Thumbnail Image

Theses

Browse

2020 - 20215
Reset filters
Subject: Information Technology × End date: 2021 × Start date: 2020 × Type: Thesis × Thesis Type: M.Tech. ×
Reset filters

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    ThesisItemOpen Access
    Kidney stone detection from ultrasound images using masking techniques
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-12) Chaudhary, Harshita; Pandey, Binay Kumar
    Here we are using masking techniques for stone detection that are present in the kidney. As we know Masking techniques are conspicuous approaches in contrast enhancement. For this firstly, the image is converted into grey and after that contrast of the image is enhanced. The process of contrast enhancement is done with the help of Optimum Wavelet-Based Masking (OWBM) using the Enhanced Cuckoo Search Algorith (ECSA). Afterward image segmentation and image masking have been done to detect stone from the image. The cuckoo search algorithm is used for global optimization of contrast enhancement. With the help of the Cuckoo search algorithm approximation of the coefficient has been optimized. The objective of this project is to design and implement a method to detect the presence of stone from the ultrasound image of a kidney. Here we are making are system our more intelligent.
  • Thumbnail Image
    ThesisItemOpen Access
    IoT based surveillance system using DNN
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-12) Rawat, Rahul; Srivastava, Ratnesh Prasad
    Localization, Visibility, Proximity, Detection, Recognition has always been a challenge for surveillance system. These challenges can be felt in the industries where surveillance systems are used like armed forces, technical-agriculture and other such fields. A way to get the ease of mind would be installing a security camera. Most of the smart system available are just for the surveillance of human intervention but there is a need for a system which can be used for animals as well because with the outburst of human population and symbiotic relationship with wild animals results in life loss and damage to agriculture. There are many electrical equipment’s available for home which can do the monitoring from a remote area all at a time. In this paper we are designing to overcome these above-mentioned challenges for human and animal-based surveillance system in real time application. The system setup is done on a Raspberry pi integrated with deep-learning models which performs the classification of objects on the frames, then the classified objects is given to a face detection model for further processing. The detected face is relayed to the back-end for feature mapping with the saved log files with containing features of familiar face IDs. Four models were tested for face detection out of which the DNN model performed the best giving an accuracy of 87.88%. The system is also able to send alerts to the admin if any threat is detected with the help of a communication module.
  • Thumbnail Image
    ThesisItemOpen Access
    Detection of Ransomware using machine learning
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-02) Pujari, Shivam Kumar; Mandoria, H.L.
    Today’s world depends on the cyber world, since it is very useful for collecting information, data and transporting them. Since anyone can use it, for security purpose of data a technique called encryption is made. Unfortunately, this strong technique of encryption for security is also useful for hackers to lock any file or system by encryption by infecting malware. This type of malware which encrypt data is called Ransomware. In the digital world there are various types of attacks for a different aspect of motive such as economic benefits, personal issues, religious issues, political benefits, or special propaganda, etc. Ransomware attacks are for financial benefits and most popular in today's world. We purpose a method in which we can classify and detect ransomware and some other malware also
  • Thumbnail Image
    ThesisItemOpen Access
    A comparative study of edge detection techniques on different images using Scilab
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-01) Rajshree Kumari; Ashok Kumar
    In the field of image processing, edge detection plays a significant role in recent years to detect images more accurately, for this purpose it is important to choose the edge detection techniques wisely and correctly based on their properties. Therefore this work aims to give a comparative study of different edge detection technique using some parameters to check which techniques gives more accurate result with some parameters. The aim of this research is to study different edge detection to detect edges under different circumstances. In this research we have proposed a comparative study between the three-edge detection techniques Canny, Sobel, and Prewitt, using different types of images under different parameters for analysis. The software tool that we have used here is Scilab which is an open source tool and an alternative to MATLAB. This study is tested by conducting experiments on the WANG image dataset and benchmark standard images. The results of this comparative studyz suggest that Prewitt works better than other edge detections with greater accuracy under certain parameters and in different image types.
  • Thumbnail Image
    ThesisItemOpen Access
    Deep learning based approach for vehicle license plate recognition
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2020-11) Gupta, Shally; Singh, Rajesh S.
    In the field of Number Plate Recognition System Artificial Intelligence and Deep Learning have played a crucial role in recent years. Therefore this work aims to establish a model of plate detection with the aid of Deep Learning. It gives us an idea of the method of object detection which gives the utmost precision. The aim of this research is to extract accurate precise and optimize the number plate image recognition as compared to the previous research work done. It is therefore necessary to implement the ANPR system model based on an effective Deep Learning algorithms. An effective License Plate Recognition System is needed to ensure the successful functioning of intelligent transportation system. During the last few years, several methods of image processing such as OpenCV have been developed. These have not been exploited in the previous researches on number plate detection. Our study is based on Image Segmentation using object detection algorithm through YOLO (You Only Look Once) object detection technique in darkflow framework and character recognition based on Convolutional Neural Network (CNN). YOLO and CNN have proved to be the most productive techniques for several supervised and unsupervised learning tasks. In this research, we study deep learning algorithms and compare their performance. We have used custom dataset to for image segmentation and character recognition. Different categories of models for object detection is classified by performing segmentation using annotated images for detecting license plates by YOLO. Further, for recognizing characters, single character recognition using CNN is used and also trained a model as a base learners. Finally, compared the performance of the model by previous research for plate detection and have drawn useful conclusions. The result shows that Deep Learning algorithms outperform with high accuracy as compared to other image processing techniques.