Basic Image Processing using the Python program

โดย อาจารยย์โอฬารริก สสุรรินตต๊ะJan 19, 2017

Preparing Linux Systems for Installation• OpenCv 2.4

–http://opencv.org/• Scikit-image

–http://scikit-image.org/• Scikit-learn

–http://scikit-learn.org/

OpenCV: Installation in Linux• Following this link

–http://www.samontab.com/web/2014/06/installing-opencv-2-4-9-in-ubuntu-14-04-lts/

OpenCV: Installation in Linux$ sudo apt-get update$ sudo apt-get upgrade

# You need to install many dependencies librariws.$ sudo apt-get install build-essential libgtk2.0-dev libjpeg-dev libtiff4-dev libjasper-dev libopenexr-dev cmake python-dev python-numpy python-tk libtbb-dev libeigen3-dev yasm libfaac-dev libopencore-amrnb-dev libopencore-amrwb-dev libtheora-dev libvorbis-dev libxvidcore-dev libx264-dev libqt4-dev libqt4-opengl-dev sphinx-common texlive-latex-extra libv4l-dev libdc1394-22-dev libavcodec-dev libavformat-dev libswscale-dev default-jdk ant libvtk5-qt4-dev

OpenCV: Installation in Linux• In Linux 16.xx You may get any problem with a library, such as “libtiff4-dev” –Change “libtiff4-dev” to “libtiff5-dev”

OpenCV: Installation in Linux• Time to get the OpenCV 2.4.9 source code:

$ cd ~$wget http://sourceforge.net/projects/opencvlibrary/files/opencv-unix/2.4.9/opencv-2.4.9.zip $ unzip opencv-2.4.9.zip$ cd opencv-2.4.9

OpenCV: Installation in Linux• We have to generate the Makefile by using cmake.

$ mkdir build$ cd build$ cmake -D WITH_TBB=ON -D BUILD_NEW_PYTHON_SUPPORT=ON -D WITH_V4L=ON -D INSTALL_C_EXAMPLES=ON -D INSTALL_PYTHON_EXAMPLES=ON -D BUILD_EXAMPLES=ON -D WITH_QT=ON -D WITH_OPENGL=ON -D WITH_VTK=ON ..

OpenCV: Installation in Linux• Now, you are ready to compile and install OpenCV 2.4.9

$ make$ sudo make install

OpenCV: Installation in Linux• Configure OpenCV.$ sudo nano /etc/ld.so.conf.d/opencv.cof• Add the following line at the end of the file and then save it.

/usr/local/lib• Run the followin code to configure the library

$ sudo ldconfig

OpenCV: Installation in Linux• Open another file$ sudo nano /etc/bash.bashrc

• Add these two lines at the end of the file and save it.

PKG_CONFIG_PATH=$PKG_CONFIG_PATH:/usr/local/lib/pkgconfigexport PKG_CONFIG_PATH

Checking your OpenCV version using Python$ python Python 2.7.6 (default, Oct 26 2016, 20:32:47) [GCC 4.8.4] on linux2

>>> import cv2>>> cv2.__version__'2.4.8'

Scikit-image: Installation in Linux• Building from source$ sudo pip install scikit-image #or$ sudo pip install -U scikit-image

• If you have any problem with “pip” $ sudo apt-get install python-pip$ sudo pip install –upgrade pip

Checking your Scikit-image version>>> python>>> import skimage>>> print('The scikit-image version is {}.'.format(skimage.__version__))The scikit-image version is 0.9.3.

Scikit-image: First programfrom skimage import data, io, filters

image = data.coins()edges = filters.sobel(image)io.imshow(edges)io.show()

#so, if you have any problem please try another way.#ถถ้ายยังไมม่สามารถแสดงรรูปไดถ้ หรรือยยังตติดปยั ญาททที่ filters ใหถ้ลองดรูวติธทตม่อไปนทน

Scikit-image: First programfrom skimage import data, io, filter

image = data.coins()edges = filter.sobel(image)io.imshow(edges)io.show()

This is because, the version of the scikit-image is out of date.

Scikit-image: update$ sudo pip install -U scikit-image

Scikit-learn: Installation in Linux$ sudo pip install -U scikit-learn

Checking your Scikit-learn version>>> python>>> import sklearn>>> print('The scikit-learn version is {}.'.format(sklearn.__version__))The scikit-learn version is 0.17.1.

Scikit-learn: First program$ python>>> from sklearn import datasets>>> iris = datasets.load_iris()>>> digits = datasets.load_digits()>>> print(digits.data)[[ 0. 0. 5. ..., 0. 0. 0.] [ 0. 0. 0. ..., 10. 0. 0.] [ 0. 0. 0. ..., 16. 9. 0.] ..., [ 0. 0. 1. ..., 6. 0. 0.] [ 0. 0. 2. ..., 12. 0. 0.] [ 0. 0. 10. ..., 12. 1. 0.]]

Scikit-learn: First program>>> digits.images[0]array([[ 0., 0., 5., 13., 9., 1., 0., 0.], [ 0., 0., 13., 15., 10., 15., 5., 0.], [ 0., 3., 15., 2., 0., 11., 8., 0.], [ 0., 4., 12., 0., 0., 8., 8., 0.], [ 0., 5., 8., 0., 0., 9., 8., 0.], [ 0., 4., 11., 0., 1., 12., 7., 0.], [ 0., 2., 14., 5., 10., 12., 0., 0.], [ 0., 0., 6., 13., 10., 0., 0., 0.]])

