Pinned Repositories
Action-Classification-using-RNN
Using Recurrent neural networks (RNNs) to classify human actions.
Auto-Scaling-of-Application-Servers
This project demonstrates the automatic spawning of an application server (Upscaling) in cases of consistent heavy server load (eg: Heavy load on Amazon servers during festives seasons and flash sale)
Binary-Segmentation
An interactive semi-automatic binary segmentation model. Implemented in OpenCV 3.3.0 and Python 2.7
DriverDrowsiness_Detection
This is a project implementing Computer Vision and Deep Learning concepts to detect drowsiness of a driver and sound an alarm if drowsy.
Face-Detection-and-Tracking
Computer Vision model to detect face in the first frame of a video and to continue tracking it in the rest of the video. This is implemented in OpenCV 3.3.0 and Python 2.7
GAN
Using Generative Adversarial Networks (GAN) to generate MNIST image data.
Image-Alignment-and-Panoramas
Stitching different perspective images into a single smooth panorama using Laplacian Blending.
NLP
A collection of Natural Language Processing projects
Question-Answering-QANet
Support-Vector-Machine
An implementation of MultiClass Support Vector Machine from scratch using Stochastic Gradient Descent and Quadratic Programming. Used this for Object Detection.
TejasNaikk's Repositories
TejasNaikk/Image-Alignment-and-Panoramas
Stitching different perspective images into a single smooth panorama using Laplacian Blending.
TejasNaikk/DriverDrowsiness_Detection
This is a project implementing Computer Vision and Deep Learning concepts to detect drowsiness of a driver and sound an alarm if drowsy.
TejasNaikk/Binary-Segmentation
An interactive semi-automatic binary segmentation model. Implemented in OpenCV 3.3.0 and Python 2.7
TejasNaikk/Face-Detection-and-Tracking
Computer Vision model to detect face in the first frame of a video and to continue tracking it in the rest of the video. This is implemented in OpenCV 3.3.0 and Python 2.7
TejasNaikk/Action-Classification-using-RNN
Using Recurrent neural networks (RNNs) to classify human actions.
TejasNaikk/Auto-Scaling-of-Application-Servers
This project demonstrates the automatic spawning of an application server (Upscaling) in cases of consistent heavy server load (eg: Heavy load on Amazon servers during festives seasons and flash sale)
TejasNaikk/GAN
Using Generative Adversarial Networks (GAN) to generate MNIST image data.
TejasNaikk/NLP
A collection of Natural Language Processing projects
TejasNaikk/Question-Answering-QANet
TejasNaikk/Support-Vector-Machine
An implementation of MultiClass Support Vector Machine from scratch using Stochastic Gradient Descent and Quadratic Programming. Used this for Object Detection.
TejasNaikk/Action-Recognition-with-CNN
Training a CNN using 3D convolution to classify each clip as a video into action classes.
TejasNaikk/DrowsyDriverDetection
This is a project implementing Computer Vision and Deep Learning concepts to detect drowsiness of a driver and sound an alarm if drowsy.
TejasNaikk/GolombRuler
This project implements Constraint Satisfaction Problem (CSPs). Plain Backtracking, Backtracking + Forward Checking are used to solve CSPs.
TejasNaikk/GSoC18
Google Summer of Code'18. Open Food Facts : Brands/Label Detection.
TejasNaikk/Histograms-Filters-and-Blending
Implementing histogram equalization, low-pass and high-pass filter, and laplacian blending of images.
TejasNaikk/IOTbasedSmartHomes
This project is a seminar on "IOT based user-centric ecosystem for heterogeneous smart home environments".
TejasNaikk/LASSO-Regression
LASSO (Least Absolute Shrinkage Selector Operator) is Linear Regression with L1 Regularization.
TejasNaikk/MachineLearning
Andrew Ng's Machine Learning course assignments and mini-projects
TejasNaikk/MultiAgentPacman
Mini-max, Alpha-Beta pruning, Expectimax techniques are used to implement multi-agent pacman adversarial search.
TejasNaikk/Resume
Resume
TejasNaikk/SearchingPacman
A project that applies several Artificial Intelligence techniques such as informed state space search, reinforcement learning and probabilistic inference. Algorithms such as Depth First Search, Breadth First Search, Uniform Cost Search, A-star Search enabled the pacman to win in different game versions