Pub Date : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262388
K. Jha, P. Das, H. Dutta
Background and Objective: Leukemia identification, detection, & classification has erupted an intriguing field in medical research. Several methodologies are convenient in theprevious work to detect five types WBCs (lymphocytes, eosinophils, monocytes, neutrophils, and basophils). Single cell Blood's smear images used for experiment. Propounded method is used for leukemia recognition, uncovering and distribution based on FAB classification. Methodology: This propounded task has developed French-American and British (FAB) classification-based detection module on blood smearimages (BSIs). Methods like pretreatment, segmentation, feature extraction, distribution are used in detection method. The Propounded algorithm-based propounded model is used for segmentation, which is combination of the segmented results of the Linde-Buzo-Gray (LBG) algorithm, Adaptive canny used for edge identification and Hysteresis and watershed algorithm used for thresholding. The shape, texture features, color of segmented image are picked by neural network and classification is performed by Support Vector Machine (SVM) and prediction by Naïve Bayes Classifier (NBC). Result: Dataset-master and Cellavison dataset is being used for the experimentation. The BSIs are considered for the Evaluation based on ROC curve analysis metrics like TPR, TNR and accuracy. Our propounded solution obtains superior classification performance in the given dataset. The suggested classifier enhanced the classification average accuracy to 99.06% and Mean Square Error (MSE) is 0.0407. Conclusion: The enhanced accuracy had achieved by enhancing performance and classification with comparison with some other methods.
{"title":"FAB Classification based Leukemia Identification and prediction using Machine Learning","authors":"K. Jha, P. Das, H. Dutta","doi":"10.1109/ICSCAN49426.2020.9262388","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262388","url":null,"abstract":"Background and Objective: Leukemia identification, detection, & classification has erupted an intriguing field in medical research. Several methodologies are convenient in theprevious work to detect five types WBCs (lymphocytes, eosinophils, monocytes, neutrophils, and basophils). Single cell Blood's smear images used for experiment. Propounded method is used for leukemia recognition, uncovering and distribution based on FAB classification. Methodology: This propounded task has developed French-American and British (FAB) classification-based detection module on blood smearimages (BSIs). Methods like pretreatment, segmentation, feature extraction, distribution are used in detection method. The Propounded algorithm-based propounded model is used for segmentation, which is combination of the segmented results of the Linde-Buzo-Gray (LBG) algorithm, Adaptive canny used for edge identification and Hysteresis and watershed algorithm used for thresholding. The shape, texture features, color of segmented image are picked by neural network and classification is performed by Support Vector Machine (SVM) and prediction by Naïve Bayes Classifier (NBC). Result: Dataset-master and Cellavison dataset is being used for the experimentation. The BSIs are considered for the Evaluation based on ROC curve analysis metrics like TPR, TNR and accuracy. Our propounded solution obtains superior classification performance in the given dataset. The suggested classifier enhanced the classification average accuracy to 99.06% and Mean Square Error (MSE) is 0.0407. Conclusion: The enhanced accuracy had achieved by enhancing performance and classification with comparison with some other methods.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"39 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89806965","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 : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262439
B. Lakshmipriya, N. Pavithra, D. Saraswathi
Deep learning has been witnessing an unprecedented growth in various applications like image classification, image recognition, object recognition and so on. In this work, a novel multifocus fusion schematic is putforth using deep learning strategy for the fusion of more than two colour images. The activations of the convolutional neural network (CNN) are used to extract the prominent deep features of the source and these features are fused by the virtue of weighted averaging technique. Finally, the weighted average outputs of the activations of the source images are considered for the recovering the enhanced fused output the image. The fused image is found to be enhanced such that the entire image is free from motion blur and defocusing. Three popular deep learning architectures namely Alexnet, VGG16 and GoogLeNet are considered in this work. It is evident from the results presented in this work that, GoogLeNet based framework performs well when compared to Alexnet and VGG16.
