Computer Vision

Computer Vision

Designing Dashcams to Freeze License Plates

Law enforcement has long had license plate readers, but now, thanks to technology, you can too. Here’s how we could design dashcams to work like police license plate readers:

Read More
Computer Vision

4 Computer Vision ideas to make a SMART FARM

Here’s an interesting take on what AI can do for agriculture. In the last 2 years, since I started showing on YouTube project prototypes built with computer vision I have been contacted by workers of different industries, and Farm is one of them. First they wanted to validate their idea, whether improving some processes inside […]

Read More
Computer Vision IoT Raspberry Pi

Raspberry pi YOLOv4-tiny Object Detection with Intel Neural Compute Stick and openVINO

Here’s an interesting computer vision project. I really need to unpack more of my stuff so I can find my Raspberry Pis.

Read More
Computer Vision

Going Beyond Medical Image Segmentation. The Road Towards Clinical Insights

Adam Klimont and Tomasz Bartczak present “Beyond Medical Image Segmentation. The Road Towards Cinical Insights” at the PyData London 2022 conference. Recent progress in deep learning for medical imaging has led to impressive results. Among them is a fully automatic human organ segmentation from Computed Tomography (CT) scans. Organ segmentation can be the end goal […]

Read More
AI Computer Vision Python

How Improved Text Readability Online Helps the Visually Impaired

Asya Frumkin presents “Can You Read This? (Or: How I Improved Text Readability on the Web for the Visually Impaired)” from the PyData London 2022: This talk will describe how Asya Frumkin used deep learning to identify texts on background images that are illegible for people with vision impairments. Frumkin explains the challenges ncountered when […]

Read More
Ethics Facial Recognition Livestream

Thursday Thoughts: AI Emotion Detectionm Ethics, and SLAs

My thoughts on Microsoft retiring some features of Azure Face. It may be the ethical thing to do, but what are the collateral damages? Could there be a more nuanced approach?

Read More
AI Computer Vision Open Source

Exploring the LAION-5B: a 5 billion image-text-pairs dataset

LAION-5B is an open, free dataset consisting of over 5 billion image-text-pairs. Today’s video is an interview with three of its creators. We dive into the mechanics and challenges of operating at such large scale, how to keep cost low, what new possibilities are enabled with open datasets like this, and how to best handle […]

Read More