Diwas Pandey's Projects
A day to day plan for this challenge. Covers both theoritical and practical aspects
Solid waste management project @ Advanced College of Engineering
In this project we have used BOTO3 (especially detect_faces()) to find gender, age, emotions and appearance from image. Under AWS Rekognition, there are various methods.
FastAPI is an excellent tool for putting your machine learning models into production. In this article, I briefly explain how you can easily put your FastAPI in production to an AWS EC2 instance using Nginx.
A curated list of awesome computer vision resources
Today we are going to build a Temperature conversion bot using Lex & Lambda. Using this bot we will be converting Celsius to Kelvin, Celsius to Farenheit & Vice-versa
The purpose of our project is to develop a system that can automatically detect cancer from the blood cell images. This system uses a convolution network that inputs a blood cell images and outputs whether the cell is infected with cancer or not.
Real Time Number Plate Recognition System is an image processing technology which uses number (license) plate to identify the vehicle. The objective is to design an efficient automatic authorized vehicle identification system by using the vehicle number plate. Number plate recognition (NPR) can be used in various fields such as vehicle tracking, traffic monitoring, automatic payment of tolls on highways or bridges, surveillance systems, tolls collection points, and parking management systems.
We are using PIL to resize the images thereby converting larger images to smaller ones.The optimize flag will do an extra pass on the image to find a way to reduce its size as much as possible.
The first 6 layers of convolution network are convolution layer. First 2 convolution layer applies 16 of 33 filters to an image in the layer. The other two layer applies 32 of 33 filters to an image.
As the collected citizenships were in pdf format, they were converted into JPG images using python script.
The Credit Card Fraud Detection project is used to identify whether a new transaction is fraudulent or not by modeling past credit card transactions with the knowledge of the ones that turned out to be fraud. We will use various predictive models to see how accurate they are in detecting whether a transaction is a normal payment or a fraud.
To conduct grouping, the KNN algorithm uses a very basic method to perform classification. When a new example is tested, it searches at the training data and seeks the k training examples which are similar to the new test example. It then assigns to the test example of the most similar class label.
Cheat Sheets
Hello everyone !! Welcome to the most awaited tutorial on deploying AI ML projects on Heroku using flask.
We will use a pre-trained Haar Cascade model to detect faces from the image. x,y are pixel location of faces, w,h are width and height of faces. We will crop face using these pixel co-ordinates
In the beginning, the algorithm chooses k centroids in the dataset randomly after shuffling the data. Then it calculates the distance of each point to each centroid using the euclidean distance calculation method.
detail about me !! contents to show on github profile
A list of all public EEG-datasets
Information exchange has always been an important aspect of our lives, and with the rapid advancement of information and communication technology, communication and information exchange have become much easier and faster, but data security and privacy have become a major concern for us. Cryptography and Steganography are two popular data hiding practices that also can be combined to enhance data security. Because of recent advancements in steganalysis, one can easily reveal the existence of secreted information in carrier files. So this project aims to introduce a new method of steganography for communication between two private parties. We used a merged technique for data security that employs both cryptography and steganography techniques to enhance information security. In cryptography, we are using the RSA algorithm for the process of key generation and information encryption decryption. And in Steganography we are using Image Steganography for hiding the encrypted data. Image Steganography refers to the technique of hiding the presence of data within an image file, whereas cryptography is related to the act of transforming plain text into incomprehensible text and vice versa. Cryptography guarantees privacy whereas Steganography guarantees secrecy. We have also used base 64 and SHA-256, which is a patented cryptographic hash function. We are hiding the encrypted data in a distinct image file to securely send over the network without any suspicion of the data being hidden. Such that any other person in the network cannot access the data present in the network. Only the sender and receiver can retrieve the message from the data.
GAN, from the field of unsupervised learning, was first reported on in 2014 from Ian Goodfellow and others in Yoshua Bengioβs lab. Generative Adversarial Network is composed of two neural networks, a generator G and a discriminator D.
This project is an amazing blend of Computer vision and Video Game. In simple words I can say move you finger in front of camera and just drive the car to surpass the obstacles.
monis vai ko project
Project for Computer Graphics which includes penalty game.
When scanning a document, a slight skew gets into the scanned image. If you are using the scanned image to extract information from it, detecting and correcting skew is crucial.