Pub Date : 2021-12-10DOI: 10.1109/SMART52563.2021.9676230
L. Poongothai, K. Sharmila
Retinal blood vessels are an indispensable entity of the human eye. The requirement to effectively protect the eye forms a censorious part of well-being. Various empirical articulations and simulative studies have evinced the effective processing of the retinal ailments in the form of diabetic retinopathy, macular degeneration, central retinal vein occlusion, central retinal artery occlusion, retinal detachment and branch retinal vein occlusion have been constant surge. However, this paper deals with the agnizing of retinal detachment by utilizing the snake contouring algorithm commingled with the Neumann boundary constraint and Gaussian kernel dissemination fitting. The existing work relevant to retinal detachment have held close significance to the various contouring methods. Nevertheless, in this proposed study, the novel implementation of identification involves the contouring combined with quadrant segmentation. The local area-based, active contours through the iterative, interleaved energy evolution and feature extraction through eigenfeature unsheathing, proffers qualitative results to evince that inhomogeneities and diverse pixel-intensity may not be an obstacle to procure impeccable results for effective feature extraction and segmentation of detachment from the retinal fundus images. The simulation of the study is implemented in MATLAB, and the results are obtained fallaciously.
{"title":"Identifying Retinal Detachment through Snake Contouring-Neumann Boundary Algorithm and Quadrant-Segmentation","authors":"L. Poongothai, K. Sharmila","doi":"10.1109/SMART52563.2021.9676230","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9676230","url":null,"abstract":"Retinal blood vessels are an indispensable entity of the human eye. The requirement to effectively protect the eye forms a censorious part of well-being. Various empirical articulations and simulative studies have evinced the effective processing of the retinal ailments in the form of diabetic retinopathy, macular degeneration, central retinal vein occlusion, central retinal artery occlusion, retinal detachment and branch retinal vein occlusion have been constant surge. However, this paper deals with the agnizing of retinal detachment by utilizing the snake contouring algorithm commingled with the Neumann boundary constraint and Gaussian kernel dissemination fitting. The existing work relevant to retinal detachment have held close significance to the various contouring methods. Nevertheless, in this proposed study, the novel implementation of identification involves the contouring combined with quadrant segmentation. The local area-based, active contours through the iterative, interleaved energy evolution and feature extraction through eigenfeature unsheathing, proffers qualitative results to evince that inhomogeneities and diverse pixel-intensity may not be an obstacle to procure impeccable results for effective feature extraction and segmentation of detachment from the retinal fundus images. The simulation of the study is implemented in MATLAB, and the results are obtained fallaciously.","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131504373","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 : 2021-12-10DOI: 10.1109/SMART52563.2021.9676325
Rahul Nijhawan, M. Ashish, Arpit Ahuja, Naveen Yadav
This study was conducted for the detection of the types of grain which germinate in India. Every class of grain has different and unique kind of proteins, carbohydrates and nutrients. The utilization of grains highly depends on their type. The main motive of the pabulum industry today is to fulfil the consumers’ demand. We propose a hybrid deep learning framework composed of the ensemble of CNNs for feature extraction and an integrated Random Forest model for classification. A distinct type of 13 grain types have been classified—Chickpeas, Lentils, Peanuts, Soybeans, Fava Beans, Finger Millets, Fonio, Japanese Millet, Kodo Millet, Barley, Oats, Rice and Wheat. Our proposed framework outperformed (classification accuracy 96.12%) the state of art algorithms for detection of grain types. Index Terms—— Grain, SVM (Support Vector Machine), Deep Learning, CNN (Convolution neural network), RF (Random Forest), KNN (K-Nearest Neighbor).
