hand gesture

README.md

@@ -0,0 +1,157 @@
+# Tutorial: Computer Vision and Machine Learning with Python, Keras and OpenCV
+### Includes a demonstration of concepts with Gesture Recognition.
+This was created as part of an educational for the [Western Founders Network](https://foundersnetwork.ca/) computer vision and machine learning educational session.
+
+## Demo
+
+The final demo can be seen [here](https://www.youtube.com/watch?v=IJV11OGTNT8) and below:
+
+<a href="https://imgflip.com/gif/22n3o6"><img src="https://i.imgflip.com/22n3o6.gif"/></a>
+
+## Contents
+[notebook.ipynb](https://github.com/jrobchin/Computer-Vision-Basics-with-Python-Keras-and-OpenCV/blob/master/notebook.ipynb) contains a full tutorial of basic computer vision and machine learning concepts, including:
+
+* *What computers see*
+* Image Filters and Functions
+  - Blurring
+  - Dilating
+  - Erosion
+  - Canny Edge Detectors
+  - Thresholding
+* Background Subtraction Techniques
+  - Using a background image to find differences
+  - Using motion based background subtraction algorithms
+* Contours
+  - Finding and sorting contours
+* Tracking
+* (Deep) Neural Networks 
+* (Deep) Convolutional Neural Networks
+* Demo Project: Gesture Recognition
+  - Extracting the subject
+  - Tracking the hand
+  - Collecting data
+  - Building the Neural Network
+  - Preparing Data for Training
+  - Training the Network
+  - Plotting Model History
+
+*Note: Please check the [issues](https://github.com/jrobchin/Computer-Vision-Basics-with-Python-Keras-and-OpenCV/issues) on this repo if you're having problems with the notebook.*
+
+## Installation Instructions ('$' means run this in terminal/command prompt, do not type '$')
+### Windows:
+* Install Anaconda (https://www.anaconda.com/download/) or Miniconda (https://conda.io/miniconda.html) to save hard drive space
+* Start an Anaconda Prompt. (Search Anaconda in the start menu.)
+#### Option 1: Exact source package installs
+* Use the spec-file.txt provided, install identical packages
+
+        $ conda create -n [ENV_NAME] --file spec-file.txt # create new env with same packages
+    or, if you have an existing environment
+
+        $ conda install -n [ENV_NAME] --file spec-file.txt # install packages into an existing env
+* Then activate the environment
+
+        $ activate cv
+* Install OpenCV3 (https://opencv.org/)
+    - Download whl file https://www.lfd.uci.edu/~gohlke/pythonlibs/#opencv
+    - Download “opencv_python 3.4.0+contrib cp35 cp35m win32.whl” or “opencv_python 3.4.0+contrib cp35 cp35m win_amd64.whl” for 32bit and 64bit respectively
+    - Install package
+
+          $ pip install [file path]
+#### Option 2: Package installs
+* Using the environment.yml file provided, run
+
+        $ conda create -n cv --file environment.yml
+    or, if you have an existing environment
+
+        $ conda install -n [ENV_NAME] --file environment.yml # install packages into an existing env
+* Activate the environment
+
+        $ activate cv
+* Install OpenCV3 (https://opencv.org/)
+    - Download whl file https://www.lfd.uci.edu/~gohlke/pythonlibs/#opencv
+    - Download “opencv_python 3.4.0+contrib cp35 cp35m win32.whl” or “opencv_python 3.4.0+contrib cp35 cp35m win_amd64.whl” for 32bit and 64bit respectively
+    - Install the package
+
+          $ pip install [file path]
+#### Option 3: Manually installing packages
+* Create and activate a Python 3.5 conda environment called cv.
