Pub Date : 2021-03-17DOI: 10.1109/INDIACom51348.2021.00109
Ati Jain, Hare Ram Sah, A. Kothari
Student's learning and education is the key for their success. Teachers always judge students attentiveness in class by their facial expressions which shows their interest in the class. But when we look at present, due to COVID-19, students are learning totally on online platform. During these classes, teachers can see students only through their video cameras and it is difficult to know level of understanding of students, therefore they can be judged by their various emotions such as happy, sad, disinterested, frustration, neutral, confusion, anger, disgust, surprise and learning. It becomes compulsory for educators to identify the state of mind of students during online class by their emotion recognition. This paper presents a review for different facial expressions, body parts and gestures through which identification can be done. With the help of Computer vision and deep learning techniques this is identified by tool in which student's image is captured by video camera and further applying feature extraction and classification techniques. This results in benefitting to both students and faculty for easy execution of online classes. Implementation results shows that emotions recognized through image classification can make better learning outcomes for students.
{"title":"Study for Emotion Recognition of Different Age Groups Students during Online Class","authors":"Ati Jain, Hare Ram Sah, A. Kothari","doi":"10.1109/INDIACom51348.2021.00109","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00109","url":null,"abstract":"Student's learning and education is the key for their success. Teachers always judge students attentiveness in class by their facial expressions which shows their interest in the class. But when we look at present, due to COVID-19, students are learning totally on online platform. During these classes, teachers can see students only through their video cameras and it is difficult to know level of understanding of students, therefore they can be judged by their various emotions such as happy, sad, disinterested, frustration, neutral, confusion, anger, disgust, surprise and learning. It becomes compulsory for educators to identify the state of mind of students during online class by their emotion recognition. This paper presents a review for different facial expressions, body parts and gestures through which identification can be done. With the help of Computer vision and deep learning techniques this is identified by tool in which student's image is captured by video camera and further applying feature extraction and classification techniques. This results in benefitting to both students and faculty for easy execution of online classes. Implementation results shows that emotions recognized through image classification can make better learning outcomes for students.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"142 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":"116611115","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/INDIACom51348.2021.00113
Mansi Patel, S. Prabhu, A. Agrawal
Preventing the cyberattacks has been a concern for any organization. In this research, the authors propose a novel method to detect cyberattacks by monitoring and analyzing the network traffic. It was observed that the various log files that are created in the server does not contain all the relevant traces to detect a cyberattack. Hence, the HTTP traffic to the web server was analyzed to detect any potential cyberattacks. To validate the research, a web server was simulated using the Opensource Damn Vulnerable Web Application (DVWA) and the cyberattacks were simulated as per the OWASP standards. A python program was scripted that captured the network traffic to the DVWA server. This traffic was analyzed in real-time by reading the various HTTP parameters viz., URLs, Get / Post methods and the dependencies. The results were found to be encouraging as all the simulated attacks in real-time could be successfully detected. This work can be used as a template by various organizations to prevent any insider threat by monitoring the internal HTTP traffic.