{"title":"Optimized Convolutional Neural Network based Colour Image Fusion","authors":"B. Lakshmipriya, N. Pavithra, D. Saraswathi","doi":"10.1109/ICSCAN49426.2020.9262439","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262439","url":null,"abstract":"Deep learning has been witnessing an unprecedented growth in various applications like image classification, image recognition, object recognition and so on. In this work, a novel multifocus fusion schematic is putforth using deep learning strategy for the fusion of more than two colour images. The activations of the convolutional neural network (CNN) are used to extract the prominent deep features of the source and these features are fused by the virtue of weighted averaging technique. Finally, the weighted average outputs of the activations of the source images are considered for the recovering the enhanced fused output the image. The fused image is found to be enhanced such that the entire image is free from motion blur and defocusing. Three popular deep learning architectures namely Alexnet, VGG16 and GoogLeNet are considered in this work. It is evident from the results presented in this work that, GoogLeNet based framework performs well when compared to Alexnet and VGG16.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"97 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86284808","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 : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262289
Akshay Prasad, Akshay Kurup, J. K, G. Abhisek, A. Samanta, G. Varaprasad
The level of service quality offered to the patients is drastically declining over the years. The main purpose of this paper is to show a systematic analysis of the literature review based on lean six sigma in the healthcare process. This review aims at to improve service quality by identifying problems faced in the healthcare process and providing reliable solutions. A descriptive review focusing on lean six sigma in the healthcare process, followed by bibliometric analysis aligned with consistent literature review. The literature review related to healthcare process identifies the problems faced in hospitals. Reliable solutions for the problems are identified from literature and summarized. Primary problems are identified through literature review, while the results might not be accurate due to lack of diversity of papers reviewed. Hospital management can utilize the literature classification and the notable references provided in this review for in-process quality improvement. The procedure adopted in this paper is an integrated bibliometric and systematic literature review. The main contribution of this paper includes providing reliable solutions for problems faced in the healthcare sector as derived from the review.
{"title":"Lean Six Sigma solutions for quality improvement in healthcare sector: a systematic review","authors":"Akshay Prasad, Akshay Kurup, J. K, G. Abhisek, A. Samanta, G. Varaprasad","doi":"10.1109/ICSCAN49426.2020.9262289","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262289","url":null,"abstract":"The level of service quality offered to the patients is drastically declining over the years. The main purpose of this paper is to show a systematic analysis of the literature review based on lean six sigma in the healthcare process. This review aims at to improve service quality by identifying problems faced in the healthcare process and providing reliable solutions. A descriptive review focusing on lean six sigma in the healthcare process, followed by bibliometric analysis aligned with consistent literature review. The literature review related to healthcare process identifies the problems faced in hospitals. Reliable solutions for the problems are identified from literature and summarized. Primary problems are identified through literature review, while the results might not be accurate due to lack of diversity of papers reviewed. Hospital management can utilize the literature classification and the notable references provided in this review for in-process quality improvement. The procedure adopted in this paper is an integrated bibliometric and systematic literature review. The main contribution of this paper includes providing reliable solutions for problems faced in the healthcare sector as derived from the review.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"33 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78546936","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 : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262355
R. Thendral, S. Revathi
The data can be missed in the image which are taken from the satellite due to covering of cloud in some places of image. This can reduce the usability of the image. Several methods can solve this accurately, but the method is not effective due to the requirement of multiple images to give the single clear image without cloud. Right now, propose a system called super pixel segmentation and neighbour embedding technique to remove the clouds placed in the images using the single image. This method works effectively using image processing and give the very accurate image. Experiment result can be obtained using satellite images.
