Computer Vision

Hi HN, We are the core developers behind FACEIO ( https://faceio.net ), a product developed from scratch here at PixLab ( https://pixlab.io

Hi HN, In machine learning, we are faced with tensor-based computations (that's the language that ML models think in). I've recently discovered a proj

I recently did a talk on how you can analyse images with the Azure Computer Vision Service. While...

Weights in the final layer of common visual models appear as horizontal bands. We investigate how and why.

A family of early-vision neurons reacting to directional transitions from high to low spatial frequency.

Show HN: Build a DIY license plate reader with machine learning. 60 comments, 190 points on Hacker News.

An overview of all the neurons in the first five layers of InceptionV1, organized into a taxonomy of 'neuron groups.'

I built a DIY license plate reader with a Raspberry Pi and machine learning. 75 comments, 178 points on Hacker News.

An example project using webpack and svelte-loader and ejs to inline SVGs

Picture Perfect Box Camera System Design (2019). 0 comments, 13 points on Hacker News.

Remastering Star Trek: Deep Space Nine with Machine Learning. 195 comments, 391 points on Hacker News.

In Part 3 , we have reviewed models in the R-CNN family. All of them are region-based object detection algorithms. They can achieve hig

[Updated on 2018-12-20: Remove YOLO here. Part 4 will cover multiple fast object detection algorithms, including YOLO.] [Updated on 2018-12-27: Add bbox regress

Part 1 of the “Object Detection for Dummies” series introduced: (1) the concept of image gradient vector and how HOG algorithm summarizes the inform

How neural networks build up their understanding of images

I’ve never worked in the field of

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that

The future of computers – Part 1: Multicore and the Memory Wall (2011). 5 comments, 39 points on Hacker News.

Who is he? Born in 1926 in the Bronx, New York, Jerome Svigals attended City College of New York. In 1950, as second lieutenant in the U.S. Army, he worked on d

Computer Vision is Artificial Intelligence. 24 comments, 51 points on Hacker News.