Computer Vision Archives - Open Data Science - Your News Source for AI, Machine Learning & more

Image Recognition: Past, Present, and Future

Modeling Computer Vision West 2022posted by ODSC Community August 5, 2022

Editor’s note: Oliver is a speaker for ODSC West 2022 this November. Be sure to check out his talk, “Image Recognition with OpenCV and TensorFlow,” there! Let’s say you run a factory producing rings and want to tell the two models you have from each other.... Read more

Overcoming ImageNet dataset biases with PASS

Modeling Computer Visionposted by Parul Pandey May 3, 2022

ImageNet is one of the most widely used datasets in Computer Vision applications. However, studies have shown biases prevalent in this dataset based on the collection methodology and the types of images present. In this respect, a team of researchers at the Visual Geometry Group, the University of... Read more

Benchmarking a Computer Vision Deep Learning Pipeline with Distributed Computing

Blogs from ODSC Speakers Deep Learning Modeling Computer Vision East 2022posted by ODSC Community March 4, 2022

Editor’s Note: Jennifer is a speaker for ODSC East 2022. Be sure to check out her talk, “Creating a Benchmark for a Large-Scale Image Captioning Pipeline,” to learn more about computer vision deep learning there! Computer vision has an essential role in solving some of the... Read more

Computer Vision & Data Annotation – An Easy Way of Understanding the Relevance in the Real World

Business + Management Guest contributor Modeling Computer Visionposted by ODSC Community November 11, 2021

Here, you will find a brief explanation of computer vision, some cases we are experiencing in real life, and some of the existent techniques in data annotation supporting the advance of computer vision. I want to highlight upfront that I’m not approaching any computer vision algorithms... Read more

Adversarial Image Explanation Through Alibi

Deep Learning Modeling Adversarial Image Explanation Computer Vision Europe 2021posted by ODSC Community May 7, 2021

Deep learning-based computer vision has plenty of real-life applications. In particular, Convolutional Neural Network (CNN) architectures are commonly used across multiple CV tasks as they have high accuracy. But their strength leads also to a weakness point, as a little perturbation to an input image/frame can... Read more

Dataset Management for Computer Vision

Blogs from ODSC Speakers Conferences Modeling Computer Vision Dataset Management East 2021posted by ODSC Community February 15, 2021

When building computer vision solutions, the emphasis is usually on the modeling side and on leveraging the latest algorithm. While the model is important, in my experience I have found that an even more important component to delivering a successful solution is to build and maintain... Read more

Creating Typography Using Word Cloud in Python

Deep Learning Modeling Computer Visionposted by ODSC Community June 25, 2020

Cameras’ biggest recent advancements have come from AI, not sensors and lenses. Over the past couple of years, technology has enabled staggering advances in photography. AI is transforming both the way we shoot photos and how we edit them. As ‘computer vision’ becomes an important part... Read more

Data Science in Manufacturing: An Overview

Business + Management Manufacturing Computer Vision East 2020posted by ODSC Community February 17, 2020

In the last couple of years, data science has seen an immense influx in various industrial applications across the board. Today, we can see data science applied in health care, customer service, governments, cybersecurity, mechanical, aerospace, and other industrial applications. Among these, manufacturing has gained more... Read more

Creativity Inspired Zero-Shot Learning: Classifying Unseen Classes

Blogs from ODSC Speakers Conferences Machine Learning Modeling Computer Vision zero-shot learningposted by ODSC Community November 5, 2019

Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of zero-shot learning, we model the visual learning process of unseen categories with inspiration from the psychology of human creativity for producing novel art. We relate... Read more

Working Towards Planetary Scale Location Insights

Deep Learning Modeling Computer Vision geospatial temporal analysisposted by ODSC Community October 24, 2019

Approaches for making geospatial imagery accessible to (geo)data scientists. This post discusses planetary scale location insights. Recent innovations in agile aerospace have created unique offerings in high cadence satellite imagery. While this is of immense interest to imagery analysts, a significant portion of GIS professionals and... Read more