Pub Date : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182044
Konjengbam Dollar Singh, Syed Thouheed Ahmed
As a proverb goes, “A Picture speaks more than a word”. The influence of a picture on any given information is predominant and has extra mileage in representing the information. In this paper, a linear model of word recognition is proposed using the image datasets. The proposed model is evaluated on primary datasets of UCL repository, the results are processed using MATLAB and the recognition ratio is effective compared to the previous approaches. Typically, the proposed technique is an optimized solution for word string extraction from a given image data-samples.
{"title":"Systematic Linear Word String Recognition and Evaluation Technique","authors":"Konjengbam Dollar Singh, Syed Thouheed Ahmed","doi":"10.1109/ICCSP48568.2020.9182044","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182044","url":null,"abstract":"As a proverb goes, “A Picture speaks more than a word”. The influence of a picture on any given information is predominant and has extra mileage in representing the information. In this paper, a linear model of word recognition is proposed using the image datasets. The proposed model is evaluated on primary datasets of UCL repository, the results are processed using MATLAB and the recognition ratio is effective compared to the previous approaches. Typically, the proposed technique is an optimized solution for word string extraction from a given image data-samples.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128563577","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182084
K. Namitha, A. Narayanan, M. Geetha
Video synopsis technique aims to condense long duration videos into its compact representation for efficient browsing and retrieval of surveillance videos. The synopsis videos depend on the results of object detection and tracking in input video. However, there is a lack of publicly available commonly used datasets that are properly annotated for training trackers and analyzing the performance of various approaches in video synopsis. This paper introduces an interactive toolbox that allows users to generate synthetic videos with user-defined parameters and related tube information, eliminating the steps of detection and tracking. The proposed toolbox enables users to simulate general and specific scenarios of interest, which are expected to be observed in surveillance videos. We present experiments that show the usability and effectiveness of using this toolbox in evaluating different video synopsis methods.
{"title":"A Synthetic Video Dataset Generation Toolbox for Surveillance Video Synopsis Applications","authors":"K. Namitha, A. Narayanan, M. Geetha","doi":"10.1109/ICCSP48568.2020.9182084","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182084","url":null,"abstract":"Video synopsis technique aims to condense long duration videos into its compact representation for efficient browsing and retrieval of surveillance videos. The synopsis videos depend on the results of object detection and tracking in input video. However, there is a lack of publicly available commonly used datasets that are properly annotated for training trackers and analyzing the performance of various approaches in video synopsis. This paper introduces an interactive toolbox that allows users to generate synthetic videos with user-defined parameters and related tube information, eliminating the steps of detection and tracking. The proposed toolbox enables users to simulate general and specific scenarios of interest, which are expected to be observed in surveillance videos. We present experiments that show the usability and effectiveness of using this toolbox in evaluating different video synopsis methods.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128617603","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182422
V. R. Mol, P. Maheswari
Images in the true world are subjected to numerous forms of modification during its capture, acquisition, storage, transmission and reproduction. Images are everywhere in our daily life, not only because they are extensively used as a channel for communication but also they are one of the best way to represent the physical world. Digital image is a numeric description, usually binary representation of a two dimensional image. Digital Image Processing is the process which uses computer algorithms to process digital image. One of the most interesting areas in image processing is to enhance the pictorial information for human interpretation. The main aim of image restoration is to reconstruct the original image from a deteriorated image. A lot of researches are being carried out on image restoration. This paper mainly focuses on different techniques used for digital restoration of paintings and various parameters used for evaluation.
{"title":"A Survey on Restoration of Paintings","authors":"V. R. Mol, P. Maheswari","doi":"10.1109/ICCSP48568.2020.9182422","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182422","url":null,"abstract":"Images in the true world are subjected to numerous forms of modification during its capture, acquisition, storage, transmission and reproduction. Images are everywhere in our daily life, not only because they are extensively used as a channel for communication but also they are one of the best way to represent the physical world. Digital image is a numeric description, usually binary representation of a two dimensional image. Digital Image Processing is the process which uses computer algorithms to process digital image. One of the most interesting areas in image processing is to enhance the pictorial information for human interpretation. The main aim of image restoration is to reconstruct the original image from a deteriorated image. A lot of researches are being carried out on image restoration. This paper mainly focuses on different techniques used for digital restoration of paintings and various parameters used for evaluation.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124782882","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182203
B. Rajarajeswarie, R. Sandanalakshmi
The current mobile infrastructure faces an exponential growth in mobile traffic volumes which causes a demand on high data rate and low latency. Hence massive MIMO is one of the most promising technology of fifth Generation (5G) wireless communication systems due to its high data rate and system throughput. In this technology the major challenges are high computational complexity and great difficulties in the exploitation of the multiple antenna systems. Hence, this survey paper focuses on the issues on the Massive MIMO system in 5G wireless systems and the use of intelligence to resolve the challenges to improve the user experience and to utilize the radio resources in an effective way. Therefore, this paper provides a short survey that provides an overview of the implementation Artificial Intelligence in 5G wireless systems for solving various challenges in the Massive MIMO system.
