learnopencv.com介绍
http://www.learnopencv.com/wp-content/uploads/2015/05/Computer-Vision-Resources.pdf
Software & Libraries
OpenCV ( http://opencv.org/ )
Summary
The biggest and the most extensive open source computer vision library. OpenCV has
more than 47 thousand people of user community and estimated number of
downloads exceeding 10 million.
Languages
C/C++ with interfaces to Python and Java.
Platforms
Windows, Linux, Mac OS, iOS, Android, Raspberry Pi, and NVIDIA Jetson TK1.
License ( http://opencv.org/license.html )
BSD : It is free for both academic and commercial use.
Note : Not all parts of OpenCV are free.
VLFeat ( http://www.vlfeat.org/ )
Summary
Computer vision algorithms specializing in image understanding and local features
extraction and matching.
Languages
C with interfaces in MATLAB
Platforms
Windows, Mac OS X, and Linux.
License
BSD : It is free for academic and commercial use.
SimpleCV ( http://simplecv.org/ )
Summary
SimpleCV is an open source wrapper around computer vision libraries such as
OpenCV that hides some of its complexities.
Languages
Python
Platforms
Windows, Mac OS X, Linux, and Raspberry Pi.
License
BSD : It is free for academic and commercial use.
MATLAB CV Toolbox ( http://www.mathworks.com/products/computer-vision/ )
Summary
A computer vision toolbox for MATLAB.
Languages
MATLAB
Platforms
Windows, Mac OS X and Linux.
License
MATLAB’s license. Requires Image Processing Toolbox. The total cost of installing
MATLAB ( 2,150)+ImageProcessingToolbox( 1, 000 ) + Computer Vision Toolbox
( 1,350)= 4500. Student licenses are much cheaper though ( few hundred dollars ).
Python Libraries
One of the main advantages of using OpenCV with Python is the vast number of scientific
libraries available for Python. Here are a few libraries you will find useful. The first three
libraries — NumPy, SciPy and Matplotlib — are part of the SciPy stack. When used together,
they pretty much replace MATLAB.
1. NumPy ( http://www.numpy.org ) : NumPy adds support for large, multidimensional
arrays and matrices to Python. It also consists of a large library of highlevel
mathematical functions to operate on these arrays. OpenCV images are read in as
NumPy arrays. Several other math, image processing, and machine learning libraries
are built on top of NumPy.
2. SciPy ( http://scipy.org/scipylib/index.html ) : SciPy is a powerful scientific library
built on top of NumPy. It’s sub packages include linalg ( linear algebra ), optimize
( optimization and root-finding routines ), stats ( statistical distributions and
functions ), ndimage ( N-dimensional image processing ), interpolate
( interpolation and smoothing splines) , fftpack ( Fast Fourier Transform routines),
cluster (Clustering algorithms) and many more.
3. matplotlib ( http://matplotlib.org/ ) : An excellent 2D plotting library for Python that
is every bit as powerful as MATLAB. You can generate plots, histograms, power
spectra, bar charts, scatterplots, etc, with just a few lines of code.
4. scikit-learn ( http://scikit-learn.org/ ) : As a computer vision programmer / engineer,
you will inevitably need a good machine learning library and scikit-learn serves that
purpose well. It uses numpy/scipy idioms and provides algorithms for preprocessing
data, classification, regression, clustering, dimensionality reduction, and model
selection.
Web APIs
1. Alchemy API ( http://www.alchemyapi.com/products/alchemyvision ) :
A deep learning based API for auto tagging images based on the content of the image. If you upload an image of a cat, it will return “cat” as a tag. Deep learning based large scale recognition is a hot topic of research these days. If you have been following ImageNet Large Scale Visual Recognition Challenge ( ILSVRC ), you probably know that even
though IBM is first to market with its API, several other teams from Google, Facebook,
Microsoft, Baidu, and several universities are doing much better in the competition.
Hope they come up with an API too!
2. CloudSight ( http://cloudsightapi.com/) :
What is better than computer vision ? Well, human vision! CloudSight API does visual recognition using a combination of computer vision and human crowd sourcing. You can use their app called CamFind to see how well it works.
3. Face++ ( http://www.faceplusplus.com/ ) :
An API for face detection, facial landmark detection, face search, and face recognition.
4. TinEye ( https://services.tineye.com/TinEyeAPI ) :
Search the entire web for an image using TinEye’s reverse image search.
5. OCRSDK ( http://ocrsdk.com ) :
Upload an image containing text and get back the results as text. They provide sample code and it works well for standard scanned text.
6. CloudCV ( http://cloudcv.org ) :
CloudCV describes itself as a Large-Scale Distributed Computer Vision as a Cloud Service. It is not a commercial product, but is being developed by Machine Learning and Perception Lab at Virginia Tech. They do image stitching and object detection / classification in the cloud.
My Contact Info
Website http://www.learnopencv.com
Email [email protected]
LinkedIn https://www.linkedin.com/in/satyamallick
Google+ https://plus.google.com/+SatyaMallick