+
+        $ conda create -n cv python=3.5
+
+        $ activate cv
+* Install Numpy (http://www.numpy.org/)
+
+        $ conda install numpy
+* Install Matplotlib (https://matplotlib.org/)
+
+        $ conda install matplotlib
+* Install Keras (https://keras.io/) 
+
+        $ conda install keras
+    - This should also install tensorflow
+* Install h5py (http://www.h5py.org/)
+
+        $ conda install h5py
+* Install OpenCV3 (https://opencv.org/)
+    - Download whl file https://www.lfd.uci.edu/~gohlke/pythonlibs/#opencv
+    - Download “opencv_python 3.4.0+contrib cp35 cp35m win32.whl” or “opencv_python 3.4.0+contrib cp35 cp35m win_amd64.whl” for 32bit and 64bit respectively
+    - Install package
+
+          $ pip install [file path]
+* Install Jupyter Notebook (http://jupyter.org/)
+
+        $ conda install jupyter notebook
+* Install IPython (https://ipython.org/)
+
+        $ conda install ipython
+        
+### Mac/Linux: Manually installing packages
+* Install Anaconda (https://www.anaconda.com/download/) or Miniconda (https://conda.io/miniconda.html) to save hard drive space
+#### Mac:
+* For Miniconda, open terminal and navigate to the directory you downloaded Miniconda3-latest-MacOSX-x86_64.sh to and run:
+
+        $ bash Miniconda3-latest-MacOSX-x86_64.sh
+
+* For Anaconda, double click the Anaconda3-5.0.1-MacOSX-x86_64.pkg file you downloaded
+
+#### Linux:
+* For Miniconda, open a terminal and navigate to the directory you downloaded Miniconda3-latest-Linux-x86_64.sh to and run:
+
+        $ bash Miniconda3-latest-Linux-x86_64.sh
+
+* For Anaconda, open a terminal and navigate to the directory you downloaded Anaconda3-5.0.1-Linux-x86_64.sh to and run:
+
+        $ bash Anaconda3-5.0.1-Linux-x86_64.sh
+
+#### Both:
+* Create and activate a Python 3.5 conda environment called cv.
+
+        $ conda create -n cv python=3.5
+
+        $ source activate cv
+* Install Numpy (http://www.numpy.org/)
+
+        $ conda install numpy
+* Install Matplotlib (https://matplotlib.org/)
+
+        $ conda install matplotlib
+* Install Keras (https://keras.io/) 
+
+        $ conda install keras
+    - This should also install tensorflow
+* Install h5py (http://www.h5py.org/)
+
+        $ conda install h5py
+* Install Jupyter Notebook (http://jupyter.org/)
+
+        $ conda install jupyter notebook
+* Install IPython (https://ipython.org/)
+
+        $ conda install ipython
+* Install OpenCV3 (https://opencv.org/)
+
+        $ conda install -c conda-forge opencv 
+
+    if the `import cv2` does not work with this install, try instead:
+
+        $ conda install -c https://conda.anaconda.org/menpo opencv3

env/environment.yml

@@ -0,0 +1,92 @@
+name: cv
+channels:
+- defaults
+dependencies:
+- backports=1.0=py35he88aa47_1
+- backports.weakref=1.0rc1=py35_0
+- bleach=1.5.0=py35_0
+- ca-certificates=2017.08.26=h94faf87_0
+- certifi=2017.11.5=py35h456c6ae_0
+- colorama=0.3.9=py35h32a752f_0
+- cycler=0.10.0=py35hcc71164_0
+- decorator=4.1.2=py35hc7d1f2e_0
+- entrypoints=0.2.3=py35hb91ced9_2
+- freetype=2.8=h51f8f2c_1
+- h5py=2.7.1=py35hd8ea038_0
+- hdf5=1.8.18=hcf527f2_1
+- html5lib=0.9999999=py35_0
+- icc_rt=2017.0.4=h97af966_0
+- icu=58.2=ha66f8fd_1
+- intel-openmp=2018.0.0=hd92c6cd_8
+- ipykernel=4.7.0=py35h2f9c1c0_0
+- ipython=6.2.1=py35h4a2ac14_1
+- ipython_genutils=0.2.0=py35ha709e79_0
+- ipywidgets=7.0.5=py35h49ade1d_0
+- jedi=0.11.0=py35_2
+- jinja2=2.10=py35hdf652bb_0
+- jpeg=9b=hb83a4c4_2
+- jsonschema=2.6.0=py35h27d56d3_0
+- jupyter=1.0.0=py35hce9caf1_2
+- jupyter_client=5.1.0=py35hcddec19_0
+- jupyter_console=5.2.0=py35hf76c22e_1
+- jupyter_core=4.4.0=py35h629ba7f_0
+- keras=2.1.2=py35_0
+- libpng=1.6.32=h140d38e_4
+- libprotobuf=3.4.1=h3dba5dd_0
+- markdown=2.6.9=py35_0
+- markupsafe=1.0=py35hc253e08_1
+- matplotlib=2.1.1=py35h2062329_0
+- mistune=0.8.1=py35h7e79247_0
+- mkl=2018.0.1=h2108138_4
+- nbconvert=5.3.1=py35h98d6c46_0
+- nbformat=4.4.0=py35h908c9d9_0
+- notebook=5.2.2=py35h2b96da0_0
+- numpy=1.14.0=py35h4a99626_0
+- openssl=1.0.2n=h74b6da3_0
+- pandoc=1.19.2.1=hb2460c7_1
+- pandocfilters=1.4.2=py35h978f723_1
+- parso=0.1.1=py35he39c48a_0
+- pickleshare=0.7.4=py35h2f9f535_0
+- pip=9.0.1=py35h691316f_4
