kunal30 Goto Github PK

arduino

ESP8266 core for Arduino

camerahack

cloud-computing

cloudsink

cosmosqa-research

depth-recovery-computer-vision

document-clustering-and-visualization

documentclustering-visualization

dth-database-management-system

A simple DTH Database Management System on postGRESQL server

feature-learning-for-disease-classification

fundamentals-of-statistical-learning

Includes the project of Binary Neural Networks

geospatial-data-analysis-using-spark-sql

gesture-recognition

Recognize gestures using a simple webcam.

image-search-engine

Image search using advanced algorithms like LSH, relevance feedback, etc.

image-super-resolution-using-deep-learning

We improve the image quality by increasing the resolution as well as the details using Convolutional Neural Networks. We achieve magnification of 2x, 4x and 8x by recycling the same network. We further achieve better quality by including regularization parameter of a smoothness prior in the loss function of the CNN architecture.

in-out-painting

information-retrieval-project

Query Drift Prevention for Robust Query Expansion: Query Drift Prevention for Robust Query Expansion ABSTRACT The automatic query expansion retrieval based on pseudo- relevance feedback(also known as the blind-relevance feed- back) performs effectively on average, but the performance is inferior to that of using the original query for many infor- mation needs. Further, the average precision(MAP) score for a query, dwindles on using the query expansion based on pseudo-relevance feedback. The important cause for this ro- bustness decrease(the plummeting MAP score for a query), that is, the query drift problem, would be attempted to be solved. The method used to ameliorate the query drift prob- lem, is by the fusion of the results retrieved in response to the original query and to its expanded form. This fusion- based approach produces a retrieval performance, which is better than that of retrieval based only on the original query and a more robust performance(the improvement in the av- erage precision per query) than that of retrieval using the expanded query.

multithreaded-client-server-chat-application

non-intrusive-attendance-marking-system-using-ai

The project that we worked on this summer internship falls in the domain of research in IoT (Internet of Things). Initially, the mentor asked us to find real-life problems, which we would attempt to solve by using the tools of Information Technology. We were allowed to discuss and work in a group of three. We picked the problem of devising an attendance monitoring system, which would mark the presence of the students in a big room, in a non-intrusive manner using image recognition, for e.g. an auditorium or our college’s lecture theatre. Our project was divided into two phases, which would be illustrated in the subsequent passages. The first phase involved doing a literature survey on the tools and technologies through various authentic research papers and the existing libraries, which would enable us to devise a backend structure for our project. We, then developed a flowchart, which comprised of two modules of processes, through which the procedure would pass through. The first module involves the initial training of a machine learning based classifier by training it with the various images of a specific person. The second module involves the testing part in the real environment, which involves face detection and face recognition. A camera would take the frames/image of a live audience. Then, these frames would be pre-processed (involves grey-scaling and image resizing) for achieving better performance in the subsequent face detection module. The face-detection algorithm would detect all the faces present in the frame, and would crop the detected faces, and would pass them to the face recognition classifier for testing. The classifier would classify the cropped images and would mark the attendance accordingly. The libraries used for face-detection were that of OpenCV, and a convolutional neural network was trained for the image recognition part. The libraries which were used for training the convolutional neural network was Keras. The second phase involved the implementation part, where we had to gather the data for training the neural network, and find out the parameters of the image, for which we are getting better accuracy performance. We trained the neural network with the images of about 64 students, with about 20 images per student, covering different angles and brightness levels. We trained the network with 70 percent of the image corpus, and used the remaining 30 percent for testing. We got an accuracy of 93 percent. For testing the face detection part, we took a video of a classroom of about 40 students. Then, we generated frames from the video and passed it to the face detection algorithm. We extrapolated that the accuracy of an individual frame was not that high, but if we consider all the detected members in all the frames, we are covering almost every student. Hence, considering multiple frames for testing is crucial to get a high detection accuracy. We are currently trying to figure out the camera and its mounting position, which would be conducive for the algorithm, to give us accurate results.

profile_webpage

profile_webpage_simple

programming-archives

raspberry-pi-powered-cctv-security-system

This project implements the Raspberry Pi CCTV surveillance system with the additional feature of Saving the Video in a read/write ­able format.The camera module utilised in this project is manufactured and distributed by Raspberry Pi Foundation connected to the Raspberry Pi Board. The WiFi USB Adapter is attached to this system for the wireless transmission of data from the CCTV to the shared memory folder for remote monitoring purpose. Purpose behind this project : Raspberry Pi CCTV with the integration of Raspberry Pi Camera Module is a very economically viable and true to it’s standard, surveillance system which can easily replace the bulky CCTV surveillance systems which costs high. Raspberry Pi can be widely customised and is thus very flexible. From HD surveillance to motion­detect features, the system is light in hardware and can be made undetectable without lowering its power which gives high security and safety by providing video streams from the camera. Raspberry Pi with the Raspbian Operating System helps in building the CCTV system in a user friendly process. The wireless video storage capability using the WiFi USB Adapter appends to the benefit of saving the video from the Camera to any memory storage disk or SD cards which makes it highly portable. The video saving capability helps the user to keep a check on the property as well as help him take precautions by analysing the data.

resume-parser

A python program to extract data from a resume

semantic-web-mining

shape-from-shading-computer-vision-

social-media-mining-and-analysis

statistical-machine-learning

traffic-pollution-monitoring-and-prediction-system-iot

Vehicular pollution has a major role in degrading the environmental system. The level of traffic pollution has increased with time due to a lot of factors like the increase in population, increased vehicle use etc. which results in harmful effects on human beings by directly affecting health of population. In this project, we focus on traffic pollution monitoring. Every vehicle has a standard of emission of gases, but the difficulty occurs when the emission is beyond the standardized values. This emission from vehicles cannot be completely avoided, but it can be definitely controlled. The aim of our project will be to monitor the pollutants at traffic signals using the pollution detection circuit. This pollution detection circuit will consist of various sensors like gas sensor(CO), temperature sensor, humidity sensor etc. and are connected to a Microcontroller(Arduino) which gives us various environmental data. The data collected by the detection circuit is sent via a wifi module to a web-server, from where it is used for various analytical purposes which gives us qualitative data about pollution.

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.