Browsing by Author "Khan, Mubashir"
Now showing 1 - 20 of 21
Results Per Page
Sort Options
Item Accident alert and pothole detection system(AIKTC, 2018-05) Khan, Mubashir; Khan, Sarfaraz H (14CO42); Malim, Usama I (14CO34); Ansari, Mohd Junaid (15DCO44)India witnessed one of the highest road accidents in the world, as stated by Union road transport and highways ministry in 2016. Road accident often takes place due to bad road weather condition, reckless driving etc. Accident occurring are often not noticed or reported late that leads to loss of victim’s life or serious injuries caused permanently. One of the problems associated with bad road condition is the pothole on road. Accident Alert Pothole Detection System (AAPDS)is a system designed for reporting of accident and potholes on roads. The System consists of various sensors that are used for sensing accident’s and pothole’s on roads. A smartphone is used to provide exact location of accidents using GSM GPS module present in smartphone after the response from the sensor is taken. A map is provided to navigate the location of accident. Similarly a sensor is used for sensing pothole’s. This data is then processed by the processing module send to the smartphone, where the map is used to display the location of pothole’s. Further the collection of such data can be send to concern authorities where this kind of data is stored and managed for managing the road condition and providing prior warning of accident prone area.Item Accident alert system(AIKTC, 2021-05) Khan, Mubashir; Ansari, Mohd Aamir Mohd Sharif (17CO38); Nathani, Aamir Haneef (17CO39); Khan, Nazim Matiullah (17CO31); Ansari, Faisal (17DCO62)Nowadays, Driver drowsiness is one of the major cause for most of the accidents in the world. Detecting the driver eye tiredness is the easiest way for measuring the drowsiness of driver. The existing systems in the literature, are providing slightly less accurate results due to low clarity in images and videos, which may result due to variations in the camera positions. In order to solve this problem, a driver drowsiness detection system is proposed in this paper, which makes use of eye blink counts for detecting the drowsiness. Specifically, the proposed framework, continuously analyzes the eye movement of the driver and alerts the driver by activating the vibrator when he/she is drowsy. When the eyes are detected closed for too long time, a vibrator signal is generated to warn the driver. The experimental results of the proposed system, which is implemented on Open CV and Raspberry Pi environment with a single camera view, illustrate the good performance of the system in terms of accurate drowsiness detection results and thereby reduces the road accidents. Keywords: Drowsiness, Fatigue Detection, Raspberry Pi, Image Processing, Eye Detection, EARItem Authentication of marksheet using QR code(AIKTC, 2018-05) Khan, Mubashir; Mungi, Abrar N. (15DCO57); Sayyed, Mehfooz (14CO44); Khan, Mustafa (14CO36); Shaikh, Mohd.Saad (15DCO72)In today’s digital world we have often hear the news about fake marksheet and unauthenticated certificate, and as we all know that marksheet is very sensitive document and no one wants to carry the hard copies of their marksheet as there is a chance of misplace of it, so it is a big challenge to provide security and authenticity of digital data. Our aim is to provide a digital marksheet which can’t be modified from third party and also user can access their marksheet in any smart device. Digital marksheet is generated through the QR code and in that modification is not possible. And also if someone wants to verify whether the marksheet is genuine or fake then instead of writing applications to Universities and Institutes they just have to scan the QR code.Item Authentication of marksheet using QR code(AIKTC, 2018-05) Khan, Mubashir; Mungi, Abrar N (15DCO57) Abrar N.(15DCO57); Sayyed, Mehfooz (14CO44); Khan, Mustafa(14CO36); Shaikh, Mohd.Saad (15DCO72)In today’s digital world we have often hear the news about fake marksheet and unauthenticated certificate, and as we all know that marksheet is very sensitive document and no one wants to carry the hard copies of their marksheet as there is a chance of misplace of it, so it is a big challenge to provide security and authenticity of digital data. Our aim is to provide a digital marksheet which can’t be modified from third party and also user can access their marksheet in any smart device. Digital marksheet is generated through the QR code and in that modification is not possible. And also if someone wants to verify whether the marksheet is genuine or fake then instead of writing applications to Universities and Institutes they just have to scan the QR code.Item Automated attendance management system using face recognition(AIKTC, 2017-05) Khan, Mubashir; Gopale, Apeksha; Chowdhary, Obaid (13CO25); Punjani, Ali Akbar (13CO49); Choudhary, Yasir (13CO24)The main goal and objective of this automated attendance system of face detection and recognition is to present face recognition in real time environment for educational institutes or an organization to see and mark the attendance of their students and employees on a daily basis to keep track of their presence. The system will mark and record