Pub Date : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528298
S. Tripathi, Taresh Sarvesh Sharan, Shiru Sharma, N. Sharma
This paper presents a modified segmentation network for brain tumour segmentation in Magnetic Resonance Images. The early detection of brain tumour is quite mandatory for planning the treatment. This work proposes a computer-based automatic approach for the segmentation of brain tumour. The network proposed in this paper effectively delineated the boundaries of the brain tumour region. Exceedingly good results were obtained when the trained network was fed with other datasets. The network also showed a good improvement in the results when it was tested on real-time MRI datasets. An improvement of 7.6% and 7% was observed in the mIoU and BF score when the real time MR dataset of brain tumour was applied to the network. The network was incorporated using depthwise separable convolution.
{"title":"Segmentation of Brain Tumour in MR Images Using Modified Deep Learning Network","authors":"S. Tripathi, Taresh Sarvesh Sharan, Shiru Sharma, N. Sharma","doi":"10.1109/ICSCC51209.2021.9528298","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528298","url":null,"abstract":"This paper presents a modified segmentation network for brain tumour segmentation in Magnetic Resonance Images. The early detection of brain tumour is quite mandatory for planning the treatment. This work proposes a computer-based automatic approach for the segmentation of brain tumour. The network proposed in this paper effectively delineated the boundaries of the brain tumour region. Exceedingly good results were obtained when the trained network was fed with other datasets. The network also showed a good improvement in the results when it was tested on real-time MRI datasets. An improvement of 7.6% and 7% was observed in the mIoU and BF score when the real time MR dataset of brain tumour was applied to the network. The network was incorporated using depthwise separable convolution.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114788224","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528216
Aishwarya Premlal Kogekar, Rashmiranjan Nayak, U. C. Pati
Water problem is one of the important issues faced across globe, particularly developing countries like India. Hence, there is a need for continuous monitoring and forecasting of water quality with the most advanced techniques having low implementation cost, less time consumption as well as high accuracy. This will help the concerned authorities and governments to plan and implement necessary steps to improve the quality of the water, particularly freshwater available in the rivers. Specifically, the water quality of the river Ganga has been deteriorated to a great extent and requires continuous monitoring as well as forecasting of water pollutants to help in water quality management. Hence, in this article, three widely used time series-based models such as Auto-Regressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), and Prophet have been implemented to predict the water quality of the river Ganga. Here, the models are developed on the Uttar Pradesh Pollution Control Board’s official data for the river Ganga corresponding to nine water quality monitoring stations situated in Uttar Pradesh. Further, only two important water parameters such as dissolved oxygen and biochemical oxygen demand, are considered for prediction and subsequently for the forecasting of the water quality. The experimental analysis concludes that SARIMA and Prophet model predict the water quality parameters as well as Water Quality Index (WQI) more accurately.
