Skip to main content

SparseEdges: A bio-inspired sparse representation of edges in natural images.

Project description

[![PyPI version](https://badge.fury.io/py/SparseEdges.svg)](https://badge.fury.io/py/SparseEdges)
[![Research software impact](http://depsy.org/api/package/pypi/SparseEdges/badge.svg)](http://depsy.org/package/python/SparseEdges)

What is the SparseEdges package?
================================

Our goal here is to build practical algorithms of sparse coding for computer vision.

This class exploits the [SLIP](https://pythonhosted.org/SLIP/) and [LogGabor](https://pythonhosted.org/LogGabor/) libraries to provide with a sparse representation of edges in images.

This algorithm was presented in the following paper:

~~~~{.bibtex}
@inbook{Perrinet15bicv,
author = {Perrinet, Laurent U.},
booktitle = {Biologically-inspired Computer Vision},
chapter = {13},
citeulike-article-id = {13566753},
editor = {Keil, Matthias and Crist\'{o}bal, Gabriel and Perrinet, Laurent U.},
keywords = {anr-trax, bicv-sparse},
posted-at = {2015-03-31 14:21:35},
priority = {2},
publisher = {Wiley, New-York},
title = {Sparse models},
year = {2015}
}
~~~~

This package gives a python implementation.

Moreover, it gives additional tools to compute useful stistics in images; first- and second order statistics of co-occurences in images.
More information is available @ http://nbviewer.ipython.org/github/bicv/SparseEdges/blob/master/SparseEdges.ipynb
Tests for the packages are available @ http://nbviewer.ipython.org/github/bicv/SparseEdges/blob/master/notebooks/test-SparseEdges.ipynb

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

SparseEdges-20180606.tar.gz (9.9 MB view details)

Uploaded Source

File details

Details for the file SparseEdges-20180606.tar.gz.

File metadata

File hashes

Hashes for SparseEdges-20180606.tar.gz
Algorithm Hash digest
SHA256 7afde8001d2244838a9fd826a4e6105fc7b1a95b0250a7d37daf1f4cd047f86f
MD5 960ec1c3a767063c67b16075cd302b1c
BLAKE2b-256 62f89efca90c4d308ad4e0acbb18703b9f7709517dfb2895307f054d508ce62d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page