{"title":"A Hybrid Deep Learning Framework Approach for the Detection of Different Varieties of Grain Types","authors":"Rahul Nijhawan, M. Ashish, Arpit Ahuja, Naveen Yadav","doi":"10.1109/SMART52563.2021.9676325","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9676325","url":null,"abstract":"This study was conducted for the detection of the types of grain which germinate in India. Every class of grain has different and unique kind of proteins, carbohydrates and nutrients. The utilization of grains highly depends on their type. The main motive of the pabulum industry today is to fulfil the consumers’ demand. We propose a hybrid deep learning framework composed of the ensemble of CNNs for feature extraction and an integrated Random Forest model for classification. A distinct type of 13 grain types have been classified—Chickpeas, Lentils, Peanuts, Soybeans, Fava Beans, Finger Millets, Fonio, Japanese Millet, Kodo Millet, Barley, Oats, Rice and Wheat. Our proposed framework outperformed (classification accuracy 96.12%) the state of art algorithms for detection of grain types. Index Terms—— Grain, SVM (Support Vector Machine), Deep Learning, CNN (Convolution neural network), RF (Random Forest), KNN (K-Nearest Neighbor).","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131897019","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 : 2021-12-10DOI: 10.1109/SMART52563.2021.9676251
G. Pandey, Ravindara Bhatt
In the last few years a drastic shift in terms of health care has occurred. Today majority of human kind is at high risk of health loss due to several reasons, for example Work Stress, lack of exercise, sleeping disorders, eating habits are major reasons. The most important point here to notice is that the diseases which are recursive in nature are most dangerous and expensive in terms of money, to the society and they are called as Chronic Diseases.In this research we have shared a detailed statistics of world health issues and the future death causing rates due to various Chronic Diseases. In our research we have created an ANN (Artificial Neural Network) model to predict whether a person is suffering from a Chronic Disease or not. We have shared a complete roadmap for the model and have covered all the crucial parameters in detail for providing a better understanding to our readers.
{"title":"The Impact of Chronic Kidney Disease (CKD) Around the Globe: A Novel ML Solution","authors":"G. Pandey, Ravindara Bhatt","doi":"10.1109/SMART52563.2021.9676251","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9676251","url":null,"abstract":"In the last few years a drastic shift in terms of health care has occurred. Today majority of human kind is at high risk of health loss due to several reasons, for example Work Stress, lack of exercise, sleeping disorders, eating habits are major reasons. The most important point here to notice is that the diseases which are recursive in nature are most dangerous and expensive in terms of money, to the society and they are called as Chronic Diseases.In this research we have shared a detailed statistics of world health issues and the future death causing rates due to various Chronic Diseases. In our research we have created an ANN (Artificial Neural Network) model to predict whether a person is suffering from a Chronic Disease or not. We have shared a complete roadmap for the model and have covered all the crucial parameters in detail for providing a better understanding to our readers.","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"44 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132077025","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 : 2021-12-10DOI: 10.1109/SMART52563.2021.9676293
K. Chitra, C. Shanthi
Early Drowsiness is the main cause for the majority fatigue accidents directly connected to vehicle crashes. This may lead to severe vehicle accidents for the on-road drivers. A major vehicle accident happens based on a microsleep collision by sensing and alerting system. Road accidents occur due to multiple reasons and the fatigue of the driver is amongst the predominant factors. The analysis identified a wide range of models capable of predicting road accident effective interventions A device for detecting the severity of the crash prior to an accident and the parameters obtained by sensors from the pre-crash vehicle. It must be anticipated and averted based on the extent of the upcoming collision. Machine Learning could identify the reality of significance of a driver’s state of mind and predict the collision. The alert would show the severity of the drowsiness and to know the state of the driver by automatic notifications. These lives could have been spared if clinical offices are given at the opportune time.