Showing Image with Different Library: OpenCV#!/usr/bin/python

import cv2image = 'image/lena.png'img = cv2.imread(image)

cv2.imshow('image', img)cv2.waitKey(0);cv2.destroyAllWindows()

Showing Image with Different Library: Skikit-Image#!/usr/bin/python

from skimage import data, io, filter

image = data.coins()io.imshow(image)io.show()

Showing Image with Different Library: Matplotlibimport matplotlib.pyplot as pltimport matplotlib.image as mpimgimport numpy as np

imgName = 'image/lena.png'img = mpimg.imread(imgName)plt.imshow(img)<matplotlib.image.AxesImage object at 0xb3b8cacc>plt.show()

Showing Image with Different Library: Matplotlibimport matplotlib.pyplot as imshowimport numpy as npfrom PIL import Image

imgName = 'image/lena.png'pil_im = Image.open(imgName,'r')pil_im.show()

Arithmetic Operations on Images• Learn several arithetic operations on images like addition, subtraction, bitwise operations etc.

• You will learn these functions: cv2.add(), cv2.addWeighted(), etc.

Arithmetic Operations on Images• Image Addition• Image Blending• Bitwise Operations

Image Addition• You can add two images by OpenCV function cv2.add() or simple by numpy operation, res = img1 + img2.

• Both images should be of same depth and type, or second image can just be a scalar value.

Image Addition>>> import cv2>>> import numpy as np>>> x = np.uint8([250])>>> y = np.uint8([10])

>>> print cv2.add(x,y) [[255]] # 250 + 10 = 260 ==> 255>>> print x+y[4] # 250 + 10 = 260 % 256 = 4

How do I check the variable type>>> x = np.array([1, 2])>>> print x.dtypeint32>>> x = np.uint8([250])>>> print x.dtypeUint8>>> x = np.array([1, 2], dtype=np.int64)int64

How do I check the variable type>>> import numpy as np>>> np.arange(10000)array([ 0, 1, 2, ..., 9997, 9998, 9999])>>> np.set_printoptions(threshold=np.inf)>>> x = np.arange(10000)>>> print x

Image Blending• This is also image addition, but different weights are given to images so that it gives a feeling of blending or transparency.

• Images are added as per the equation below:

Image Blending: image size: 512x512

Image Blending: Example#!/usr/bin/python

import cv2import numpy as np

img = cv2.imread(imgName)img1 = cv2.imread('image/watermark.png')alpha = 0.8beta = (1.0 - alpha)dst = cv2.addWeighted(img, alpha, img1, beta, 0.0, 0)

cv2.imshow('blend',dst)cv2.waitKey(0)cv2.destroyAllWindows()

Image Blending: result• Try to change a parameter to another values.

Bitwise Operations• This includes bitwise AND, OR, NOT and XOR operations.

• They will highly useful while extracting any part of the image, defining and working with non-rectangular ROI etc.

Bitwise Operations: example#!/usr/bin/python

import cv2 # Using OpenCVimport numpy as np

# Load an color imageimgName = 'image/lena.png'imgWatermark = 'image/watermark-small.png'img1 = cv2.imread(imgName)img2 = cv2.imread(imgWatermark)

# want to put watermark on top-left corner, then create a ROI (Region of Interest)rows,cols,channels = img2.shaperoi = img1[0:rows, 0:cols]

Bitwise Operations: example# Now create a mask of watermark and create its #inverse mask alsoimg2gray = cv2.cvtColor(img2,cv2.COLOR_BGR2GRAY)ret, mask = cv2.threshold(img2gray, 10, 255, \ cv2.THRESH_BINARY)mask_inv = cv2.bitwise_not(mask)

# Now black-out the area of logo in ROIimg1_bg = cv2.bitwise_and(roi,roi,mask = mask_inv)

Bitwise Operations: example# Take only region of logo from logo image.img2_fg = cv2.bitwise_and(img2,img2,mask = mask)

# Put logo in ROI and modify the main imagedst = cv2.add(img1_bg, img2_fg)img1[0:rows, 0:cols] = dst

cv2.imshow('res',img1)cv2.waitKey(0)cv2.destroyAllWindows()

Bitwise Operations

Trick: Connect to web camera• Using VLC player to capture device such as web camera.–VLC: Media >> Open Capture Device–Capture Device tap: Select Video device name from a list (/dev/video0)

–Then, click at “play” button

Trick: Connect to web cameraimport numpy as npimport cv2

cap = cv2.VideoCapture(0) # (/dev/video0)while (True): # Capture frame-by-frame ret, frame = cap.read()

# Our operations on the frame come here gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

# Display the resulting frame cv2.imshow('frame',gray) if cv2.waitKey(1) & 0xFF == ord('q'): break

# When everything done, release the capturecap.release()cv2.destroyAllWindows()

Trick: Connect to web camera

• https://media.readthedocs.org/pdf/opencv-python-tutroals/latest/opencv-python-tutroals.pdf•

References• http://biop.epfl.ch/pdf/Basic%20Image%20Processing.pdf

• http://matplotlib.org/users/image_tutorial.html

• http://docs.opencv.org/3.0-beta/doc/py_tutorials/py_core/py_image_arithmetics/py_image_arithmetics.html

• http://cs231n.github.io/python-numpy-tutorial/#numpy-datatypes

• https://media.readthedocs.org/pdf/opencv-python-tutroals/latest/opencv-python-tutroals.pdf

•