{"title":"Occlusion detection and recognizing human face using neural network","authors":"Tanvi Patel, Jalpa Patel","doi":"10.1109/I2C2.2017.8321959","DOIUrl":"https://doi.org/10.1109/I2C2.2017.8321959","url":null,"abstract":"Face recognition is one of the most important problems of verifying or identifying a face from query image or input image. This system has emerged as an important field in case of surveillance systems. Face detection is a very powerful tool for video surveillance, human computer interface, face recognition, and image database management. Occlusion means extraneous objects that hinder face recognition, e.g., face covered with scarf, wearing glasses, beard, cap etc., is one of the greatest challenges in face recognition systems. Other issues are illumination, pose, expressions etc. An efficient method is used for detection of occlusions, which specifies the missing information in the occluded face. Method used for face detection is Viola-Jones algorithm, for occlusion detection and reconstruction of face fast weighted PCA is used are Neural Network (NN) is used for face recognition. Other appropriate methods are Principal Component Analysis (PCA), Local Binary Pattern (LBP), Eigenfaces. Propose method which is used will detect occluded face and recognize the face with the help of given same faces from the database.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"107 1-2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132062453","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}
{"title":"Automatic toll payment, alcohol detection, load and vehicle information using Internet of things & mailing system","authors":"Anand Kumar, N. Anusha, B. Prasad","doi":"10.1109/I2C2.2017.8321775","DOIUrl":"https://doi.org/10.1109/I2C2.2017.8321775","url":null,"abstract":"Present days, the technology has emerged in such a way that it can provide solutions to any real life problems. One such solution to the problem of collecting toll payments efficiently is RFID. When a vehicle passes through the toll gate, by using RFID the vehicle can be detected easily and the amount will be deducted from the user's prepaid account automatically. In order to detect the drunken drivers, Alcohol sensor(MQ135) is fixed near the driver steering. If the alcohol consumed by the driver exceeds the limit detected by sensors automatically accelerometer reduces the speed. The load detector fixed at the toll gates checks the load of heavy vehicles if load exceeds the limit, the barrier remains closed and the camera captures a snap of the vehicle. And also the notification will be sent to the consignment officer for registering complaint against the vehicle and also penalty amount will be deducted from the owner's account.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115487368","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}
{"title":"Image annotation using deep learning: A review","authors":"Utkarsh Ojha, U. Adhikari, D. Singh","doi":"10.1109/I2C2.2017.8321819","DOIUrl":"https://doi.org/10.1109/I2C2.2017.8321819","url":null,"abstract":"In the last few years, deep learning has led to huge success in the field of computer vision and natural language understanding and also in the interplay between them. Among different types of deep learning models, convolutional neural networks have been most extensively studied for the tasks related to visual perception and machine vision. Due to lack of computational resources and training data, it is very hard to the use high-capacity convolutional neural network without overfitting. But recent growth in the availability of annotated data and high performance GPUs have made it possible to obtain state-of-the-art results using convolutional neural networks. In this paper, we present a review on how and why CNNs are extensively getting used in the computer vision community. It also introduces an application of ConvNets for annotating contents of the image by partially localizing them.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123216161","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}
P. Adithya, S. Aishwarya, S. Megalai, S. Priyadharshini, R. Kurinjimalar
{"title":"Security enhancement in automated teller machine","authors":"P. Adithya, S. Aishwarya, S. Megalai, S. Priyadharshini, R. Kurinjimalar","doi":"10.1109/I2C2.2017.8321773","DOIUrl":"https://doi.org/10.1109/I2C2.2017.8321773","url":null,"abstract":"Security is provided to grant access to a legal user and to prevent the system from an illegal person. Password authentication in public space often poses the problem of disclosure either through spywares like key loggers installed on target machine or a malicious onlooker who observes while the person enters the password. Virtual keyboards provide protection against key loggers but fail to avoid shoulder-surfing. In this proposed system it is planned to improvise these keyboards by changing the layout to frustrate the hackers. When the person enters his PIN in the touch screen, immediately the arrangement of the numbers in the screen will be changed from its original position. The person entering next wouldn't have the same arrangement of numbers in the touch screen. Even when the shoulder-Surfer observes the movement of the person entering the PIN number they can't able to hack the password. By using Arduino IDE compiler with Arduino it is efficiently possible to avoid Shoulder-Surfing attacks.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132133216","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}
{"title":"Analysis of various delay elements @ 16-nm technology node","authors":"Amit Krishna Dwivedi, A. Mal, A. Islam","doi":"10.1109/I2C2.2017.8321786","DOIUrl":"https://doi.org/10.1109/I2C2.2017.8321786","url":null,"abstract":"This paper makes a profound study of seven different non-programmable delay elements. Signals can be delayed by a desired amount by passing it through these delay elements. Maintaining the signal integrity while incorporating certain delay is also a vital role of these delay elements. Performance evaluation of these delay circuits is presented in terms of different design metrics to lay down comparison among these circuits. This work will help design engineers to select appropriate delay elements based upon their specific requirements. Reported results are based on extensive simulations performed on SPICE simulator using predictive technology model (PTM) @ 16-nm technology node.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132527123","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}