{"title":"Deletion of Thick Clouds from Landsat images using Super Pixel Segmentation and Neighbour Embedding Techniques","authors":"R. Thendral, S. Revathi","doi":"10.1109/ICSCAN49426.2020.9262355","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262355","url":null,"abstract":"The data can be missed in the image which are taken from the satellite due to covering of cloud in some places of image. This can reduce the usability of the image. Several methods can solve this accurately, but the method is not effective due to the requirement of multiple images to give the single clear image without cloud. Right now, propose a system called super pixel segmentation and neighbour embedding technique to remove the clouds placed in the images using the single image. This method works effectively using image processing and give the very accurate image. Experiment result can be obtained using satellite images.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"51 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83672637","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 : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262373
C. Someswararao, Shiva Shankar Reddy, S. V. Appaji, Vmnssvkr Gupta
The anomalous development of cells in brain causes brain tumor that may lead to death. The rate of deaths can be reduced by early detection of tumor. Most common method to detect the tumor in brain is the use of Magnetic Resonance Imaging (MRI). MR images are considered because it gives a clear structure of the tumor. In this paper we proposed an novel mechanism for detecting tumor from MR image by applying machine learning algorithms especially with CNN model.
{"title":"Brain Tumor Detection Model from MR Images using Convolutional Neural Network","authors":"C. Someswararao, Shiva Shankar Reddy, S. V. Appaji, Vmnssvkr Gupta","doi":"10.1109/ICSCAN49426.2020.9262373","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262373","url":null,"abstract":"The anomalous development of cells in brain causes brain tumor that may lead to death. The rate of deaths can be reduced by early detection of tumor. Most common method to detect the tumor in brain is the use of Magnetic Resonance Imaging (MRI). MR images are considered because it gives a clear structure of the tumor. In this paper we proposed an novel mechanism for detecting tumor from MR image by applying machine learning algorithms especially with CNN model.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"17 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83974878","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 : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262286
M. Madhumitha, P. Dhivya
Vehicle Recognition from obtaining images in a motion platform is still challenging. The system would focus and capture attributes of vehicles like color, number plate and speed of the vehicle. The images are being captured from various CCTV systems through distributed intelligence along with time and location stamps. The database used to identify suspects from video clips of crime related CCTV footages. This can be achieved by optical character recognition (OCR) and algorithm based on regression YOLO (You Only Look Once). To recognize an vehicle features, Conda tool is used with Tensor flow and Keras framework.
在运动平台上获取图像进行车辆识别仍然具有挑战性。该系统将聚焦并捕捉车辆的颜色、车牌和速度等属性。这些图像是通过分布式智能从不同的闭路电视系统捕获的，并附有时间和地点戳。该数据库用于从与犯罪有关的闭路电视录像片段中识别嫌疑人。这可以通过光学字符识别(OCR)和基于YOLO (You Only Look Once)回归的算法来实现。为了识别车辆特征，将Conda工具与Tensor flow和Keras框架结合使用。
{"title":"Vehicle Recognition and Compilation in Database Software","authors":"M. Madhumitha, P. Dhivya","doi":"10.1109/ICSCAN49426.2020.9262286","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262286","url":null,"abstract":"Vehicle Recognition from obtaining images in a motion platform is still challenging. The system would focus and capture attributes of vehicles like color, number plate and speed of the vehicle. The images are being captured from various CCTV systems through distributed intelligence along with time and location stamps. The database used to identify suspects from video clips of crime related CCTV footages. This can be achieved by optical character recognition (OCR) and algorithm based on regression YOLO (You Only Look Once). To recognize an vehicle features, Conda tool is used with Tensor flow and Keras framework.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"22 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84774872","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 : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262372
R. Poovendran, B. A. Kumar, V. Bhuvaneshwari, R. Aswini, K. Priya
These days, Many agriculture tasks are mechanized and numerous programmed hardware and robots accessible industrially. Two significant issues in present day agribusiness are water shortage and high work worth. The above issues are settled utilizing agribusiness task mechanization it is planned to configuration to diminish work cost [1]. ECOBOT is a robot extraordinarily intended for farming purposes. This diminishes the human work and yields the creation development with low venture of seeds. Agrobot goes about as an Internet of Things gadget which gathers the information from various sensors and passes the data to the client by means of Wi-Fi. This robot for the most part manages burrowing of land, seeding, furrowing, giving water, preparing, splashing medicinal, collecting and so forth. What's more, Microcontrollers like Arduino and Node-MCU is utilized to control and gathers the sensors data.