the attendance in any environment. This system is purely automated and user can capture video and accordingly attendance will be marked, improving the accuracy to great extent and finally the attendance report will be generated.Item Automated attendance system using face recognition(AIKTC, 2016-05) Khan, Mubashir; Zakariya, Md. Hussian (12CO63); Khan, Suhel (11CO25); Khan, Shoeb (11CO24); Pathan, Nazim (11CO21)The objective of this system is to present an automated system for human face recognition for an organization or institute to mark the attendance of their students or employees. This paper introduces face detection method using the Voila and Jones algorithm and recognition using correlation technique. The system will record the attendance of the students in class room environment. The above system is fully automated and easily deployable. User gets an authentication to upload the image containing file and also to view the attendance.Item Automated Attendance System Using Face Recognition(International Journal of Innovative Research in Computer and Communication Engineering, 2016-04) Khan, Suhel (11CO25); Khan, Shoeb (11CO24); Zakariya, Md. Hussian (12CO63); Pathan, Nazim (11CO21); Khan, Mubashir; Gopale, ApekshaThe objective of this system is to present an automated system for human face recognition for an organization or institute to mark the attendance of their students or employees. This paper introduces face detection method using the Voila and Jones algorithm and recognition using correlation technique. The system will record the attendance of the students in class room environment. The above system is fully automated and easily deployable. User gets an authentication to upload the image containing file and also to view the attendance.Item Detection of retinal blood vessel using deep learning(AIKTC, 2019-05) Khan, Mubashir; Khan, Sahil Jafar [16DCO58]; Ansari, Mohd. Akram Sajid Ahmed [16DCO47]; Shaikh, Mohd. Yusuf Abdul Salam [16DCO76]Traditional Retinal Scans Provides color image of the scan due to which the visibility of the identification eye diseases.Thus in an effort to improve the visibility of scans we presenet our paper making use Neural Networks to get better visibility. The field of Ophthalmology has increasingly turned into medical imaging to play important role in diagnosing diseases. It requires retinal scanned images in identifi- cation of eye diseases. Determining eye disease on the basis of traditional retinal scans can sometimes be difficult due to presence of hemorrhage or thin blood vessels since the image is not very clear. Therefore this paper attempts to improve the quality of retinal scans through im- age segmentation and supervised machine learning algorithms so diagnosis can be as accurate as possible. Keywords: Neural Networks,Opthalmology,Image Segmentation,GAN’s(Generative Adversarial Network.Item Fitness monitoring using machine learning(AIKTC, 2020-05) Khan, Mubashir; Shaikh, Shafaque Naushad (16CO15); Shaikh, Altamas Shakeel (16CO11); Ulde, Fahmi Nisar (16CO17)The enhanced performance of modern Artificial Intelligence algorithms has opened up limitless possibilities in the development of smart systems and devices. One of the most complex tasks for interactive devices is the analysis of human motion. However, using neural networks, movement can be classified and even understood. Our system proposes the use of an enhanced Pose Estimation algorithm[8] and Alternating Least Square(ALS)[4] for developing an application that functions as a personal exercise trainer. As the problem of staying healthy & fit is important as well as considering the use of smartphones, an easy-to-use application is a great solution. This report provide details of this application that offers a full workout program, monitors the user’s workout, and alerts the user when the move is performed incorrectly. Pose estimation detects human figures in images and videos[8].The algorithm is simply estimating where key body joints are and then joining them to know human pose. ALS is Alternating Least Square method for recommendation that we are using in diet and exercise recommendation system after categorising the user[4]. Keywords: BMI Calculation, Diet Recommendation, Exercise Recommendation, ALS, Pose estimation, Machine learning, Body detection, ScheduleItem Fruit sorting and grading based on image processing(2020-05) Khan, Mubashir; Shaikh, Ashraf Tahir Parveen Bano (15CO35); Sayyed, Asim Farooque Najma (16DCO71); Shaikh, Mehvash Samir Fauziya (16DCO75)In recent years, automated machine vision based technology has become more potential and important in many areas like Agricultural Sector and Food Processing Industry. Grading and Sorting of the fruit is one of the most important process, but this procedure is mostly carried out manually which is not efficient as it tends to human error. An automatic fruit quality inspection system helps in speed up the process improve accuracy and efficiency and reduce time. In our project we have two main module, Grading Module and Sorting Module. In Grading process, is carried out by capturing the fruit image using camera and this image is interpreted using image processing various techniques.The Sorting process is done by sorting the fruits based on Color. With