The world’s leading publication for data science, AI, and ML professionals.

April Edition: A Closer Look at Computer Vision

New angles on an ever-evolving field

Photo by Jessica Ruscello on Unsplash
Photo by Jessica Ruscello on Unsplash

Even if you’re new to data science and machine learning, you’ve probably heard about Computer Vision and its impact in fields as diverse as healthcare, autonomous driving, and industrial manufacturing. If you’re a ML practitioner, you already know just how fast the field has been moving, with new research and real-world applications emerging at a constant clip.

Regardless of how familiar you are with the topic, we think you’ll find new and interesting ideas to explore in this Monthly Edition. We’ve put together a wide-ranging selection of recent contributions on computer vision from writers working in industry and in academia, as well as from self-taught tinkerers who prefer a hands-on approach. These posts include tutorials and basic explainers, as well as advanced deep dives around the technical and social aspects of an increasingly ubiquitous technology. Happy reading!

If these articles inspire you to support our authors by becoming Medium members, we’d be especially grateful.

TDS Editors


The Layperson’s Introduction to Computer Vision

A light introduction to the concepts behind computer vision for any audience to understand.

By David Hundley (10 minutes)


Revisiting MNIST with Fresh Eyes

A spatial perspective to MNIST data, rather than the usual vector-treatment.

By Raveena Jayadev (8 minutes)


The Practical Guide for Object Detection with YOLOv5 Algorithm

A detailed tutorial explaining how to efficiently train the object detection algorithm YOLOv5 on your own custom dataset.

By Lihi Gur Arie, PhD (9 minutes)


Land Cover Classification Using TensorFlow in Python

EuroSAT land cover classification using a TensorFlow convolutional neural network.

By Andrew Joseph Davies (8 minutes)


How to Extract the Text from PDFs Using Python and the Google Cloud Vision API

A comprehensive guide to using a powerful tool to run simple OCR applications.

By Silvia Zeamer (10 minutes)


Computer Vision and Melanin, a DEI Case Study

On strides and errors in Machine Learning, particularly Computer Vision, and the necessity of having a large and diverse dataset.

By Monica P. (7 minutes)


TerrificEye: An Edge Computing System for Traffic Analytics from Videos

How to build a real-time, standalone traffic monitoring and analytics system.

By J. Rafid S., PhD (7 minutes)


What I Learned While Implementing Computer Vision Papers

An effective way to practice multiple skills simultaneously.

By Lilit Yolyan (3 minutes)


An Intuitive Introduction to Generative Adversarial Networks (GANs)

Explaining the magic of GANs in computer vision.

By Lakshmi Ajay (7 minutes)


How Computers See Depth: Recent Advances in Deep Learning-Based Methods

A deep dive into the realm of image-based stereovision.

By Joseph Robinson, PhD (28 minutes)


Getting Started with PyTorch Image Models (timm): A Practitioner’s Guide

How to use this versatile, useful library in your own training scripts.

By Chris Hughes (40 minutes)


Building a Semantics Segmentation Computer Vision Algorithm for Deployment on the Edge

Technical challenges and learnings in a production Computer Vision project.

By Mengyong Lee (11 minutes)


How to Build a Computer Vision Project Easily and without Code

A beginner friendly, no-code solution to your own fruit detector.

By Ane Berasategi (7 minutes)


PostGIS for Computer Vision Developers

Analyzing geometric objects directly in SQL without additional Python code.

By Sivan Biham (6 minutes)


Powering Semantic Similarity Search in Computer Vision with State of the Art Embeddings

Covering the easiest ways to perform image-to-image and text-to-image similarity search.

By Marie Stephen Leo (17 minutes)


Before we sign off, please join us in welcoming all the talented authors who joined our ranks in the past month. (If you’d like to see your name here too, the first step is to share your work with us!) They include Naresh Ram, Tony Pizur, Lopamudra Nayak, Patrick Schreiber, Weronika Gawarska-Tywonek, Thomas Chaigneau, Bruno Scalia C. F. Leite, Stefan Krawczyk, Maxime Labonne, Najma Bader, Adam Orucu, Wing Poon, Ern Chow, Marios Perrakis, Mark Did, Chris Brown, Antonin Leroy, Richard Kang, Jingyi Jessica Li, Pere Miquel Brull, Diego Barba, Pádraig Cunningham, Marlene Mhangami, Yann Hoffmann, [Dan Robinson](None), Giovanni Valdata, Vitor Cerqueira, Shilpa Gupta, Jessie Huang, Jill Villany, Zachary Lee, Yenwee Lim, Yusuf Sarıgöz, Ishtiak Mahmud, Udit Gupta, Danie Theron, and Dan Robinson.


Related Articles