{"title":"Façade cleaning machine","authors":"Vyankatesh Ravindra Maindargikar, Charudatt Mane, Vikas Sominath Kandgul","doi":"10.1109/i2c2.2017.8321924","DOIUrl":"https://doi.org/10.1109/i2c2.2017.8321924","url":null,"abstract":"The automatic façade cleaning machine has been profitably and successfully designed and fabricated. The elements used in this work are simple and cheap. This machine can work well for buildings having completely façade exterior. The cleaning process takes about (35) seconds to finish a 1m2 window/façade pane. The time rely on the speed of the motors and the degree of dirtiness of the glass pane. Uniform whisk off by using rubber brush and optimal in-line water pump deliver soap water for removing stubborn stains and controlled spray of water. This system is simple in design, inexpensive to manufacture, rugged in construction, easy to use and efficient in operation. The major advantage of this machine is the reduction of death rate of the façade cleaning workers by replacing them with an automatic and efficient façade cleaning machine. The machine construction is able to perform its predetermined functions that, the efficient cleaning of façade structures.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115316678","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}
K. Reddy, K. Tejas, C. Swathi, K. Ashok, M. RajeshKumar
{"title":"High capacity, secure (n, n/8) multi secret image sharing scheme with security key","authors":"K. Reddy, K. Tejas, C. Swathi, K. Ashok, M. RajeshKumar","doi":"10.1109/i2c2.2017.8321797","DOIUrl":"https://doi.org/10.1109/i2c2.2017.8321797","url":null,"abstract":"The rising need of secret image sharing with high security has led to much advancement in lucrative exchange of important images which contain vital and confidential information. Multi secret image sharing system (MSIS) is an efficient and robust method for transmitting one or more secret images securely. In recent research, n secret images are encrypted into n or n+ 1 shared image's and stored in different database servers. Decoder has to receive all n or n+1 encrypted images to reproduce the secret image. One can recover partial secret information from n-1 or fewer shared images, which poses risk for the confidential information encrypted. In this proposed paper we developed a novel algorithm to increase the sharing capacity by using (n, n/8) multi secret sharing scheme with increased security by generating unique security key. An unrevealed comparison image is used to produce shares which makes the secret image invulnerable to the hackers.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115441660","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}
{"title":"Analysis of Energy Aware Sleep Scheduling Routing protocol(EASSR) in wireless sensor networks","authors":"S. Sanjana, L. Shavanthi, R. Bhagya","doi":"10.1109/I2C2.2017.8321920","DOIUrl":"https://doi.org/10.1109/I2C2.2017.8321920","url":null,"abstract":"Wireless Sensor Networks (WSNs) refers to a collection of many sensor nodes which are of low cost. WSNs are deployed in many applications like inhospitable terrain, health applications, military etc. Nowadays WSN related protocols and algorithms are designed to achieve higher life time and energy efficiency in the deployed networks. In this regard, clustering is the appropriate technique to with stand the load among the clusters. Various energy efficient cluster based algorithms are studied and Energy Aware Sleep Scheduling Routing (EASSR) being one of the best approaches is implemented because of its advantages over their counterpart and simulated in MATLAB.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115492620","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}
{"title":"Interactive retrieval of spoken content optimizing by LDA algorithm","authors":"S. Chavan, R. Kagalkar","doi":"10.1109/I2C2.2017.8321791","DOIUrl":"https://doi.org/10.1109/I2C2.2017.8321791","url":null,"abstract":"Communication between the human are performed by using different languages. Language is either in written or spoken form. In our paper, as an author we are representing a framework that gives output as a description for audio file using signal processing. The output is in the text format which is derived by examining the audio content and providing the description of audio in the text format. So the study of translation of audio into text goes increasing. The framework is distributed into two sections called training and testing section. The training section is train the audio with its description like speech conversation present in that audio. This data is stored in the system using database with features of scenario of audio. Another section is testing section. The testing section test the audio file and retrieve the output as description of audio comparing audios stored into database (i.e. in training section). Using Latent Dirichlet allocation processing sentences are generated from objects and their activities.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117151669","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}
{"title":"ICI mitigation in MIMO-OFDM by iterative equalization using OPT in time varying channels","authors":"K. P. Sherin, E. Abhitha","doi":"10.1109/I2C2.2017.8321824","DOIUrl":"https://doi.org/10.1109/I2C2.2017.8321824","url":null,"abstract":"Time variation of channel in orthogonal frequency division multiplexing (OFDM) system destroys the orthogonality between subcarriers, and introduces inter carrier interference (ICI). Different methods have been used to combat ICI, but the computational complexity of some methods is high. In multiple-input multiple-output (MIMO) system the complexity is even higher. This paper proposes a low complexity iterative method called operator perturbation technique (OPT) is used for MIMO-OFDM system to reduce ICI under the assumption of linear time-varying channels. It requires channel estimation based on linear time-varying channel model. Time-domain synchronous-OFDM suits for this proposed iterative technique because its receiver can easily estimate linear time-varying channels. Simulation with QPSK modulation demonstrates the performance of the proposed method. Here we compare LTI and LTV performance for QPSK modulation. Result shows that the iterative method has nearly similar performance for both LTV and LTI channel irrespective of their channel condition. Also better BER and MSE performance for both LTV and LTI algorithm is achieved when the Doppler frequency is 10Hz.","PeriodicalId":288351,"journal":{"name":"2017 International Conference on Intelligent Computing and Control (I2C2)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123332608","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}