There are no reviews yet. Be the first to send feedback to the community and the maintainers!
HumanDetectionAndCounting
3D-HumanPoseEstimation
-Implementation-of-a-Visible-and-Invisible-Video-Watermarking-Technique
Although tremendous progress has been made in the past years on video watermarking, there still exist a number of problems. We believe that the most important one is related to the compression rates, robustness against attacks and high security for privacy data. In digital image processing domain “achieving better compression rates in dual digital watermarking” is still area of concern. The proposed work shows the embedding of visible and invisible watermark during compression on the video encoder and the respective embedding approach on the video is termed as optimized compression/watermarking algorithm and system. The performance of the video watermarking is better when the complexity is low and this low complexity is achieved in our proposed work by discrete cosine transform (DCT). Finally, the results show the high correlation against different attacks in the extraction section. The proposed algorithm is more successful in order to overcome, the conventional algorithm drawbacks and more suitable to applied in the real time applications.ShaminiKoravuna
Advanced_Computer_Vision
python_projects
Real world applications of pythonClassification_of_Car_Brand
Fake_News_Classifier
Computer_Vision_Projects
GeneratingImageCaptions-DL
ShaminiKoravuna.github.io
prusa-i3-3d-printer
German_Traffic_Signs_Recognition
ImageSegmentationUsingMachineLearning
Sentiment_Analysis_Deployment
Built and deployed a deep learning model that predicts the sentiment of a user-provided movie review using Amazon SageMaker. In addition, created a simple web app that uses the deployed model and accepts user input.Plagiarism_Detector
Used advanced machine learning skills to define similarity metrics between two text documents and identified cases of plagiarism. Performed feature engineering and trained and deployed a custom, plagiarism-classification model using Amazon SageMaker. Implemented this project as a part of the Udacity Machine Learning Engineer Nanodegree Program.DriversDrowsinessDetection
Dog-Breed-Classifier
Machine Learning Engineer Nanodegree Udacity Capstone Project. This project shows how to build a pipeline that can be used within a web or mobile app to process real-world, user-supplied images. Given an image of a dog, the algorithm identifies an estimate of the canine’s breed. If supplied an image of a human, the resembling dog breed is shown.Love Open Source and this site? Check out how you can help us