{"title":"Network Traffic Analysis for Real-Time Detection of Cyber Attacks","authors":"Mansi Patel, S. Prabhu, A. Agrawal","doi":"10.1109/INDIACom51348.2021.00113","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00113","url":null,"abstract":"Preventing the cyberattacks has been a concern for any organization. In this research, the authors propose a novel method to detect cyberattacks by monitoring and analyzing the network traffic. It was observed that the various log files that are created in the server does not contain all the relevant traces to detect a cyberattack. Hence, the HTTP traffic to the web server was analyzed to detect any potential cyberattacks. To validate the research, a web server was simulated using the Opensource Damn Vulnerable Web Application (DVWA) and the cyberattacks were simulated as per the OWASP standards. A python program was scripted that captured the network traffic to the DVWA server. This traffic was analyzed in real-time by reading the various HTTP parameters viz., URLs, Get / Post methods and the dependencies. The results were found to be encouraging as all the simulated attacks in real-time could be successfully detected. This work can be used as a template by various organizations to prevent any insider threat by monitoring the internal HTTP traffic.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"216 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":"130346250","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/INDIACom51348.2021.00065
Adnan Ahmed Abi Sen, N. Bahbouh, Mohammed Ahmed F Alrowaili, Omer Nasraldeen Awad Yassin, Abdulmajeed Yahya Almuashi, A. M. Fallata
The world has changed dramatically after the emergence of the concept of the Internet of things (IoT), which now includes billions of things, including technologies and applications. All that surrounds us has become a smart thing with an identifier with the ability to collect, process, or share data, in addition to the ability to access and control it from anywhere at any time. Smart homes are one of the most important applications of the IoT, which has enabled users to monitor and control their homes remotely. Besides, this has resulted in saving energy, which would otherwise be wasted. In addition, Smart Home provides automated services that do not require user intervention, which is known as the machine-to-machine relationship. This research presents an innovative method to employ old personal computers as central computing units with a simple control circuit which can be designed locally, in addition to a small application for controlling in some devices based on an internet connection and web application. The proposed system is capable of transforming ordinary homes into smart homes without significant costs. The proposed method will enable users to remotely control their home devices (to turn on and off), and track the status of these devices, in addition to some smart services. To demonstrate the efficiency of the proposed system, we implemented the main functions with the hardware circuit. The results are very encouraging in terms of reliability, ease of use, and to significantly lower the costs compared to the existing commercial systems.
{"title":"A Novel Cost-efficient Framework for Smart Home Creation","authors":"Adnan Ahmed Abi Sen, N. Bahbouh, Mohammed Ahmed F Alrowaili, Omer Nasraldeen Awad Yassin, Abdulmajeed Yahya Almuashi, A. M. Fallata","doi":"10.1109/INDIACom51348.2021.00065","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00065","url":null,"abstract":"The world has changed dramatically after the emergence of the concept of the Internet of things (IoT), which now includes billions of things, including technologies and applications. All that surrounds us has become a smart thing with an identifier with the ability to collect, process, or share data, in addition to the ability to access and control it from anywhere at any time. Smart homes are one of the most important applications of the IoT, which has enabled users to monitor and control their homes remotely. Besides, this has resulted in saving energy, which would otherwise be wasted. In addition, Smart Home provides automated services that do not require user intervention, which is known as the machine-to-machine relationship. This research presents an innovative method to employ old personal computers as central computing units with a simple control circuit which can be designed locally, in addition to a small application for controlling in some devices based on an internet connection and web application. The proposed system is capable of transforming ordinary homes into smart homes without significant costs. The proposed method will enable users to remotely control their home devices (to turn on and off), and track the status of these devices, in addition to some smart services. To demonstrate the efficiency of the proposed system, we implemented the main functions with the hardware circuit. The results are very encouraging in terms of reliability, ease of use, and to significantly lower the costs compared to the existing commercial systems.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"14 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":"129552527","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/INDIACom51348.2021.00107
Farooq Ahmad, Mohd. Faisal
This study is intended to analyze the methods used to test resemblance of sentences. For many Natural Language Processing applications such as text grouping, information recovery, brief reaction reviewing, machine learning, passage summary and text categorization, measuring resemblance between sentences is a vital activity. In this paper, we classify the approaches to measuring the resemblance of sentences based on the methods implemented into three groups. The most frequently used methods to finding phrase resemblance are word-to-word based, structure-based, and vector-based. Centered on a particular viewpoint, each approach tests the interaction between short texts. Furthermore, to provide a full view of this problem, datasets that are often used as benchmarks for testing techniques in this field are added. Better outcomes are obtained through methods that incorporate more than one viewpoint. In addition, resemblance of sentences is based on the correspondence of their meanings that tests the semantic resemblance between two concepts, words or sentences needs further research.