{"title":"Multi-Purpose Intelligent Drudgery Reducing Ecobot","authors":"R. Poovendran, B. A. Kumar, V. Bhuvaneshwari, R. Aswini, K. Priya","doi":"10.1109/ICSCAN49426.2020.9262372","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262372","url":null,"abstract":"These days, Many agriculture tasks are mechanized and numerous programmed hardware and robots accessible industrially. Two significant issues in present day agribusiness are water shortage and high work worth. The above issues are settled utilizing agribusiness task mechanization it is planned to configuration to diminish work cost [1]. ECOBOT is a robot extraordinarily intended for farming purposes. This diminishes the human work and yields the creation development with low venture of seeds. Agrobot goes about as an Internet of Things gadget which gathers the information from various sensors and passes the data to the client by means of Wi-Fi. This robot for the most part manages burrowing of land, seeding, furrowing, giving water, preparing, splashing medicinal, collecting and so forth. What's more, Microcontrollers like Arduino and Node-MCU is utilized to control and gathers the sensors data.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"53 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80744689","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 : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262420
Maheeja Maddegalla, A. B. Bazil Raj, Gurugubelli Syamala Rao
With the advent of Active Electronically Scanned Array (AESA) technology in the design and development of advanced multi-target handling Radar and Electronic Warfare (EW) systems, a new EW system with a Phased Array of a uniform spacing was developed, whose beam can be controlled using adaptive software programs. The critical EW system is recognized with miniaturized Planar Arrays using Transmit/Receive modules or T-R modules. The T-R modules use a novel core technology for the development of AESA technology. The planar arrays are miniaturized using multifunctional Monolithic Microwave Integrated Circuits (MMIC) with an inbuilt digital circuitry for beam steering, which requires high quality and different levels of programming using Field Programmable Gate Arrays (FPGA's). The AESA generally consists of thousands of T-R modules which can individually spread their signal emissions out across a band of the frequencies and sensitively receive the echoes from target objects, allowing it to broadcast transmitting signals while remaining stealthy and greatly increasing the detection and tracking abilities. Implementation of beam steering and control algorithms has to be designed in the frequency of 5–18 GHz for T-R module based planar arrays.
{"title":"Beam Steering and Control Algorithm for 5-18GHz Transmit/Receive Module Based Active Planar Array","authors":"Maheeja Maddegalla, A. B. Bazil Raj, Gurugubelli Syamala Rao","doi":"10.1109/ICSCAN49426.2020.9262420","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262420","url":null,"abstract":"With the advent of Active Electronically Scanned Array (AESA) technology in the design and development of advanced multi-target handling Radar and Electronic Warfare (EW) systems, a new EW system with a Phased Array of a uniform spacing was developed, whose beam can be controlled using adaptive software programs. The critical EW system is recognized with miniaturized Planar Arrays using Transmit/Receive modules or T-R modules. The T-R modules use a novel core technology for the development of AESA technology. The planar arrays are miniaturized using multifunctional Monolithic Microwave Integrated Circuits (MMIC) with an inbuilt digital circuitry for beam steering, which requires high quality and different levels of programming using Field Programmable Gate Arrays (FPGA's). The AESA generally consists of thousands of T-R modules which can individually spread their signal emissions out across a band of the frequencies and sensitively receive the echoes from target objects, allowing it to broadcast transmitting signals while remaining stealthy and greatly increasing the detection and tracking abilities. Implementation of beam steering and control algorithms has to be designed in the frequency of 5–18 GHz for T-R module based planar arrays.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"46 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78201202","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 : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262392
A. Bakiya, K. Kamalanand, S. Arunmozhi, V. Rajinikanth
Pathological variation in biological soft tissues are commonly interrelated with changes in their mechanical as well as electrical and properties, which helps to distinguish abnormalities. The interrelation between the dielectric and viscoelastic properties is not well established in the biological soft tissue analysis. In this work, an effort has been made to develop a mathematical model to interrelate the dielectric properties and viscoelastic properties of the soft tissues, in frequency domain. The proposed mathematical models have been derived using standard rheological model namely Zener model and dielectric model known as the Debye model. This work is highly useful for predicting the viscoelastic characteristics of the soft tissues using measurements of dielectric quantities as a function of frequency.