当前的移动基础设施面临着移动通信量的指数级增长，这导致了对高数据速率和低延迟的需求。因此，大规模多输入多输出（MIMO）因其高数据速率和系统吞吐量而成为第五代（5G）无线通信系统中最有前途的技术之一。这项技术面临的主要挑战是计算复杂度高和利用多天线系统的巨大困难。因此，本调查报告重点关注 5G 无线系统中的 Massive MIMO 系统问题，以及如何利用智能来解决这些挑战，从而改善用户体验并有效利用无线电资源。因此，本文提供了一份简短的调查报告，概述了人工智能在 5G 无线系统中的应用，以解决 Massive MIMO 系统中的各种挑战。
{"title":"A Short Survey: Applications of Artificial Intelligence in Massive MIMO","authors":"B. Rajarajeswarie, R. Sandanalakshmi","doi":"10.1109/ICCSP48568.2020.9182203","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182203","url":null,"abstract":"The current mobile infrastructure faces an exponential growth in mobile traffic volumes which causes a demand on high data rate and low latency. Hence massive MIMO is one of the most promising technology of fifth Generation (5G) wireless communication systems due to its high data rate and system throughput. In this technology the major challenges are high computational complexity and great difficulties in the exploitation of the multiple antenna systems. Hence, this survey paper focuses on the issues on the Massive MIMO system in 5G wireless systems and the use of intelligence to resolve the challenges to improve the user experience and to utilize the radio resources in an effective way. Therefore, this paper provides a short survey that provides an overview of the implementation Artificial Intelligence in 5G wireless systems for solving various challenges in the Massive MIMO system.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126915801","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182338
P. Yaswanth, Pranav A, R. Minu
In our world around one-third of people are suffering from seizures and these people must have a continuous optimal medication process. Now a day’s systems are developed with an algorithm for the detection of a seizure by using EEG data, sensors, and video/audio captures. But it still unclear what combination of technologies will give the best output of detection.
{"title":"Automatic Seizure Classification using CNN","authors":"P. Yaswanth, Pranav A, R. Minu","doi":"10.1109/ICCSP48568.2020.9182338","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182338","url":null,"abstract":"In our world around one-third of people are suffering from seizures and these people must have a continuous optimal medication process. Now a day’s systems are developed with an algorithm for the detection of a seizure by using EEG data, sensors, and video/audio captures. But it still unclear what combination of technologies will give the best output of detection.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127024924","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182197
Sweety Singh, Subhasish Banerjee
Network Anomaly Detection Systems (NADS) has a great importance in Network Defense System for detecting potential or critical threats. Numerous Organization have actualized, Intrusion Detection System (IDS) as a security segment, and introduced the various mechanism to recognize the effect of the system assaults. However, Machine Learning methods are widely used in IDS to detect the various attacks. In this context, network traffic dataset plays very important role. Hence, IDS uses those datasets to learn about normal and anomalous activities. Whereas the labelled datasets are used for training phase. As appropriate selection of Machine Learning methods gives the better result, therefore, a comparative study about few machine learning methods have been used in this article using NSL-KDD dataset for the analysis purpose. Finally, the simulated results have been compared by implementing of Naïve Bayes classifier (NB), Support Vector Machine (SVM) and Decision Tree classifier on NSL-KDD dataset. Recursive Feature Elimination (RFE) and Principal Component Analysis (PCA) have been used for selecting the appropriate features among all features present in the dataset to improve the accuracy and processing speed of the IDS.