+- prompt_toolkit=1.0.15=py35h89c7cb4_0
+- protobuf=3.4.1=py35h58370bd_0
+- pygments=2.2.0=py35h24c0941_0
+- pyparsing=2.2.0=py35hcabcaab_1
+- pyqt=5.6.0=py35hd46907b_5
+- python=3.5.4=h1357f44_23
+- python-dateutil=2.6.1=py35h6b299a3_1
+- pytz=2017.3=py35hb294b1a_0
+- pyyaml=3.12=py35h4bf9689_1
+- pyzmq=16.0.3=py35h1861011_0
+- qt=5.6.2=vc14h6f8c307_12
+- qtconsole=4.3.1=py35hc47b0dd_0
+- scipy=1.0.0=py35h75710e8_0
+- setuptools=36.5.0=py35h21a22e4_0
+- simplegeneric=0.8.1=py35h6406082_0
+- sip=4.18.1=py35h01cbaa7_2
+- six=1.11.0=py35hc1da2df_1
+- sqlite=3.20.1=h9eeafa9_2
+- tensorflow=1.2.1=py35_0
+- testpath=0.3.1=py35h06cf69e_0
+- tornado=4.5.2=py35h03246f3_0
+- traitlets=4.3.2=py35h09b975b_0
+- vc=14=h2379b0c_2
+- vs2015_runtime=14.0.25420=0
+- wcwidth=0.1.7=py35h6e80d8a_0
+- werkzeug=0.12.2=py35hc854123_0
+- wheel=0.30.0=py35h38a90bc_1
+- widgetsnbextension=3.0.8=py35hdf37555_0
+- win_unicode_console=0.5=py35h56988b5_0
+- wincertstore=0.2=py35hfebbdb8_0
+- yaml=0.1.7=hc54c509_2
+- zlib=1.2.11=h8395fce_2
+- pip:
+  - ipython-genutils==0.2.0
+  - jupyter-client==5.1.0
+  - jupyter-console==5.2.0
+  - jupyter-core==4.4.0
+  - opencv-python==3.4.0+contrib
+  - prompt-toolkit==1.0.15
+  - win-unicode-console==0.5
+prefix: C:\Users\jason\AppData\Local\conda\conda\envs\cv
+

env/spec-file.txt

@@ -0,0 +1,90 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: win-64
+@EXPLICIT
+https://repo.continuum.io/pkgs/main/win-64/bleach-2.1.1-py35h73b2768_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/ca-certificates-2017.08.26-h94faf87_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/certifi-2017.11.5-py35h456c6ae_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/colorama-0.3.9-py35h32a752f_0.tar.bz2
+https://repo.continuum.io/pkgs/free/win-64/cudatoolkit-8.0-3.tar.bz2
+https://repo.continuum.io/pkgs/free/win-64/cudnn-6.0-0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/cycler-0.10.0-py35hcc71164_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/decorator-4.1.2-py35hc7d1f2e_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/entrypoints-0.2.3-py35hb91ced9_2.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/freetype-2.8-h51f8f2c_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/h5py-2.7.1-py35hb2c3add_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/hdf5-1.10.1-h98b8871_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/html5lib-1.0.1-py35h047fa9f_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/icc_rt-2017.0.4-h97af966_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/icu-58.2-ha66f8fd_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/intel-openmp-2018.0.0-hd92c6cd_8.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/ipykernel-4.7.0-py35h2f9c1c0_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/ipython-6.2.1-py35h4a2ac14_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/ipython_genutils-0.2.0-py35ha709e79_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/ipywidgets-7.0.5-py35h49ade1d_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/jedi-0.11.0-py35_2.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/jinja2-2.10-py35hdf652bb_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/jpeg-9b-hb83a4c4_2.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/jsonschema-2.6.0-py35h27d56d3_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/jupyter-1.0.0-py35hce9caf1_2.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/jupyter_client-5.1.0-py35hcddec19_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/jupyter_console-5.2.0-py35hf76c22e_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/jupyter_core-4.4.0-py35h629ba7f_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/keras-2.0.8-py35h15001cb_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/libiconv-1.15-h1df5818_7.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/libpng-1.6.32-h140d38e_4.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/libprotobuf-3.4.1-h3dba5dd_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/libtiff-4.0.9-h0f13578_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/libxml2-2.9.4-h41ea7b2_6.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/libxslt-1.1.29-h0037b19_6.