{"title":"Forecasting of Water Quality for the River Ganga using Univariate Time-series Models","authors":"Aishwarya Premlal Kogekar, Rashmiranjan Nayak, U. C. Pati","doi":"10.1109/ICSCC51209.2021.9528216","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528216","url":null,"abstract":"Water problem is one of the important issues faced across globe, particularly developing countries like India. Hence, there is a need for continuous monitoring and forecasting of water quality with the most advanced techniques having low implementation cost, less time consumption as well as high accuracy. This will help the concerned authorities and governments to plan and implement necessary steps to improve the quality of the water, particularly freshwater available in the rivers. Specifically, the water quality of the river Ganga has been deteriorated to a great extent and requires continuous monitoring as well as forecasting of water pollutants to help in water quality management. Hence, in this article, three widely used time series-based models such as Auto-Regressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), and Prophet have been implemented to predict the water quality of the river Ganga. Here, the models are developed on the Uttar Pradesh Pollution Control Board’s official data for the river Ganga corresponding to nine water quality monitoring stations situated in Uttar Pradesh. Further, only two important water parameters such as dissolved oxygen and biochemical oxygen demand, are considered for prediction and subsequently for the forecasting of the water quality. The experimental analysis concludes that SARIMA and Prophet model predict the water quality parameters as well as Water Quality Index (WQI) more accurately.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128533150","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528091
M. Themalil, Satya Singh, R. Kaur, Divanshu Jain, Gustavo Sanchez, Mayank Sharma
Present day dimension of satellites are constantly being scaled down, hence there is a stronger need for the antennas placed on them to be highly miniaturized. The emergence of small satellites needs new antenna designs compatible with footprints scaled down highly comparative to that of traditional satellites for similar earth coverage operation. The phenomenon of transverse evanescent modes of the inner cavity field and their wide band capability [1] allows the pixel antenna design to be a feasible approach for miniaturization on such scale. The antenna proposed in this paper is redesigned to be used as a lone pixel, but it can be arranged as an array in the agile reconfigurable radiating matrices format, hence being termed as pixel antennas [4]. The objectivity of this present work is to establish the miniaturization capability of this Pixel antenna by designing a miniaturized planar antenna for a small satellite specification, implanted on a nanosatellite and to realize the communication uplink/downlink links in right hand circularly polarized in the upper UHF band.
{"title":"Investigation on Miniaturization Feasibility of the Pixel Antenna for Small Satellite Footprints","authors":"M. Themalil, Satya Singh, R. Kaur, Divanshu Jain, Gustavo Sanchez, Mayank Sharma","doi":"10.1109/ICSCC51209.2021.9528091","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528091","url":null,"abstract":"Present day dimension of satellites are constantly being scaled down, hence there is a stronger need for the antennas placed on them to be highly miniaturized. The emergence of small satellites needs new antenna designs compatible with footprints scaled down highly comparative to that of traditional satellites for similar earth coverage operation. The phenomenon of transverse evanescent modes of the inner cavity field and their wide band capability [1] allows the pixel antenna design to be a feasible approach for miniaturization on such scale. The antenna proposed in this paper is redesigned to be used as a lone pixel, but it can be arranged as an array in the agile reconfigurable radiating matrices format, hence being termed as pixel antennas [4]. The objectivity of this present work is to establish the miniaturization capability of this Pixel antenna by designing a miniaturized planar antenna for a small satellite specification, implanted on a nanosatellite and to realize the communication uplink/downlink links in right hand circularly polarized in the upper UHF band.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133177127","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528193
Mehbooba P. Shareef, Linda Rose Jimson, B. R. Jose
Recommendation systems bring in the lion’s share of e-business. Personalised recommendations make it easy for the user to take decisions quickly since the top recommended items will be produced after analysing user preferences, past user actions and current market trends. A very good recommendation engine is necessary for the e-business to ensure huge revenue. In this paper we quantitatively analyse the research works done on recommendation systems in the last decade(2010-2020) and qualitatively analyze the current state of the art(2018-2021). We find that towards the end of the last decade, deep learning based recommendations attracted more attention due to their ability to make more accurate recommendations.
{"title":"Recommendation Systems : A Comparative Analysis of Classical and Deep Learning Approaches","authors":"Mehbooba P. Shareef, Linda Rose Jimson, B. R. Jose","doi":"10.1109/ICSCC51209.2021.9528193","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528193","url":null,"abstract":"Recommendation systems bring in the lion’s share of e-business. Personalised recommendations make it easy for the user to take decisions quickly since the top recommended items will be produced after analysing user preferences, past user actions and current market trends. A very good recommendation engine is necessary for the e-business to ensure huge revenue. In this paper we quantitatively analyse the research works done on recommendation systems in the last decade(2010-2020) and qualitatively analyze the current state of the art(2018-2021). We find that towards the end of the last decade, deep learning based recommendations attracted more attention due to their ability to make more accurate recommendations.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130117569","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528231
Midhunkrishna P R, L. J., S. Joy, Mukundan K K, Narayanan Namboothiripad M
Radar Altimeters (RA) are widely used as a landing aid for aerospace vehicles because of its better measurement accuracy particularly at low altitude ranges. This paper describes the linear frequency modulated signal generation and the signal processing algorithm developed for an FM-CW altimeter. The altimeter uses two modulation rates to satisfy the measurement accuracy criteria for different applications. For generating the linear frequency modulated signal for both modulation rates, a Direct Digital Synthesis (DDS) based methodology is adopted. The altitude of the aerospace vehicle is measured based on the instantaneous frequency difference (beat signal frequency) between the transmitted and received signals. The beat signal is processed by Fast Fourier Transform (FFT) techniques which provide an additional gain so that the frequency of the required signal can be measured even if the signal to noise ratio is near zero dB. The proposed Radar Altimeter signal processing algorithm decides the modulation rate based on the measured altitude and the strength of the received signal. Higher resolution is ensured at lower altitudes by using a higher modulation rate.
