Category: Articles

Optical character recognition (OCR) is a method that helps machines recognize texts. Traditional OCR uses patterns and correlation to differentiate words from other elements. However, these techniques don’t tend to produce results with high accuracy for complex text or in-motion streams. For these tasks, you’re better served using deep learning models. In that spirit, in this article we’ll explore three deep learning models for OCR.

Continue reading Optical Character Recognition Using Deep Learning Techniques

In recent years, research related to vision-based 3D image processing has become increasingly active, given its many applications in virtual reality (VR) and augmented reality (AR). Despite years of studies, however, there are still images that machines struggle to understand—one of those is images of human hands.

Hand image understanding targets the problem of recovering the spatial configuration of hands from natural RGB or/and depth images. This task has many applications, such as human-machine interaction and virtual/augmented reality, among others.

Continue reading HAMR — 3D Hand Shape and Pose Estimation from a Single RGB Image

In this tutorial, we’ll create a car that controlled using a USB camera and a Raspberry Pi. We’ll use a wood plank as the car body, which will hold all the car’s components. The components are:

After fixing the component using cable ties, we’ll connect the Raspberry Pito the motors using its general purpose input output (GPIO) pins. Similar to a traffic sign, the motors will run when the dominant color in the captured images is green and stop when it’s red.

Continue reading Building a Vision-Controlled Car Using Raspberry Pi—From Scratch

In this piece, we’ll take a closer look at some of the top machine learning articles in 2019, as ranked by MyBridge.

According to the article:

Pluribus was tested against professional poker players. This included two winners of the World Series of Poker Event. Pluribus uses self-play to teach itself how to win. This happens without any examples or guidance. The self-play version used in Pluribus is an improved version of the iterative Monte Carlo CFR (MCCFR) algorithm.

Continue reading 2019’s Top Machine Learning Articles

Computer vision is a field in artificial intelligence based on giving machines an understanding of data from images, video frames, pixel manipulations, and others. In this article, we will look into four commonly used annotation tools for object detection/tracking. To demonstrate these, we will be annotating team players on the football pitch.

The following is an outline on what we will be looking into:

Continue reading Four Important Computer Vision Annotation Tools you Need to Know in 2020

Object detection is a computer vision technique whose aim is to detect objects such as cars, buildings, and human beings, just to mention a few. The objects can generally be identified from either pictures or video feeds.

Continue reading A 2019 Guide to Object Detection

Compression involves processing an image to reduce its size so that it occupies less space. There are already codecs, such as JPEG and PNG, whose aim is to reduce image sizes. There are two types of image compression; lossy and lossless.

In lossless compression, one can retrieve the original image data, while in lossy compression one cannot. As a point of reference, PNG is lossless and JPEG is lossy.

Continue reading A 2019 Guide to Deep Learning-Based Image Compression

With recent developments in big data, we’ve been given more access to high-dimensional data. Consequently, the performance of machine learning models has improved by a large margin.

On the other hand, there are significant noisy and useless features often collected or generated by different sensors and methods. These unneeded features not only influence a model’s accuracy, but they also can demand a lot of computational resources.

Continue reading Hands-on with Feature Selection Techniques: An Introduction

This will be a short and concise tutorial on how to build a facial recognition system with JavaScript, using faceapi.js built on Tensorflow.js; hence we won’t be interacting with Tensorflow.js directly.

This is what our final model output should look like

We want to build an ML system, that when given a specific input image, will tell us if a face in the input image is similar a face in our database. 😉

Continue reading Facial Recognition System with JavaScript

This write up is an excerpt from my recent research on transfer functions and machine learning operations. Throughout this post, I’ll basically be establishing the core principles of these two different concepts, and examine their relationship to each other.

I have always understood machine learning algorithms as a simple relationship between variable X and Y, where X is the input data and Y is the learning outcome. The general polynomial relationship between X and Y is bounded by the following function:

Continue reading Transfer Functions for Machine Learning, Simplified