{"title":"A Comparative Study of Classification Models for Predicting Monotonous Driver Drowsiness","authors":"K. Chitra, C. Shanthi","doi":"10.1109/SMART52563.2021.9676293","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9676293","url":null,"abstract":"Early Drowsiness is the main cause for the majority fatigue accidents directly connected to vehicle crashes. This may lead to severe vehicle accidents for the on-road drivers. A major vehicle accident happens based on a microsleep collision by sensing and alerting system. Road accidents occur due to multiple reasons and the fatigue of the driver is amongst the predominant factors. The analysis identified a wide range of models capable of predicting road accident effective interventions A device for detecting the severity of the crash prior to an accident and the parameters obtained by sensors from the pre-crash vehicle. It must be anticipated and averted based on the extent of the upcoming collision. Machine Learning could identify the reality of significance of a driver’s state of mind and predict the collision. The alert would show the severity of the drowsiness and to know the state of the driver by automatic notifications. These lives could have been spared if clinical offices are given at the opportune time.","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130895714","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 : 2021-12-10DOI: 10.1109/SMART52563.2021.9676282
S. Kaushik, S. Pandey, R. Singhal
The paper describes the effect of heavy ion irradiation on resistance switching behavior in zinc oxide deposited by RF sputtering on ITO-coated substrates. When annealed ZnO/ITO structures in oxygen atmosphere are bombarded with Ag+8 ions, they exhibit hysteresis in current-voltage curves caused by an increase in the resistance ratio, whereas the pristine samples (annealed in oxygen) exhibit linear characteristics. As compared to the changes in (OV-) oxygen vacancies at the interface, the changes in defect density caused by heavy ion irradiation give rise to metallic filaments, which are a main cause of resistance switching in ZnO.
{"title":"Role of Ion Irradiation in Resistive Memory Devices","authors":"S. Kaushik, S. Pandey, R. Singhal","doi":"10.1109/SMART52563.2021.9676282","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9676282","url":null,"abstract":"The paper describes the effect of heavy ion irradiation on resistance switching behavior in zinc oxide deposited by RF sputtering on ITO-coated substrates. When annealed ZnO/ITO structures in oxygen atmosphere are bombarded with Ag+8 ions, they exhibit hysteresis in current-voltage curves caused by an increase in the resistance ratio, whereas the pristine samples (annealed in oxygen) exhibit linear characteristics. As compared to the changes in (OV-) oxygen vacancies at the interface, the changes in defect density caused by heavy ion irradiation give rise to metallic filaments, which are a main cause of resistance switching in ZnO.","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131060058","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 : 2021-12-10DOI: 10.1109/SMART52563.2021.9676299
N. Agrawal, Ajeet K. Sharma
Most of the global population depends on agriculture and consider agricultural activities as their primary source of occupation to earn their income. If any problem occurs in this primary sector, then it is going to affect the livelihood and lives of the population seriously. Henceforth, it is important to keep up balance in the agricultural area by preventing it from something similar like the adverse effect of plant diseases. The area of artificial intelligence has taken an interesting turn in present times, with the growth of the Neural Networks based Intelligence and Machine Learning. These organically roused computational models can far outshines the presentation of past types of human-made consciousness in like manner artificial intelligence errands. One of the most amazing forms of Artificial Neural Network engineering is CNN. CNN is basically utilized to tackle troublesome picture-driven pattern recognition tasks and with their exact yet straightforward construction, provide a untangle method for starting with ANNs.A new strategy for identification of diseases in plants using CNN is proposed in this paper. The dataset utilized contains around 70,000 images including training and testing dataset. This paper gives a short prologue to CNNs, discussing lately expressed documents and newly framed strategies in evolving these brilliantly tremendous picture recognition models.
{"title":"Detection of Diseases in Plants using Convolutional Neural Networks","authors":"N. Agrawal, Ajeet K. Sharma","doi":"10.1109/SMART52563.2021.9676299","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9676299","url":null,"abstract":"Most of the global population depends on agriculture and consider agricultural activities as their primary source of occupation to earn their income. If any problem occurs in this primary sector, then it is going to affect the livelihood and lives of the population seriously. Henceforth, it is important to keep up balance in the agricultural area by preventing it from something similar like the adverse effect of plant diseases. The area of artificial intelligence has taken an interesting turn in present times, with the growth of the Neural Networks based Intelligence and Machine Learning. These organically roused computational models can far outshines the presentation of past types of human-made consciousness in like manner artificial intelligence errands. One of the most amazing forms of Artificial Neural Network engineering is CNN. CNN is basically utilized to tackle troublesome picture-driven pattern recognition tasks and with their exact yet straightforward construction, provide a untangle method for starting with ANNs.A new strategy for identification of diseases in plants using CNN is proposed in this paper. The dataset utilized contains around 70,000 images including training and testing dataset. This paper gives a short prologue to CNNs, discussing lately expressed documents and newly framed strategies in evolving these brilliantly tremendous picture recognition models.","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126904395","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 : 2021-12-10DOI: 10.1109/SMART52563.2021.9676245
Sandeep Kumar, Arpit Jain, S. Rani, D. Ghai, Swathi Achampeta, P. Raja
Day by day need for a continuous assessment on effectiveness and its accuracy of the recovery algorithm increased. Several sketch-based recovery algorithms exist in the world, but they are not optimal. In the existing work, file structures are applied to enormous databases and data warehouses to acknowledge the recovery process. The process can be sensible and may get affected by quantization blunders. However, the ambiguousness of client models exhibits inappropriate information when using customary picture recovery strategies. So the proposed method, the Sketch-based picture recovery (SBIR) approach, works with recoding and testing. Our methodology utilizes the semantics in inquiry outlines and the top positioned pictures of the essential outcomes. The proposed work applied criticism to find progressively significant information from the sketch-based image. The efficiency of the proposed method is evaluated on QMUL-Shoe dataset and Saavedra dataset. Results show that proposed algorithm improves the accuracy of the sketch-based recovery algorithm.
