Winning interactivity using computer vision
Tags: computer-vision, pose-estimation, deep learning, deployment
In this article, We explain some of the ways how Computer Vision is being used at cult.fit to make workouts and user experience fun and interactive.
The Why and the How of Deep Metric Learning
Tags: deep Learning, mathematics, algorithm, metrics
This article provides insights into the very basics of Deep Metric learning methods and how it helps in achieving state-of-the-art results for tasks like face verification and face recognition. Besides Face Recognition, Verification there are a number of other applications where Deep Metric Learning has proven to be quite effective.
Generating authentic product shadows using Image Processing
Tags: Image Processing, Affine Transformations, OpenCV
In this article, I talk about a simple yet effective and novel algorithm I developed, named Shadowfier, for generating product shadows in an image using image processing. This technique improves the visual appeal of product images by crafting high-quality shadows.
Constrained Optimization demystified
Tags: optimization, mathematics, algorithm
In this article, I have shown how the refashioning of simple unconstrained Optimization techniques leads to a hybrid algorithm for constrained optimization problems. I have shown the robustness of the algorithm through a detailed analysis of a problem set by comparing the results with some of the inbuilt functions in Python.
Vision-Based Rep Counting in the Wild
Tags: computer-vision, signal-processing, pose-estimation, algorithm
In this article, I try to explain my exploration of different vision-based repetition counting techniques and discuss their pros and cons. Specifically, I highlight five major ways in which computer vision has been employed for rep counting.
Towards a more applicative Pose Estimation
Tags: computer-vision, pose-estimation, low-pass-filter
In this blog, I talk about making the pose estimation algorithms more effective by highlighting a key issue during inference and discuss ways to mitigate this issue. I also walk through an example where pose estimation is made more applicative by implementing the same in python.
Building an exercise rep-counter using ideas from signal processing
Tags: computer-vision, signal-processing, pose-estimation, algorithm
In this blog post, I discuss a very new and unique approach for building a real-time exercise rep counter, one that employs signal processing ideas on top of pose estimation. This approach can be easily adapted to build rep-counters for other classes.
Color Swapping techniques in Image Processing
Tags: image-processing, color-spaces, algorithm
In this article, I try to explain my exploration of why there can be a need to swap colors in images and how we can use simple image processing methods to smartly swap colors in an image by implementing the same in Python.
Understanding the crux of objects and classes in python
Tags: OOPs, inheritance, python
In this article, I try to explain the essentials of Object-Oriented Programming in my own understanding via a conversation that took place between me and my friend Nitin.
14 Probability problems for acing Data Science interviews
Tags: probability, statistics, interviews, data science
Questions on probability are very common in any Data Science interview. The questions might be challenging (and tricky) but are easily tractable if you have some practice and know basic formulas and concepts. In this blog, I share some practice questions (with solutions) on different concepts in probability.
Understanding the nuts and bolts of a RESTful API
Tags: API, CRUD, REST, client, server
In this article, I introduced the key concepts related to an API and thoroughly discussed what is an API and the fundamentals of the web. Then showed how to go on to build a RESTful API using Typescript and Express. It’s a beginner-friendly post and even if you don't know Typescript, I think you will enjoy learning the fundamentals.