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/lxml-4.1.1-py35ha957a02_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/markupsafe-1.0-py35hc253e08_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/matplotlib-2.1.1-py35h2062329_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/mistune-0.8.1-py35h7e79247_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/mkl-2018.0.1-h2108138_4.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/nbconvert-5.3.1-py35h98d6c46_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/nbformat-4.4.0-py35h908c9d9_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/notebook-5.2.2-py35h2b96da0_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/numpy-1.12.1-py35h02c1717_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/olefile-0.44-py35h7ba86d0_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/openssl-1.0.2n-h74b6da3_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pandoc-1.19.2.1-hb2460c7_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pandocfilters-1.4.2-py35h978f723_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/parso-0.1.1-py35he39c48a_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pickleshare-0.7.4-py35h2f9f535_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pillow-4.3.0-py35h967e314_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pip-9.0.1-py35h691316f_4.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/prompt_toolkit-1.0.15-py35h89c7cb4_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/protobuf-3.4.1-py35h58370bd_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pygments-2.2.0-py35h24c0941_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pyparsing-2.2.0-py35hcabcaab_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pyqt-5.6.0-py35hd46907b_5.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/python-3.5.4-h1357f44_23.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/python-dateutil-2.6.1-py35h6b299a3_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pytz-2017.3-py35hb294b1a_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pyyaml-3.12-py35h4bf9689_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/pyzmq-16.0.3-py35h1861011_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/qt-5.6.2-vc14h6f8c307_12.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/qtconsole-4.3.1-py35hc47b0dd_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/scipy-1.0.0-py35h75710e8_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/setuptools-36.5.0-py35h21a22e4_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/simplegeneric-0.8.1-py35h6406082_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/sip-4.18.1-py35h01cbaa7_2.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/six-1.11.0-py35hc1da2df_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/sqlite-3.20.1-h9eeafa9_2.tar.bz2
+https://repo.continuum.io/pkgs/free/win-64/tensorflow-1.1.0-np112py35_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/testpath-0.3.1-py35h06cf69e_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/tk-8.6.7-hcb92d03_3.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/tornado-4.5.2-py35h03246f3_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/traitlets-4.3.2-py35h09b975b_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/vc-14-h2379b0c_2.tar.bz2
+https://repo.continuum.io/pkgs/free/win-64/vs2015_runtime-14.0.25420-0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/wcwidth-0.1.7-py35h6e80d8a_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/webencodings-0.5.1-py35h5d527fb_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/werkzeug-0.12.2-py35hc854123_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/wheel-0.30.0-py35h38a90bc_1.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/widgetsnbextension-3.0.8-py35hdf37555_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/win_unicode_console-0.5-py35h56988b5_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/wincertstore-0.2-py35hfebbdb8_0.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/yaml-0.1.7-hc54c509_2.tar.bz2
+https://repo.continuum.io/pkgs/main/win-64/zlib-1.2.11-h8395fce_2.tar.bz2