Neckerworld is a computer game designed to teach and explore human and computer vision.
-
Updated
May 19, 2024 - C++
Neckerworld is a computer game designed to teach and explore human and computer vision.
A course project for Android application built for an image classifier
A test to see how many shades of gray can a human distinguish, written with HTML/CSS/JavaScript.
Test framework and reference implementation of our algorithms relating to the real-time simulation of human vision.
Code used to create the Neural Encoding Datasets (NED), and utility functions to generate neural responses to arbitrary images using NED's trained models.
Deep fMRI Encoding Models of Human Vision using Capsule Networks
Visual Search Model: A Bayesian model for visual search on natural scenes.
Software for Environmental Light Field (ELF) analysis. For more information, check out our Interface article "Quantifying biologically essential aspects of environmental light" at https://doi.org/10.1098/rsif.2021.0184
[TIP-2018] MATLAB implementation of the "A Gabor Feature-Based Quality Assessment Model for the Screen Content Images"
Matlab implementation of "Image quality assessment using human visual DOG model fused with random forest"
Repository related to the manuscript "Automatic Gemstone Classification Using Computer Vision" by Bona Hiu Yan Chow and Constantino Carlos Reyes-Aldasoro published in Minerals MDPI, 2022, 12(1), 60 (doi: 10.3390/min12010060).
Load and model the brain data of the Algonauts Project 2023 Challenge.
Python package to conduct feature-reweighted representational similarity analysis.
Data and materials from the paper "Comparing deep neural networks against humans: object recognition when the signal gets weaker" (arXiv 2017)
Use DNNs to build encoding models of EEG visual responses.
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)
Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)
Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)
Add a description, image, and links to the human-vision topic page so that developers can more easily learn about it.
To associate your repository with the human-vision topic, visit your repo's landing page and select "manage topics."