{"title":"Comparative Study of Techniques used for Word and Sentence Similarity","authors":"Farooq Ahmad, Mohd. Faisal","doi":"10.1109/INDIACom51348.2021.00107","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00107","url":null,"abstract":"This study is intended to analyze the methods used to test resemblance of sentences. For many Natural Language Processing applications such as text grouping, information recovery, brief reaction reviewing, machine learning, passage summary and text categorization, measuring resemblance between sentences is a vital activity. In this paper, we classify the approaches to measuring the resemblance of sentences based on the methods implemented into three groups. The most frequently used methods to finding phrase resemblance are word-to-word based, structure-based, and vector-based. Centered on a particular viewpoint, each approach tests the interaction between short texts. Furthermore, to provide a full view of this problem, datasets that are often used as benchmarks for testing techniques in this field are added. Better outcomes are obtained through methods that incorporate more than one viewpoint. In addition, resemblance of sentences is based on the correspondence of their meanings that tests the semantic resemblance between two concepts, words or sentences needs further research.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"31 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":"130677530","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/INDIACom51348.2021.00012
Meenu Sharma, R. Parveen
The liver is the most significant internal organ in the human body's abdomen. A person cannot survive without a healthy liver. Liver cancer is a life-threatening illness, difficult to detect by biomedical engineering technicians. Hepatocellular carcinoma (HCC) is the most common type of liver cancer which makes up 75% of cases. Plenty of people with liver tumors have lost their lives because of poor and late detection. Hence it is far essential to discover the tumor at an early stage. So, the principal intention is to detect liver cancer at an earlier stage using the image processing technique. Here the tumors are detected from Magnetic Resonance Imaging images. The image undergoes image pre-processing and is segmented by a hybrid method consisting of the edge and mask method, which is simple and easy to use. Detected tumors are further categorized into the cyst, adenoma, hemangioma, and malignant tumor based on statistical features. The scope of this propounded technique is to highlight and categorized the tumor region present in the Magnetic Resonance Imaging images.
{"title":"A Novel Digital Image Processing based Mechanism for Liver Tumor Diagnosis","authors":"Meenu Sharma, R. Parveen","doi":"10.1109/INDIACom51348.2021.00012","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00012","url":null,"abstract":"The liver is the most significant internal organ in the human body's abdomen. A person cannot survive without a healthy liver. Liver cancer is a life-threatening illness, difficult to detect by biomedical engineering technicians. Hepatocellular carcinoma (HCC) is the most common type of liver cancer which makes up 75% of cases. Plenty of people with liver tumors have lost their lives because of poor and late detection. Hence it is far essential to discover the tumor at an early stage. So, the principal intention is to detect liver cancer at an earlier stage using the image processing technique. Here the tumors are detected from Magnetic Resonance Imaging images. The image undergoes image pre-processing and is segmented by a hybrid method consisting of the edge and mask method, which is simple and easy to use. Detected tumors are further categorized into the cyst, adenoma, hemangioma, and malignant tumor based on statistical features. The scope of this propounded technique is to highlight and categorized the tumor region present in the Magnetic Resonance Imaging images.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"13 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":"133342380","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/INDIACom51348.2021.00162
P. Dodamani, A. Danti
X-ray application in medical fields has given rise to various research challenges related to bone, due to its wide usage in finding out the disease related to human anatomy. It has lot of research challenges to solve using available wide application of medical imaging techniques and inspired by this, a novel X-ray images based survey was conducted to understand the role of Xray images in medical field. Bone mass density identification is the standard procedure to monitor the risk of fracture in bone using DEXA. Lot of research has been carried out to calculate BMD using X-ray images and it provided prominent results. Since Xray is economically affordable and very economical compared to DEXA, we have decided to work on X-ray images. This paper explains us about various current advancements and disadvantages with respect to X-ray image in medical sector and various techniques related to BMD calculation. X-ray images characteristics and its fundamentals in the medical field for identifying bone related diseases are also discussed.
