CODECHECK Certificate 2020-002
Paper details
Title: The principal components of natural images
Authors: Peter J. B. Hancock, Roland J. Baddeley, Leslie S. Smith
Abstract: Obtained from OpenAlex
AbstractA neural net was used to analyse samples of natural images and text. For the natural images, components resemble derivatives of Gaussian operators, similar to those found in visual cortex and inferred from psychophysics. While the results from natural images do not depend on scale, those from text images are highly scale dependent. Convolution of one of the text components with an original image shows that it is sensitive to inter-word gaps.
Codecheck details
Certificate identifier: 2020-002
Codechecker names: Stephen J. Eglen, Daniel Nüst
Time of codecheck: 2020-04-13 10:00:00
Repository: https://github.com/codecheckers/Reproduction-Hancock
Codecheck report: http://doi.org/10.5281/zenodo.3750741
Summary:
Matlab code written by Iain Davies to reproduce original paper; natural images provided by Peter Hancock.
https://codecheck.org.uk/ | codecheckers
Published under CC BY-SA 4.0
CODECHECK is a process for independent execution of computations underlying scholarly research articles.