{"title":"Frequency Domain Modelling of Interrelation between Dielectric and Viscoelastic Properties of Soft Tissues","authors":"A. Bakiya, K. Kamalanand, S. Arunmozhi, V. Rajinikanth","doi":"10.1109/ICSCAN49426.2020.9262392","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262392","url":null,"abstract":"Pathological variation in biological soft tissues are commonly interrelated with changes in their mechanical as well as electrical and properties, which helps to distinguish abnormalities. The interrelation between the dielectric and viscoelastic properties is not well established in the biological soft tissue analysis. In this work, an effort has been made to develop a mathematical model to interrelate the dielectric properties and viscoelastic properties of the soft tissues, in frequency domain. The proposed mathematical models have been derived using standard rheological model namely Zener model and dielectric model known as the Debye model. This work is highly useful for predicting the viscoelastic characteristics of the soft tissues using measurements of dielectric quantities as a function of frequency.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"22 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83243858","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 : 2020-07-03DOI: 10.1109/ICSCAN49426.2020.9262343
S. Pariselvam, Dhanuja. N, D. S, S. B
Nowadays, Hand gestures playing a important role for human interactions with the computer. Deep Learning is a part of machine learning methods which makes the recognition process easier by using Convolution Neural Networks (ConvNet/CNN). Convolution Neural Networks is a multilayer process network which includes Input layer, Convolution layer, Max pooling layer, Fully connected layer, Output layer. When compared to other algorithms, CNN can give more accurate results. CNN is mainly used to analyze visual images and for the image processing, segmentation and classification with higher accuracy. Here, this model consists of two main systems. One is voice input is converted into text and hand gestures and second approach is hand gestures conversion to text. These two systems are mainly used for abnormal people. These systems are implemented in Python and OpenCV is used to capture images. Each of these two systems has different modules. Human Computer Interaction are main source for the communication between humans and computer. So, these systems are helpful in communicating some information to humans. These systems are free from lighting conditions and background noise by using CNN algorithm.
{"title":"An Interaction System Using Speech and Gesture Based on CNN","authors":"S. Pariselvam, Dhanuja. N, D. S, S. B","doi":"10.1109/ICSCAN49426.2020.9262343","DOIUrl":"https://doi.org/10.1109/ICSCAN49426.2020.9262343","url":null,"abstract":"Nowadays, Hand gestures playing a important role for human interactions with the computer. Deep Learning is a part of machine learning methods which makes the recognition process easier by using Convolution Neural Networks (ConvNet/CNN). Convolution Neural Networks is a multilayer process network which includes Input layer, Convolution layer, Max pooling layer, Fully connected layer, Output layer. When compared to other algorithms, CNN can give more accurate results. CNN is mainly used to analyze visual images and for the image processing, segmentation and classification with higher accuracy. Here, this model consists of two main systems. One is voice input is converted into text and hand gestures and second approach is hand gestures conversion to text. These two systems are mainly used for abnormal people. These systems are implemented in Python and OpenCV is used to capture images. Each of these two systems has different modules. Human Computer Interaction are main source for the communication between humans and computer. So, these systems are helpful in communicating some information to humans. These systems are free from lighting conditions and background noise by using CNN algorithm.","PeriodicalId":6744,"journal":{"name":"2020 International Conference on System, Computation, Automation and Networking (ICSCAN)","volume":"24 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2020-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87175696","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：