{"title":"Design & implementation of algorithm for linear sweep generation and signal processing for an FMCW radar altimeter","authors":"Midhunkrishna P R, L. J., S. Joy, Mukundan K K, Narayanan Namboothiripad M","doi":"10.1109/ICSCC51209.2021.9528231","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528231","url":null,"abstract":"Radar Altimeters (RA) are widely used as a landing aid for aerospace vehicles because of its better measurement accuracy particularly at low altitude ranges. This paper describes the linear frequency modulated signal generation and the signal processing algorithm developed for an FM-CW altimeter. The altimeter uses two modulation rates to satisfy the measurement accuracy criteria for different applications. For generating the linear frequency modulated signal for both modulation rates, a Direct Digital Synthesis (DDS) based methodology is adopted. The altitude of the aerospace vehicle is measured based on the instantaneous frequency difference (beat signal frequency) between the transmitted and received signals. The beat signal is processed by Fast Fourier Transform (FFT) techniques which provide an additional gain so that the frequency of the required signal can be measured even if the signal to noise ratio is near zero dB. The proposed Radar Altimeter signal processing algorithm decides the modulation rate based on the measured altitude and the strength of the received signal. Higher resolution is ensured at lower altitudes by using a higher modulation rate.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129418750","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528127
Jacob John, M. Varkey, Selvi M
Over the past decade, India’s major cities have been deemed as some of the most unsafe places in the world for women. We know that crimes against women occur every day as newspapers show reports of the activities that occur to not just women but also minor girls. As a result of this, women’s safety is a growing concern for the government. The women in our lives deserve to feel secure wherever they go. This paper aims to help women select the states they travel to or relocate to based on recent criminal activity. The proposed methodology is a web application utilizing the Django framework. The web application provides a map with the crime hotspots of India sourced from reputed news articles on the Internet. Articles are first scraped using a web crawler we have designed. The scraped article is classified into a corresponding category to depict them on the heatmap. Classifying news articles is a multi-class classification problem that requires a robust and powerful machine learning model. A novel hybrid architecture of Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) is adopted and proposed in this paper. The ensemble model performs incredibly well on news sources collated from reputed websites and successfully classifies news articles with an accuracy of 95.1%.