{"title":"Assesment of Bone Mineral Density in X-ray Images using Image Processing","authors":"P. Dodamani, A. Danti","doi":"10.1109/INDIACom51348.2021.00162","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00162","url":null,"abstract":"X-ray application in medical fields has given rise to various research challenges related to bone, due to its wide usage in finding out the disease related to human anatomy. It has lot of research challenges to solve using available wide application of medical imaging techniques and inspired by this, a novel X-ray images based survey was conducted to understand the role of Xray images in medical field. Bone mass density identification is the standard procedure to monitor the risk of fracture in bone using DEXA. Lot of research has been carried out to calculate BMD using X-ray images and it provided prominent results. Since Xray is economically affordable and very economical compared to DEXA, we have decided to work on X-ray images. This paper explains us about various current advancements and disadvantages with respect to X-ray image in medical sector and various techniques related to BMD calculation. X-ray images characteristics and its fundamentals in the medical field for identifying bone related diseases are also discussed.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"480 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":"133632629","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}
The Internet of Things (IoT) is a growing technology in which social surroundings are connected through different sensors networked together. The sensors can communicate data with each other with the help of internet connectivity. This paper focuses on safe kitchens in smart homes using IoT. In terms of safety in the household gas connections, a regulator and LPG stove are provided in which knobs control the flow. Gas leakage may be hazardous, especially in closed areas. In these cases, a safety system with a high leakage detection ability is required. In this paper, an IoT-based safety system is proposed, which may reduce accidents caused by electricity during LPG leakage which will automatically cutoff the ac mains if there is any leakage of LPG is detected by the sensor MQ5. This system provides safety from the short circuit during LPG leakage.
{"title":"Arduino based LPG Leakage Detection and Prevention System","authors":"Brijesh Sharma, P. Vaidya, Nagesh Kumar, Chi-Chung Chen, Ruchika Sharma, Ram Prakash Dwivedi, Gaurav Gupta","doi":"10.1109/INDIACom51348.2021.00029","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00029","url":null,"abstract":"The Internet of Things (IoT) is a growing technology in which social surroundings are connected through different sensors networked together. The sensors can communicate data with each other with the help of internet connectivity. This paper focuses on safe kitchens in smart homes using IoT. In terms of safety in the household gas connections, a regulator and LPG stove are provided in which knobs control the flow. Gas leakage may be hazardous, especially in closed areas. In these cases, a safety system with a high leakage detection ability is required. In this paper, an IoT-based safety system is proposed, which may reduce accidents caused by electricity during LPG leakage which will automatically cutoff the ac mains if there is any leakage of LPG is detected by the sensor MQ5. This system provides safety from the short circuit during LPG leakage.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"69 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":"116269608","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/INDIACom51348.2021.00114
S. Singla, Manjit Singh, Navdeep Kanwal
Secure and robust authentication is the key requirements for today's growing world of information and technology. High data security with ease of use is one of the key requirements for security systems today and biometric technologies provide several advantages over conventional systems which make them highly acceptable by individuals worldwide. A comprehensive study of the various existing biometric modalities has been discussed in this paper with some of the modern challenges and various key features to be kept in mind while choosing any biometric for a certain application. The different parameters used for performance evaluation of a biometric system are also discussed.
{"title":"Biometric System - Challenges and Future Trends","authors":"S. Singla, Manjit Singh, Navdeep Kanwal","doi":"10.1109/INDIACom51348.2021.00114","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00114","url":null,"abstract":"Secure and robust authentication is the key requirements for today's growing world of information and technology. High data security with ease of use is one of the key requirements for security systems today and biometric technologies provide several advantages over conventional systems which make them highly acceptable by individuals worldwide. A comprehensive study of the various existing biometric modalities has been discussed in this paper with some of the modern challenges and various key features to be kept in mind while choosing any biometric for a certain application. The different parameters used for performance evaluation of a biometric system are also discussed.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"42 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":"114612873","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/INDIACom51348.2021.00158
Dhiraj Khurana, Sunita Dhingra
Recommender system is an adaptive technology and tool that is used in business organizations for offering the products and services by observing their interest and popularity of products. In this paper, an improvement over the existing hybrid and knowledge based recommender system is proposed by integrating the clustering method within content based filter and classification method within collaborative filter. The proposed method handled the scalability problem by using the fuzzy clustering method. This reduced dimension based dataset is processed by the probabilistic Bayesian network classifier for predicting the recommendations. The sparsity problem is handled in both stage of this model. The proposed recommender system model is applied on MovieLens dataset. The comparative analysis was done against content-based recommender system (CBRS), Pearson correlation based collaborative recommender system (PCRS), Frequency-weighted Pearson Correlation (FPC), Weighted Pearson Correlation (WPC) and hybrid recommender systems (HRS). The average RMSE rate achieved by CBRS, PCRS, FPC, WPC, HRS and the proposed hybrid recommender system are 0.3851, 0.3515, 0.3527, 0.3539, 0.3340 and 0.1987 respectively. The significant reduction in MAE rate is also identified in this work. The experimentation results identified that the proposed model reduced the error rate and improved the accuracy rate over existing systems.
