Tools and Frameworks I love to work with:
This project can take input images and store them as a numpy file. The test Algorithm forms different clusters based on photos of various people and when a test image is served, the algorithm uses KNN to classify it. SVM (with kernels) and CNN can also be used for classification.
Currently, I am also doing research project on topics like Effects of Image processing and GAN's on real time Face recognition (Large number of Subjects, Low Per subject Data) using Deep CNN and its deployment on Edge devices.
GANs are a clever way of training a generative model by framing the problem as a supervised learning problem with two sub-models: the generator model that we train to generate new examples, and the discriminator model that tries to classify examples as either real (from the domain) or fake (generated). The two models are trained together in a zero-sum game, adversarial, until the discriminator model is fooled about half the time, meaning the generator model is generating plausible examples.
I have worked with GAN on many datasets like MNIST, Pokemon, Anime, LFW, ORL etc.
Image caption generator is a task that involves computer vision and natural language processing concepts to recognize the context of an image and describe them in a natural language like English.
DCNN and LSTM are used for image analysis and caption generation respectively.
In order to reduce pressure on Doctors, this application which is a part of COVID DOCTOR that helps people to recognise the possibility of COVID-19 infection by analysing their X-Ray. In addition to COVID-19 virus, this application also classifies few other types of flu. The model is more than 95% accurate
Drop me a mail, if you need help with some project or want to collaborate/ communicate with meCLICK TO MAIL