{"title":"Multi-class Text Classification and Publication of Crime Data from Online News Sources","authors":"Jacob John, M. Varkey, Selvi M","doi":"10.1109/ICSCC51209.2021.9528127","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528127","url":null,"abstract":"Over the past decade, India’s major cities have been deemed as some of the most unsafe places in the world for women. We know that crimes against women occur every day as newspapers show reports of the activities that occur to not just women but also minor girls. As a result of this, women’s safety is a growing concern for the government. The women in our lives deserve to feel secure wherever they go. This paper aims to help women select the states they travel to or relocate to based on recent criminal activity. The proposed methodology is a web application utilizing the Django framework. The web application provides a map with the crime hotspots of India sourced from reputed news articles on the Internet. Articles are first scraped using a web crawler we have designed. The scraped article is classified into a corresponding category to depict them on the heatmap. Classifying news articles is a multi-class classification problem that requires a robust and powerful machine learning model. A novel hybrid architecture of Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) is adopted and proposed in this paper. The ensemble model performs incredibly well on news sources collated from reputed websites and successfully classifies news articles with an accuracy of 95.1%.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117146621","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528254
Ayshabi M K, S. M. Idicula
To build an interactive human-like conversational agent, one of the key challenges is to learn to generate responses in a more empathic way. When a conversation has a tone of empathy to it, the person conversing with the conversational agent will feel a sense of contentment. Building an empathetic dialogue system results in increased user interaction and thereby more effective communication. To improve the perception and expression of emotional states, the proposed model uses a multi-resolution mechanism that helps to capture the nuances of user emotions effectively. Moreover, it uses separate decoders, which are optimized to respond to specific emotions, and combines the output response representations to generate an empathetic response. Experimental results show that the proposed approach excels the state-of-the-art baselines in empathy, relevance, and fluency.
{"title":"A Multi-resolution Mechanism with Multiple Decoders for Empathetic Dialogue Generation","authors":"Ayshabi M K, S. M. Idicula","doi":"10.1109/ICSCC51209.2021.9528254","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528254","url":null,"abstract":"To build an interactive human-like conversational agent, one of the key challenges is to learn to generate responses in a more empathic way. When a conversation has a tone of empathy to it, the person conversing with the conversational agent will feel a sense of contentment. Building an empathetic dialogue system results in increased user interaction and thereby more effective communication. To improve the perception and expression of emotional states, the proposed model uses a multi-resolution mechanism that helps to capture the nuances of user emotions effectively. Moreover, it uses separate decoders, which are optimized to respond to specific emotions, and combines the output response representations to generate an empathetic response. Experimental results show that the proposed approach excels the state-of-the-art baselines in empathy, relevance, and fluency.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131109730","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528196
Nazir Nadaf, Preethi A
Alternate sources of energy are explored by researchers to reduce global warming, carbon foot print and power cost. Exponential increase in power requirements for communication and computing devices paved a way to an increased research interest in the area of energy harvesting based power generators. Devices and machines loose energy in the form heat and harvesting this wasted energy is a green and clean energy option. Thermoelectric Generators (TEGs) can convert thermal energy into electrical energy and such generators can be used to harvest energy from waste heat. This paper explores various application areas for thermal energy harvesting using TEGs in both low power and high-power scenarios. This paper also focuses on reviewing available electronic circuitry and methods used for efficient transfer of power to the load from TEGs. A proof-of-concept circuit is developed and tested without incorporating any converters. The maximum power harvested for a temperature gradient of 105 degree Celsius is 64.59mW.
{"title":"Review on Waste Heat Energy Harvesting using TEG: Applications and Enhancements","authors":"Nazir Nadaf, Preethi A","doi":"10.1109/ICSCC51209.2021.9528196","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528196","url":null,"abstract":"Alternate sources of energy are explored by researchers to reduce global warming, carbon foot print and power cost. Exponential increase in power requirements for communication and computing devices paved a way to an increased research interest in the area of energy harvesting based power generators. Devices and machines loose energy in the form heat and harvesting this wasted energy is a green and clean energy option. Thermoelectric Generators (TEGs) can convert thermal energy into electrical energy and such generators can be used to harvest energy from waste heat. This paper explores various application areas for thermal energy harvesting using TEGs in both low power and high-power scenarios. This paper also focuses on reviewing available electronic circuitry and methods used for efficient transfer of power to the load from TEGs. A proof-of-concept circuit is developed and tested without incorporating any converters. The maximum power harvested for a temperature gradient of 105 degree Celsius is 64.59mW.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128354434","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528167
Arnold Sachith A Hans, Mohit Bansal, S. Rao
Face serves as the primary source of contact for humans while interacting with each other. Facial Expressions fall under the bucket of non-verbal type of communication and plays a vital role in understanding the emotional state of a person. Identifying emotions through Facial Expressions can be used in various fields like revealing the Behavior of a candidate in a Job Interview, Understanding the comprehension level of the candidates in a classroom, Healthcare, Electoral campaign etc.; In additions to images fed to the Neural Network, Open Face tool is also used to extract the Facial Action Units of the subject in the dataset which contributes in training a neural network. We have designed and built a model-based technique with a high accuracy to classify the Facial based emotions. The data is trained on a Temporal Relations based Neural Network. Emotions can help us make decisions and it has a wide use case.