the help of this two module we will detect the defected fruits. We will be doing Size detection based on binary image of fruits. The Main aim of the our system is to Sort and Grade the variety of Fruits by using different Image Processing Techniques and also by using Neural Networks(Sequential Neural networks).Image Processing Techniques like converting color image to gray scale image so with the help of thresholding we can get the amount of color the image would be having like RGB color and canny edge detection for detecting the edge of fruits and also neural network that can to changing input; so the network generates the best possible result without needing to redesign the output criteria.with help of this techniques we can make the the sorting and grading process more efficient than the manual work.It will improve the quality as well as it will take less time. Keywords: :Fruits, OpenCV, Contours,Image Processing, Edge Detection,Color Detection, Canny Edge Detection, Neural Network,Camera.Item Geolocation based advance waste collection(AIKTC, 2021-05) Khan, Mubashir; Chogle, Saif Ali Naushad (12CO27); Ansari, Hoida Mohammed Naeem (18DCO02); Lambe, Maaz Muzaffer (18DCO09); Khalfe, Sajjd Mohammed Shoukat (18DCO15)Everyday a huge amount of solid waste generates. It generates from various sources such as from industries, markets, house complexes, etc. This waste also varies in state and shape. As the human involvement is rising in nature, we have seen a rapid growth in solid waste in the world. Due to rise in solid waste, various problems have arisen in society. To control such problems, a proper plan and management of solid waste is needed in society.Due to lack of planning and management of solid waste , huge number of regions have faced problems regarding waste management. The primary aim of sustainable solid waste management is to address concerns related to public health, environmental pollution, land use, resource management and socio-economic impacts associated with improper disposal of waste. To reduce those problems and build a well-defined solid waste management, we have developed a “GEO-LOCATION BASED ADVANCEWASTE COLLECTION” system. This system focuses on optimization of entire solid waste management process. For a specific region or city, garbage bins are set to different locations in that city or respective region. An ultra sonic sensor is attached to every garbage bin. As soon as the garbage gets overflow from bin, this sensor sends a signal to a WiFi module which then send data to web application. Current status of garbage bin is monitored by management personnel. Selection of proper vehicle to collect waste from a site and to dump it on a dumping site is one of the task of the management personnel. The respective vehicle would lift the garbage and dump it on a dumping site through an optimized way. Management personnel can analyse vehicle trip reports for further evaluation. An application has developed for citizens to initiate a complaint regarding waste. They can further track the status of their complaints. This system is economically beneficial to the authorities because of its high efficiency and optimization.Item Image segmentation for MRI brain tumor(AIKTC, 2015-05) Khan, Mubashir; Mapari, Waqas Moinuddin Zaibunnisa (12CO103); Khan, Siddiqa bee Shamsher shenaaz (12CO80); Rajwadkar, Ifrah Ayaz Zaibunnisa (11CO06)The task of detecting the position of tumor (the so called gross tu- mor volume-GT)in the body of the patient is the starting point for a medical treatment. In the conformal radiotherapy the tumor cells are irradiated and killed with high precision without damaging the neighboring healthy tissues. Usually, a medical doctor recognizes the GTV and designs its border lines manually on the computer tomography slices (CT-SCAN).The CT-SCAN procedure affects the consequence planning target volume (PTV) of irradiation, ei- ther if it is decided by the same medical doctor or by the automatic supporting system. The main objective of this study is to design a computer system able to detect the presence of a tumor in the digital images of the brain and to accurately define is border line. The basic assumption is that different local textures in images can describe different physical characteristics corresponding to differ- ent objects. We will be using this in wide range of field such as Bio medical informatics, Oceanography, Computer vision. We assume that the local texture of tumor cells is highly different from local texture of other biological tissues. Thus texture measurement in the image could be part of an effective discrimination technique between healthy tissues and possible tumor areas. A computer system has been design to recognize the typical fea- 1 tures of the tumor from the digital images of the brain. The basic concept is that local texture in the images can reveal the typical regularities of the biological structures. Thus, the textual features have been extracted using a co-occurrence matrix approach. The level of recognition, among three possible types of image areas are: tumor, non tumor, non tumor and back ground. We are focus- ing on tumor image segmentation .Item Image sorting using object detection and face recognition(AIKTC, 2020-05) Khan, Mubashir; Shaikh, Rehan (16CO52); Shaikh, Arbaz (16CO54); Shaikh, Sohail (16CO57)The requirement of the user is to quickly organize their images while doing little work. To achieve this we have implemented image sorting and grouping using three techniques; Object detection, face recognition and face detection. Face detection is acheived using Haar cascade classifier, whereas face recognition is done using LBPH algorithm. Object detection uses a deep learning method called as YOLO algorithm. Keywords: Adaboost, Machine learning, Deep learning, Categorize, Object detection, Face detection, Face recognition, Convolution Neural Network(CNN).Item Image stitching algorithm based on feature extraction(AIKTC, 2015-05) Khan, Mubashir; Ansari, Mohd Manzoor Maqsood Rehana (12CO65)This paper proposes a novel edge-based stitching method to detect moving objects and construct mosaics from images. The method is a coarse-to-fine scheme which first estimates a good initialization of camera parameters with two complementary methods and then refines the solution through an optimization process. The two complementary methods are the edge alignment and correspondence-based approaches, respectively. The edge alignment method estimates desired image translations by checking the consistencies of edge positions between images. This method has better capabilities to overcome larger displacements and lighting variations between images. The correspondence-based approach estimates desired parameters from a set of correspondences by using a new feature extraction scheme and a new correspondence building method. The method can solve more general camera motions than the edge alignment method. Since these two methods are complementary to each other, the desired initial estimate can be obtained more robustly. After that, a Monte-Carlo style method is then proposed for integrating these two methods together. In this approach, a grid partition scheme is proposed to increase the accuracy of each try for finding the correct parameters. After that, an optimization process is then applied to refine the above initial parameters. Different from other optimization methods minimizing errors on the whole images, the proposed scheme minimizes errors only on positions of features points. Since the found initialization is very close to the exact solution and only errors on feature positions are considered, the optimization process can be achieved very quickly. Experimental results are provided to verify the superiority of the proposed method.Item Poster Recognition With Calender Integraion(AIKTC, 2016-05) Khan, MubashirText characters and strings in natural scene can provide valuable information for many applications. Extracting text directly from natural scene images or videos is a challenging task because of diverse text patterns and variant background interferences.This paper proposes a method of scene text recogntion from detected text regions. The proposed method combines previously scene text detection and scene text detection algorithms. Besides,previous work rarely presents the mobile implementation of scene text extraction,and we transplant our method into an Android based platform.Our proposed system will have an android application that will capture an image as an input and will process that image to extract text from it. Firtly we are extracting the event name,event date from the image of poster. Secondly by using the extracted date,reminder of the day before of event is set in the smartphone.Item SignTalk and animator for speech and hearing imapaired(AIKTC, 2017-05) Khan, Mubashir; Shaikh, Abdus Salam; Shaikh, Ruba (13CO12); Siddiqui, Sayma (13CO14); Biya, Haseeb (13CO21); Khot, Sufiyan (12CO41)Communication is basic fundamental human right, however who are deaf and mute communicate differently than everyone else using Sign Language (SL), while we communicate verbally. This puts them at disadvantage. Our system will help them better communicate with rest of the world without changing how they already interact with each other. The system, SignTalk i.e. Hand gloves will translate sign language to voice. Flex sensors, accelerometer, gyroscope, are placed on hand gloves to capture hand movements. Arduino Nano recognizes these signals and sends it to smart phone via Bluetooth for voice generation. Animator is an android application that takes text sentences as input and converts it to 2D animations for facilitating two way communication.Item Smart class: An extension to smart lecture delivery system(AIKTC, 2017-05) Khan, Mubashir; Jamkhandikar, Irfan; Shaikh, Yusuf (13CO54); Gharade, Abdul Mueed (13CO28); Choudhary, Haider (13CO23); Ansari, Ziauddin (13CO18)This Project illustrates extension to the Smart Lecture Delivery System. For this project, we have used a credit card sized, mini board computer called Raspberry Pi. A general working about the project, a camera module of RPi is used for recording video feed, a wired microphone is used for taking sound input. Recorded video are processed in Raspberry Pi and uploaded on a local server. Video recording is handled by the faculty through an VNC client application. After completion, the video is uploaded automatically on the server. All videos are uploaded through FTP protocol into a local Server and entry