{"title":"Enhanced SBIR based Re-Ranking and Relevance Feedback","authors":"Sandeep Kumar, Arpit Jain, S. Rani, D. Ghai, Swathi Achampeta, P. Raja","doi":"10.1109/SMART52563.2021.9676245","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9676245","url":null,"abstract":"Day by day need for a continuous assessment on effectiveness and its accuracy of the recovery algorithm increased. Several sketch-based recovery algorithms exist in the world, but they are not optimal. In the existing work, file structures are applied to enormous databases and data warehouses to acknowledge the recovery process. The process can be sensible and may get affected by quantization blunders. However, the ambiguousness of client models exhibits inappropriate information when using customary picture recovery strategies. So the proposed method, the Sketch-based picture recovery (SBIR) approach, works with recoding and testing. Our methodology utilizes the semantics in inquiry outlines and the top positioned pictures of the essential outcomes. The proposed work applied criticism to find progressively significant information from the sketch-based image. The efficiency of the proposed method is evaluated on QMUL-Shoe dataset and Saavedra dataset. Results show that proposed algorithm improves the accuracy of the sketch-based recovery algorithm.","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127018309","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 : 2021-12-10DOI: 10.1109/SMART52563.2021.9676311
Sukrati Jain, Ashendra K. Saxena
In today’s era, cloud computing is the most interesting technology in the field of computer science. While there are numerous concerns in this field like power management, security & the most complex concern is balancing the load. Numerous algorithms are being developed for load balancing in cloud computing. Load Balancing is mainly the process for the workload distribution across multiple servers. Attaining a high user gratification and resource utilization has ever been a remarkable topic for the researchers. In this research paper, we suggested a new approach which describes how to balance the workload using ant colony optimization.
{"title":"An Approach to Balance the Load in Cloud Environment","authors":"Sukrati Jain, Ashendra K. Saxena","doi":"10.1109/SMART52563.2021.9676311","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9676311","url":null,"abstract":"In today’s era, cloud computing is the most interesting technology in the field of computer science. While there are numerous concerns in this field like power management, security & the most complex concern is balancing the load. Numerous algorithms are being developed for load balancing in cloud computing. Load Balancing is mainly the process for the workload distribution across multiple servers. Attaining a high user gratification and resource utilization has ever been a remarkable topic for the researchers. In this research paper, we suggested a new approach which describes how to balance the workload using ant colony optimization.","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125359686","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 : 2021-12-10DOI: 10.1109/SMART52563.2021.9676265
Anu Sharma, M. K. Sharma, R. K. Dwivedi
In this paper we used classification algorithms on social networking. We are proposing, a new classification algorithm called the improved Decision Tree (IDT). Our model provides better classification accuracy than the existing systems for classifying the social network data. Here we examined the performance of some familiar classification algorithms regarding their accuracy with our proposed algorithm. We used Naïve Bayes ,SVM, , KNN, decision tree in our research and performed analyses on social media dataset. Matlab is used for performing experiments. The result shows that the proposed algorithm achieves the best results with an accuracy of 84.66%.