{"title":"An Advanced Facial Expression Detection using Deep Neural Network","authors":"Arnold Sachith A Hans, Mohit Bansal, S. Rao","doi":"10.1109/ICSCC51209.2021.9528167","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528167","url":null,"abstract":"Face serves as the primary source of contact for humans while interacting with each other. Facial Expressions fall under the bucket of non-verbal type of communication and plays a vital role in understanding the emotional state of a person. Identifying emotions through Facial Expressions can be used in various fields like revealing the Behavior of a candidate in a Job Interview, Understanding the comprehension level of the candidates in a classroom, Healthcare, Electoral campaign etc.; In additions to images fed to the Neural Network, Open Face tool is also used to extract the Facial Action Units of the subject in the dataset which contributes in training a neural network. We have designed and built a model-based technique with a high accuracy to classify the Facial based emotions. The data is trained on a Temporal Relations based Neural Network. Emotions can help us make decisions and it has a wide use case.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121558311","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528163
Aruna K A, V. S. Anil, Anju Anand, Anagha Jaysankar, Anjali Venugopal, K. L. Nisha, G. Sreelekha
Retinopathy of Prematurity (ROP) is an ocular disease observed in premature babies which, if left untreated, causes permanent blindness. Problematically, the visual indicators of ROP are not well understood and neonatal fundus images are usually of poor quality and resolution. Simplifying the methods of the detection of ROP would be highly beneficial. The various features for detection of ROP disease come from the anterior and posterior regions of the retina, which will not be available in a single image. Hence in practice, multiple images of different views are taken from the same infant and various regions are tested individually from different images. Here we propose an efficient methodology for combining the images through image mosaicing where the transformation parameters are obtained from the pre-processed neonatal fundus images. A crucial step in image mosaicing is finding robust features for feature matching, which will in turn help in obtaining the appropriate transformation parameters. In the proposed method, feature locations are taken from skeletonized images and feature descriptors from enhanced images. This approach enables us to obtain a satisfactory mosaic even while choosing a less complex six parameter-affine transformation model in contrast to the existing methodologies which require more parameters.
{"title":"Image Mosaicing for Neonatal Fundus Images","authors":"Aruna K A, V. S. Anil, Anju Anand, Anagha Jaysankar, Anjali Venugopal, K. L. Nisha, G. Sreelekha","doi":"10.1109/ICSCC51209.2021.9528163","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528163","url":null,"abstract":"Retinopathy of Prematurity (ROP) is an ocular disease observed in premature babies which, if left untreated, causes permanent blindness. Problematically, the visual indicators of ROP are not well understood and neonatal fundus images are usually of poor quality and resolution. Simplifying the methods of the detection of ROP would be highly beneficial. The various features for detection of ROP disease come from the anterior and posterior regions of the retina, which will not be available in a single image. Hence in practice, multiple images of different views are taken from the same infant and various regions are tested individually from different images. Here we propose an efficient methodology for combining the images through image mosaicing where the transformation parameters are obtained from the pre-processed neonatal fundus images. A crucial step in image mosaicing is finding robust features for feature matching, which will in turn help in obtaining the appropriate transformation parameters. In the proposed method, feature locations are taken from skeletonized images and feature descriptors from enhanced images. This approach enables us to obtain a satisfactory mosaic even while choosing a less complex six parameter-affine transformation model in contrast to the existing methodologies which require more parameters.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117348556","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：