{"title":"An Improved Hybrid and Knowledge Based Recommender System for Accurate Prediction of Movies","authors":"Dhiraj Khurana, Sunita Dhingra","doi":"10.1109/INDIACom51348.2021.00158","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00158","url":null,"abstract":"Recommender system is an adaptive technology and tool that is used in business organizations for offering the products and services by observing their interest and popularity of products. In this paper, an improvement over the existing hybrid and knowledge based recommender system is proposed by integrating the clustering method within content based filter and classification method within collaborative filter. The proposed method handled the scalability problem by using the fuzzy clustering method. This reduced dimension based dataset is processed by the probabilistic Bayesian network classifier for predicting the recommendations. The sparsity problem is handled in both stage of this model. The proposed recommender system model is applied on MovieLens dataset. The comparative analysis was done against content-based recommender system (CBRS), Pearson correlation based collaborative recommender system (PCRS), Frequency-weighted Pearson Correlation (FPC), Weighted Pearson Correlation (WPC) and hybrid recommender systems (HRS). The average RMSE rate achieved by CBRS, PCRS, FPC, WPC, HRS and the proposed hybrid recommender system are 0.3851, 0.3515, 0.3527, 0.3539, 0.3340 and 0.1987 respectively. The significant reduction in MAE rate is also identified in this work. The experimentation results identified that the proposed model reduced the error rate and improved the accuracy rate over existing systems.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"41 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":"128283476","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/INDIACom51348.2021.00047
Versha Thakur, Harjinder Singh
The implementation of an image contrast enhancement algorithm along with artificial intelligence techniques can have various applications besides modern photography. It basically ameliorates the quality of low contrast images. The main focus of this research is developing a new image contrast enhancement method that combines the concept of artificial intelligence and histogram equalization techniques to provide a contrast distribution for the low contrast images by utilizing the classifier to prevent data loss from images. In this research an ANN based AHE algorithm for enhancement of low contrast images is proposed. The main objectives of this research is to study the existing digital image contrast enhancement techniques to find out the exact problems and to classify the level of contrast in a digital image as low or high, so as to ascertain whether enhancement is required or not. The concept of ANN with AHE is used here to find out the contrast level of the image before processing for contrast enhancement. For validation of the proposed ANN-AHE algorithm, a comparison with the existing techniques are performed on the behalf of performance parameters such as PSNR, MSE, Entropy, QI, QRCM, CQE, SSIM and Computational Time. The simulation of the proposed model is performed in MATLAB 2016a with the help of image processing and artificial neural network toolbox.
{"title":"An Artificial Neural Network based Adaptive Histogram Equalization Algorithm for Enhancement of Low Contrast Images","authors":"Versha Thakur, Harjinder Singh","doi":"10.1109/INDIACom51348.2021.00047","DOIUrl":"https://doi.org/10.1109/INDIACom51348.2021.00047","url":null,"abstract":"The implementation of an image contrast enhancement algorithm along with artificial intelligence techniques can have various applications besides modern photography. It basically ameliorates the quality of low contrast images. The main focus of this research is developing a new image contrast enhancement method that combines the concept of artificial intelligence and histogram equalization techniques to provide a contrast distribution for the low contrast images by utilizing the classifier to prevent data loss from images. In this research an ANN based AHE algorithm for enhancement of low contrast images is proposed. The main objectives of this research is to study the existing digital image contrast enhancement techniques to find out the exact problems and to classify the level of contrast in a digital image as low or high, so as to ascertain whether enhancement is required or not. The concept of ANN with AHE is used here to find out the contrast level of the image before processing for contrast enhancement. For validation of the proposed ANN-AHE algorithm, a comparison with the existing techniques are performed on the behalf of performance parameters such as PSNR, MSE, Entropy, QI, QRCM, CQE, SSIM and Computational Time. The simulation of the proposed model is performed in MATLAB 2016a with the help of image processing and artificial neural network toolbox.","PeriodicalId":415594,"journal":{"name":"2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)","volume":"96 45 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":"129329463","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：