Blog

Semantic segmentation refers to the process of linking each pixel in an image to a class label. These labels could include a person, car, flower, piece of furniture, etc., just to mention a few.

We can think of semantic segmentation as image classification at a pixel level. For example, in an image that has many cars, segmentation will label all the objects as car objects. However, a separate class of models known as instance segmentation is able to label the separate instances where an object appears in an image. This kind of segmentation can be very useful in applications that are used to count the number of objects, such as counting the amount of foot traffic in a mall.

Continue reading A 2019 Guide to Semantic Segmentation

This tutorial guides Android developers in preparing the popular library OpenCV (Open Computer Vision) for use. Through a step-by-step guide, the library will be imported into Android Studio (the official IDE for Android).

Upon installation and setup, OpenCV can be used for performing any of the operations it supports, such as object detection, segmentation, tracking, and more.

Continue reading A Guide to Preparing OpenCV for Android

Position Map Regression Networks (PRN) is a method to jointly regress dense alignment and 3D face shape in an end-to-end manner. In this article, I’ll provide a short explanation and discuss its applications in computer vision.

Continue reading 3D Face Reconstruction with Position Map Regression Networks

According to Snapchat’s founders, the smartphone camera has always been at the heart of their app. Over the years, Snapchat has evolved to do much more to your photos than simple image and video messaging.

This giant social media platform is most popular among young people, and the main reason for this is its amazing photo/video editing tools and a wide variety of available camera filters.

Continue reading Creating Snapchat Augmented Reality Lenses in Lens Studio—A Beginner’s Guide

I was inspired by this example of Core ML + ARKit. But I found one significant disadvantage — it doesn’t place annotations on objects automatically. Instead, you need to center the object in your camera view and use your finger to place an annotation.

In my opinion, this destroys user expectations, so I decided to fix that and build a more immersive user experience using object detection in augmented reality.

Continue reading Core ML + ARKit: Annotating Objects in Augmented Reality

One of the most popular languages in the data science and machine learning world is Python, and most Python tasks usually involve at least 5 packages that need to be installed. However, these packages typically have their own dependency packages for them to function well. And some of these dependency packages must be in a specific version. This is where a Python virtual environment comes into play.

Continue reading Creating Python Virtual Environments with Conda: Why and How

It doesn’t matter whether you’re a student, a researcher, a data scientist, a machine learning engineer, or just a machine learning enthusiast, you’re surely going to find PyTorch very useful.

As you might be aware, PyTorch is an open source machine learning library used primarily for applications such as computer vision and natural language processing.

Continue reading 10 reasons why PyTorch is the deep learning framework of the future

Hello seekers! In this post (part 2 of our short series — you can find part 1 here), I’ll explain how to implement an image segmentation model with code. This model will allow us to change the background of any image, just by using the API that we’ll build.

Continue reading Changing Backgrounds with Image Segmentation & Deep Learning: Code Implementation