is added to the database. Student can access these video lectures according to his/her convenience from an android application or a website. With some modifications, it can also be used to monitor the behaviour of the student in the class and used to control any misconduct happening in the class.Item Smart greenhouse system based on IoT(AIKTC, 2018-05) Khan, Mubashir; Pawle, Musa A. (14DCO60); Peerzade, Nilofer (14DCO62); Thakur, Atif U. (14DCO69); Gigani, Meenaz (15DCO47)Today, convection agricultural is now improving to emphasise the productivity of the field. The agriculture, production becomes nowadays important in two terms quality and quantity. Under the Bureau of Indian Standards IS 15930(Part 1): 2010 requirements for good agricultural practices have been prescribed. From the research work of Mr S.K. Jadhav el at 2016, information like crop period, whether pruning is the foundation or forward pruning and appearance of infection of downy mildew etc, his team suggests various preventive measures and different pesticide treatments[5]. They conclude that the knowledge-based system will be helpful to an agricultural professional to take decision-related to the management of crop. Today‘s scenario was facing the problem of less space and more output. Overall expenditure of agricultural field reduced to half of its value. Use IOT based smart agricultural system give new research area in field. India’s food deficient was changed to leading agricultural status. 21st-century the market is facing the main problem of “smart customer”. In this plight, technology is playing a vital role to uplift the agricultural production. Due to boom explosion in population, there is a vast improvement in agricultural machines over last century. As humans are making more relevant them self with monitoring systems, GPS locators, maps and an electronic sensor, these technologies start taking the stand in the agricultural field. Agricultural engineers work on planning, supervising, and managing the building of dairy effluent schemes, irrigation, drainage, and flood and water control systems. They aim to conserve soil and water and to improve the processing of agricultural products. In this paper, there is a survey on the technical aspect of agriculture.Item Smart greenhouse system based on IoT(AIKTC, 2018-05) Khan, Mubashir; Pawle, Musa A (14DCO60); Peerzade, Nilofer (14DCO62); Thakur, Atif U (14DCO69); Gigani, Meenaz (15DCO47)Today, convection agricultural is now improving to emphasise the productivity of the field. The agriculture, production becomes nowadays important in two terms quality and quantity. Under the Bureau of Indian Standards IS 15930(Part 1): 2010 requirements for good agricultural practices have been prescribed. From the research work of Mr S.K. Jadhav el at 2016, information like crop period, whether pruning is the foundation or forward pruning and appearance of infection of downy mildew etc, his team suggests various preventive measures and different pesticide treatments[5]. They conclude that the knowledge-based system will be helpful to an agricultural professional to take decision-related to the management of crop. Today‘s scenario was facing the problem of less space and more output. Overall expenditure of agricultural field reduced to half of its value. Use IOT based smart agricultural system give new research area in field. India’s food deficient was changed to leading agricultural status. 21st-century the market is facing the main problem of “smart customer”. In this plight, technology is playing a vital role to uplift the agricultural production. Due to boom explosion in population, there is a vast improvement in agricultural machines over last century. As humans are making more relevant them self with monitoring systems, GPS locators, maps and an electronic sensor, these technologies start taking the stand in the agricultural field. Agricultural engineers work on planning, supervising, and managing the building of dairy effluent schemes, irrigation, drainage, and flood and water control systems. They aim to conserve soil and water and to improve the processing of agricultural products. In this paper, there is a survey on the technical aspect of agriculture.Item Violence detection system(AIKTC, 2019-05) Khan, Mubashir; Sayed, Najneen Fatma Mustaq Ali [15CO07]; Kothari, Hozefa Abbas [15CO24]; Chougle, Zaid Noornabi [15CO15]As action recognition problem is becoming a hot topic within computer vision, the detection of fights or in general aggressive behavior has been comparatively less studied. Such capability may be extremely useful in some video surveillance scenarios like in prisons, psychiatric centers or even embedded in camera phones Our System will be capable enough to detect aggressive behavior in a fight and various objects used in it. It will be using various computer vision technique and deep neural network to detect and recognize objects and actions in the violent outbreak. Our System is mainly dependent on how the model is trained and how good the quality of CCTV camera is, as we will be doing the processing on CCTV feed Keywords: Computer-vision, neural network, violent outbreak, action recognition, object detection, Keras, Numpy, Tensorflow, surveillance video, HMM(Hidden Markov Model)