{"title":"Machine Learning Mechanisms for Network Anomaly Detection System: A Review","authors":"Sweety Singh, Subhasish Banerjee","doi":"10.1109/ICCSP48568.2020.9182197","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182197","url":null,"abstract":"Network Anomaly Detection Systems (NADS) has a great importance in Network Defense System for detecting potential or critical threats. Numerous Organization have actualized, Intrusion Detection System (IDS) as a security segment, and introduced the various mechanism to recognize the effect of the system assaults. However, Machine Learning methods are widely used in IDS to detect the various attacks. In this context, network traffic dataset plays very important role. Hence, IDS uses those datasets to learn about normal and anomalous activities. Whereas the labelled datasets are used for training phase. As appropriate selection of Machine Learning methods gives the better result, therefore, a comparative study about few machine learning methods have been used in this article using NSL-KDD dataset for the analysis purpose. Finally, the simulated results have been compared by implementing of Naïve Bayes classifier (NB), Support Vector Machine (SVM) and Decision Tree classifier on NSL-KDD dataset. Recursive Feature Elimination (RFE) and Principal Component Analysis (PCA) have been used for selecting the appropriate features among all features present in the dataset to improve the accuracy and processing speed of the IDS.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129028711","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182331
Dinna Davis, R. Dipin Krishnan
The Power amplifier is an indispensable component for the transmitter. Unfortunately, it is nonlinear, when the PA operates around its region of high power efficiency. The functioning of PA is needed to be at its saturation level,for the purpose of getting good energy-efficiency, which generates nonlinear outputs as their outcomes. HPAs are habitually deformed and however shows a tendency to produce the nonlinear outputs, thereby saturation level is forlorn failed to achieved. A new approach is used here in order to rectify the issues due to the non-linear effects in power amplifier operation. Linearization of power amplifier using predistortion technique is our new method. Linearization enables the PA to generate more output power and to operate at a higher efficiency level for the given input. Linearization is a systematic procedure that can be used to reduce the amplifier distortion. A pre-distorter is aptly designed and inserted in front of the PA, to oppose the non-linearization in PA. To model the PA Wiener model is considered and the Hammerstein model is considered to built pre-distorter. To solve the existing problems in the predistorter of power amplifier optimization algorithms such as ABC and PSO are used. Using MATLAB the new approach is simulated and the outputs achieved are analyzed.
{"title":"Power Amplifier Linearization using Hybrid Optimization Techniques","authors":"Dinna Davis, R. Dipin Krishnan","doi":"10.1109/ICCSP48568.2020.9182331","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182331","url":null,"abstract":"The Power amplifier is an indispensable component for the transmitter. Unfortunately, it is nonlinear, when the PA operates around its region of high power efficiency. The functioning of PA is needed to be at its saturation level,for the purpose of getting good energy-efficiency, which generates nonlinear outputs as their outcomes. HPAs are habitually deformed and however shows a tendency to produce the nonlinear outputs, thereby saturation level is forlorn failed to achieved. A new approach is used here in order to rectify the issues due to the non-linear effects in power amplifier operation. Linearization of power amplifier using predistortion technique is our new method. Linearization enables the PA to generate more output power and to operate at a higher efficiency level for the given input. Linearization is a systematic procedure that can be used to reduce the amplifier distortion. A pre-distorter is aptly designed and inserted in front of the PA, to oppose the non-linearization in PA. To model the PA Wiener model is considered and the Hammerstein model is considered to built pre-distorter. To solve the existing problems in the predistorter of power amplifier optimization algorithms such as ABC and PSO are used. Using MATLAB the new approach is simulated and the outputs achieved are analyzed.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121340601","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182052
Hilkiya Joseph, Bindhu K. Rajan
The success of internet technology transform the world of technology and fashioned our life such a lot easier. The matter of duplication and unauthorized use of information become a great threat within the field of technology. To beat these problems, techniques like digital watermarking, steganography and cryptography were introduced. The approach of embedding a secret data associated with the digital signal inside the signal itself is digital watermarking. For embedding and detecting the watermark different techniques are used; spatial domain techniques like Least Significant Bit (LSB) and Patch Work Algorithm, then the frequency domain techniques such as Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Discrete Fourier Transform (DFT) are some of them. Combination of DCT & DWT technique for digital watermarking is proposed here. The proposed methodology is implemented in MATLAB 2017a simulator and result is analysed using evaluation parameters like Peak Signal to Noise Ratio (PSNR) & Mean Square Error (MSE). PSNR value obtained for the case of watermarking using DWT is 27.46 and MSE value is 17.45. The value of PSNR for watermarking using DCT is 41.4 and for MSE the value is 0.67. The PSNR and MSE values obtained for watermarking using LSB technique is 50.55 and 0.58. The proposed method improves the watermarked image quality and the MSE & PSNR value obtained is 0.52 and 51.017 respectively.
