunting task for doctors to deal with it. Consequently, if remained ignored or untreated, it can even be fatal at times. Therefore, the need for a rapid detection system for skin disorder is a must to reduce its criticality level. This paper is an attempt to develop a system using deep learning technology to detect skin diseases accurately. Using the Fast R-CNN architecture of deep learning, appropriate annotation technique and proper selection of parameters, the results were obtained. We are able to detect the specified skin disease from the given classes with an overall accuracy of 90% and the loss of 0.3 which shows the effectiveness of the model.
{"title":"A deep learning based approach for automated skin disease detection using Fast R-CNN","authors":"Prakriti Dwivedi, A. Khan, Amit Gawade, Subodh Deolekar","doi":"10.1109/ICIIP53038.2021.9702567","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702567","url":null,"abstract":"Skin conditions vary widely in terms of its symptoms and criticality which can be persistent or temporary, pain-free or painful, mild or severe and at times situational or genetic in nature. This varying complexity and uncertainty not only make it difficult for a patient to sense it, but also becomes a daunting task for doctors to deal with it. Consequently, if remained ignored or untreated, it can even be fatal at times. Therefore, the need for a rapid detection system for skin disorder is a must to reduce its criticality level. This paper is an attempt to develop a system using deep learning technology to detect skin diseases accurately. Using the Fast R-CNN architecture of deep learning, appropriate annotation technique and proper selection of parameters, the results were obtained. We are able to detect the specified skin disease from the given classes with an overall accuracy of 90% and the loss of 0.3 which shows the effectiveness of the model.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128882757","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 : 2021-11-26DOI: 10.1109/ICIIP53038.2021.9702650
Vijay Kumar Gowda B N, Sabitha Gauni, V. Maik
An image in the underwater ocean depth of 10 meters by capturing a low-resolution camera. An image is characterized by low contrast and blurriness. Despite water medium has considering the propagation of light, it degrades the underwater image due to refraction, scatters, and color absorption. This underwater image needs to improve its color contrast and quality image by using Simple Histogram Equalization for color correction and DSNMF (Deep Sparse Non-Negative Matrix Factorization) for color contrast improvement. Finally, the proposed method results describe based on the observations of the qualitative and quantitative parameters of PSNR (Peak Signal to Noise Ratio), RMSE (Root Mean Square Error), and SSIM (System Similarity Index Matrix). The output of This proposed method is shown a qualitative state-of-the-art underwater enhanced image with better brightness and contrast and developed technique simulation produces a quantitative output of enhancing the image of PSNR, RMSE, and SSIM are 25.256, 13.235, and 8.232, with these parameters increasing better quality visual perception.
{"title":"Underwater image enhancement by using color correction and contrast techniques","authors":"Vijay Kumar Gowda B N, Sabitha Gauni, V. Maik","doi":"10.1109/ICIIP53038.2021.9702650","DOIUrl":"https://doi.org/10.1109/ICIIP53038.2021.9702650","url":null,"abstract":"An image in the underwater ocean depth of 10 meters by capturing a low-resolution camera. An image is characterized by low contrast and blurriness. Despite water medium has considering the propagation of light, it degrades the underwater image due to refraction, scatters, and color absorption. This underwater image needs to improve its color contrast and quality image by using Simple Histogram Equalization for color correction and DSNMF (Deep Sparse Non-Negative Matrix Factorization) for color contrast improvement. Finally, the proposed method results describe based on the observations of the qualitative and quantitative parameters of PSNR (Peak Signal to Noise Ratio), RMSE (Root Mean Square Error), and SSIM (System Similarity Index Matrix). The output of This proposed method is shown a qualitative state-of-the-art underwater enhanced image with better brightness and contrast and developed technique simulation produces a quantitative output of enhancing the image of PSNR, RMSE, and SSIM are 25.256, 13.235, and 8.232, with these parameters increasing better quality visual perception.","PeriodicalId":431272,"journal":{"name":"2021 Sixth International Conference on Image Information Processing (ICIIP)","volume":"321 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115839064","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：