{"title":"Improved Decision Tree Classification (IDT) Algorithm for Social Media Data","authors":"Anu Sharma, M. K. Sharma, R. K. Dwivedi","doi":"10.1109/SMART52563.2021.9676265","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9676265","url":null,"abstract":"In this paper we used classification algorithms on social networking. We are proposing, a new classification algorithm called the improved Decision Tree (IDT). Our model provides better classification accuracy than the existing systems for classifying the social network data. Here we examined the performance of some familiar classification algorithms regarding their accuracy with our proposed algorithm. We used Naïve Bayes ,SVM, , KNN, decision tree in our research and performed analyses on social media dataset. Matlab is used for performing experiments. The result shows that the proposed algorithm achieves the best results with an accuracy of 84.66%.","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"26 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113984379","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 : 2021-12-10DOI: 10.1109/SMART52563.2021.9675309
Resham Raj Shivwanshi, Neelamshobha Nirala
Advanced technological tools in medical image analysis for disease detection and diagnosis are progressively coming into the utility of doctors and academicians due to various methodological evolution. Since the last three decades, various studies have been performed to achieve the state of the art predictive ability through early warning disease detection systems. After going through existing research work, it has been found that there is a lack of credibility in CT (computed tomography) image disease detection algorithms, which can be overcome by applying certain image processing and statistical analysis techniques. This article is made to describe a disparate approach in order to attain eminence in terms of lung disease diagnosis and detection. There are a huge amount of databases available online, but most of them encounter the issues of image noise and quality deterioration that further becomes the cause of irregularity and erroneous outcomes. The notion of this paper is to delineate an approach to pre-process input images and measure the quality of the given technique in order to choose better image operations and improve their visual information before analyzing them through a meticulous algorithm. An amalgamation of appropriate filters and image enhancement operations are also utilized to make clear insights of abnormality present inside of lung parenchyma. Furthermore, This study shows that the application of a high pass filter in the spatial domain improves the input image quality that is clearly identified by performing statistical analysis of output parameters. It is also observed that the otsu filtered image is more suitable to prepare the image for an efficient segmentation procedure. At last, it has been discussed that the overall approach in the form of pre-processing and its parameter estimation would not only help to assure quality enhancement of input image but also assist to run disease detection precisely in order to obtain reliable outcomes.
{"title":"Parametric Analysis of CT-image-Preprocessing for Improved Performance of Post-Processing Operation","authors":"Resham Raj Shivwanshi, Neelamshobha Nirala","doi":"10.1109/SMART52563.2021.9675309","DOIUrl":"https://doi.org/10.1109/SMART52563.2021.9675309","url":null,"abstract":"Advanced technological tools in medical image analysis for disease detection and diagnosis are progressively coming into the utility of doctors and academicians due to various methodological evolution. Since the last three decades, various studies have been performed to achieve the state of the art predictive ability through early warning disease detection systems. After going through existing research work, it has been found that there is a lack of credibility in CT (computed tomography) image disease detection algorithms, which can be overcome by applying certain image processing and statistical analysis techniques. This article is made to describe a disparate approach in order to attain eminence in terms of lung disease diagnosis and detection. There are a huge amount of databases available online, but most of them encounter the issues of image noise and quality deterioration that further becomes the cause of irregularity and erroneous outcomes. The notion of this paper is to delineate an approach to pre-process input images and measure the quality of the given technique in order to choose better image operations and improve their visual information before analyzing them through a meticulous algorithm. An amalgamation of appropriate filters and image enhancement operations are also utilized to make clear insights of abnormality present inside of lung parenchyma. Furthermore, This study shows that the application of a high pass filter in the spatial domain improves the input image quality that is clearly identified by performing statistical analysis of output parameters. It is also observed that the otsu filtered image is more suitable to prepare the image for an efficient segmentation procedure. At last, it has been discussed that the overall approach in the form of pre-processing and its parameter estimation would not only help to assure quality enhancement of input image but also assist to run disease detection precisely in order to obtain reliable outcomes.","PeriodicalId":356096,"journal":{"name":"2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123987534","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：