{"title":"Image Security Enhancement using DCT & DWT Watermarking Technique","authors":"Hilkiya Joseph, Bindhu K. Rajan","doi":"10.1109/ICCSP48568.2020.9182052","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182052","url":null,"abstract":"The success of internet technology transform the world of technology and fashioned our life such a lot easier. The matter of duplication and unauthorized use of information become a great threat within the field of technology. To beat these problems, techniques like digital watermarking, steganography and cryptography were introduced. The approach of embedding a secret data associated with the digital signal inside the signal itself is digital watermarking. For embedding and detecting the watermark different techniques are used; spatial domain techniques like Least Significant Bit (LSB) and Patch Work Algorithm, then the frequency domain techniques such as Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Discrete Fourier Transform (DFT) are some of them. Combination of DCT & DWT technique for digital watermarking is proposed here. The proposed methodology is implemented in MATLAB 2017a simulator and result is analysed using evaluation parameters like Peak Signal to Noise Ratio (PSNR) & Mean Square Error (MSE). PSNR value obtained for the case of watermarking using DWT is 27.46 and MSE value is 17.45. The value of PSNR for watermarking using DCT is 41.4 and for MSE the value is 0.67. The PSNR and MSE values obtained for watermarking using LSB technique is 50.55 and 0.58. The proposed method improves the watermarked image quality and the MSE & PSNR value obtained is 0.52 and 51.017 respectively.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128080087","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182249
G. M. Sai, K. Avinash, L. S. G. Naidu, M. Rohith, M. Vinodhini
Temporary errors which are classified under soft errors are created because of fluctuations in the voltage or external radiations. These errors are very common and obvious in memories. In this paper, Diagonal Hamming based multi-bit error detection and correction technique is proposed to identify errors to an extent of 8-bit. Rectification of 1, 2, 3, 4, 5 bit errors are possible. Few combinations of 6 and 7 random bit errors and burst errors of 8 bit are correctable. By using this method, high code rate is achieved with less area and delay when in contrast to various techniques.
{"title":"Diagonal Hamming Based Multi-Bit Error Detection and Correction Technique for Memories","authors":"G. M. Sai, K. Avinash, L. S. G. Naidu, M. Rohith, M. Vinodhini","doi":"10.1109/ICCSP48568.2020.9182249","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182249","url":null,"abstract":"Temporary errors which are classified under soft errors are created because of fluctuations in the voltage or external radiations. These errors are very common and obvious in memories. In this paper, Diagonal Hamming based multi-bit error detection and correction technique is proposed to identify errors to an extent of 8-bit. Rectification of 1, 2, 3, 4, 5 bit errors are possible. Few combinations of 6 and 7 random bit errors and burst errors of 8 bit are correctable. By using this method, high code rate is achieved with less area and delay when in contrast to various techniques.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134018250","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182133
G. Sundar, Varsha Anand, J. P. Anita
Facial Recognition has become a key feature when it comes to biometrics. In order to capture a person’s face, there are certain vital attributes of the face that we need to understand such as length and width of nose, eyes, chin, eyebrows etc. There are many existing methods (algorithms) for performing facial detection but it is difficult to assess the performance of these methods because of its complexity. In this paper, facial recognition using the property of golden ratio of human face is discussed. The proposed technique is more efficient in terms of run time length and detection process is easy as it only stores the eye data. Hence measuring only the distance between the eyes would help us do facial recognition. A realistic comparison between Haar feature-based cascade classifier and contour mapping based algorithm is presented. Georgia tech university’s dataset has been used for the purpose of comparison of different algorithms.
{"title":"Interocular Distance based Facial Recognition","authors":"G. Sundar, Varsha Anand, J. P. Anita","doi":"10.1109/ICCSP48568.2020.9182133","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182133","url":null,"abstract":"Facial Recognition has become a key feature when it comes to biometrics. In order to capture a person’s face, there are certain vital attributes of the face that we need to understand such as length and width of nose, eyes, chin, eyebrows etc. There are many existing methods (algorithms) for performing facial detection but it is difficult to assess the performance of these methods because of its complexity. In this paper, facial recognition using the property of golden ratio of human face is discussed. The proposed technique is more efficient in terms of run time length and detection process is easy as it only stores the eye data. Hence measuring only the distance between the eyes would help us do facial recognition. A realistic comparison between Haar feature-based cascade classifier and contour mapping based algorithm is presented. Georgia tech university’s dataset has been used for the purpose of comparison of different algorithms.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134095815","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：