SlideShare a Scribd company logo

OpenCV+Android.pptx

•Download as PPTX, PDF•
•
V
Vishwas459764

This document provides an overview of computer vision and OpenCV. It defines computer vision as using algorithms to identify patterns in image data. It describes how images are represented digitally as arrays of pixels and how features like edges and corners are important concepts. It introduces OpenCV as an open source library for computer vision with over 2500 algorithms. It supports languages like C++ and Python. OpenCV has modules for tasks like image processing, video analysis, and object detection. The document provides details on OpenCV data structures like Mat and how to get started with OpenCV in Android Studio by importing the module and adding the native libraries.

1 of 46
Computer Vision Programming using Android and Open CV Vishwas Raval,
Computer Vision in brief Computer Vision… what?
 Computer Vision is the process of using a computer based algorithm to identify patterns in the data of images  Basic Steps:  Process the image  Use an algorithm to identify a pattern  Present that pattern in a meaningful way What is Computer Vision?
Image Processing
An “Image” and A “Frame”  Both images and frames are made up of individual pixels organized in a 2 dimensional array.  For a color image, each pixel can be anything from 8 to 32 bits wide.  Most monochrome images use 8 bits per pixel.  A frame is a single image in a video sequence. X Y pixel
“Feature” - A Fundamental Concept in Computer Vision Feature (fchr) n. A prominent or distinctive aspect, quality, or characteristic: a feature of one’s personality; a feature of the landscape. http://www.thefreedictionary.com/feature  The concept of, “a feature of an object” is very important for most computer vision algorithms.  In an image or frame, a feature is a group of pixels with some unique attribute. corner points edge contrast motion
Some Basic “Building Blocks” Algorithms in Computer Vision  Detection  Motion Detection—Finds groups of pixels (features) that are in motion (change in position from one frame to the next).  Line Detection—Finds groups of pixels (features) that are organized in straight lines, along edges.  Face Detection—Finds groups of pixels organized in a group that fits the template of a face.  Tracking  Optical Flow based tracking—A combination of algorithms used to track moving objects in a video using features.
What is Image in Computer?
Digital Image- Representing Image into digits
W H A TISIT
A BEGINNERS GUIDE TOCOMPUTER VISION W H A TISIT
A BEGINNERS GUIDE TOCOMPUTER VISION W H A TISIT
For more precision – Using floating values
Image Classification Classification
Why is it challenging?
COMPUTER VISION HAS SURPRISING APPLICATIONS
OpenCV+Android.pptx
OpenCV+Android.pptx
OpenCV in brief OpenCV… what?
What is OpenCV?  Open source Computer Vision library BSD License http://opencv.org  Originally developed by Intel  Has more than 2500 optimized algorithms  Supports a lot of different languages C, C++, Python, Java but is written natively in C++  Cross platform also available for Android and iOS
Open CV – At Glance
Capabilities
What it is used for?  Human-Computer Interaction (HCI)  Object Recognition  Face Recognition  Gesture Recognition  Motion Tracking  Image Processing  Mobile Robotics  … and so on
Always ask Motivations
Why OpenCV?
OpenCV: pros & cons Specificity OpenCV was made for image processing, Matlab is quite generic Processing Speed 30+ frames/second in real time image processing with OpenCV. Around 4-5 frames/second in Matlab Efficient Matlab needs more system resources than OpenCV  Price (!)
OpenCV: pros & cons  Easy of use Matlab won hands down!  Integrated Development Environment (IDE) you can use Eclipse, Netbeans, Visual Studio, Qt, XCode, Android Studio … even a simple text editor for OpenCV  Matlab has its own IDE  Automatic memory management in OpenCV
OpenCV meets Android
Modules OpenCV has a modular structure: the package includes several shared or static libraries core basic structures and algorithms imgproc image processing algorithms (such as image filtering, geometrical image transformations, histograms, etc.) video video analysis (such as motion estimation and object tracking)
Modules highgui basic operation to read/write/encode images; in C, C++ and Python it provides also basic UI capabilities calib3d camera calibration and 3D reconstruction features2d 2D features framework (feature detectors, descriptors, and descriptor matchers) objdetect detection of objects and other items (e.g., faces, eyes, mugs, people, …)
Modules  ml machine learning classes used for statistical classification, regression and clustering of data  gpu GPU-accelerated algorithms  photo computational photography  ccl OpenCL-accelerated algorithms
Data Structures  We speak about Java API  All the OpenCV classes and methods are placed into the org.opencv.* packages  Mat: The primary image structure in OpenCV 2.x overcomes the “old” IplImage/CvMat problem of (OpenCV x/C API) automatic memory management (more or less in C++) two data parts:  matrix header (contains information about the matrix)  a pointer to the matrix containing the pixel values
Data Structures Point 2D point defined by x, y coordinates  Point first = new Point(2, 3); Size 2D size structure specify the size (width and height) of an image or rectangle Rect 2D rectangle object
Basic Image I/O  Highgui.imread loads an image from file and return the corresponding Mat object  Highui.imwrite save an image on disk
Basic Drawing Operations  Core.circle draws a simple or filled circle with a given center and radius on a given image  Core.line draws a line between two point in the given image  Core.ellipse draws an ellipse outline, a filled ellipse, an elliptic arc, a filled ellipse sector, …  Core.rectangle draws a rectangle outline or a filled rectangle note that negative thickness will fill the rectangle
Color Spaces  Imgproc.cvtColor converts an input image from one color space to another examples:  Important! Images in OpenCV uses BGR instead of RGB  cvtColor(src, dest, Imgproc.COLOR_RGB2GRAY);  cvtColor(src, dest, Imgproc.COLOR_HSV2BGR);  cvtColor(src, dest, Imgproc.COLOR_RGB2BGR);
Getting Started…
Configuring Open CV in Android Studio 1. Extract the downloaded zip file. 2. Open Android Studio and create a new project with package of your choice. 3. Then select File ->New -> Import Module 4. You need to select the OpenCV SDK location. Select OpenCV-android-sdk/sdk/java. Then select Next and Finish. OpenCV sdk is imported as a module.
OpenCV+Android.pptx
Configuring Open CV in Android Studio But it may throw error. Lets see how to fix this. 5. In the project explorer change the project view from Android to Project. Open Project -> openCVLibrary -> build.gradle 6. Change the compileSdkVersion, targetSdkVersion and buildToolsVersion value to the latest version you use. Then sync the project. The errors will be gone.
OpenCV+Android.pptx
Configuring Open CV in Android Studio 7. Switch back to Android view in Project explorer. Right click on the app module and select Open Module Settings. 8. For the app module in the Dependencies tab, select Add -> Module Dependency -> openCVLibrary
OpenCV+Android.pptx
Add Native Library 1. Now we need to add native JNI libraries in our project. These libraries should be added in jniLibs directory. Create a new jniLibs directory in app-> src -> main. 2. Open the extracted OpenCV SDK directory. Switch to OpenCV-android-sdk/sdk/native/libs directory.
Add Native Library 3. You will find directories for many CPU architectures. Copy the required architecture directory to the jniLibs directory. (for eg. Copy x86_64 and armeabi-v7a because if your Android emulator has x86_64 architecture and Phone has armeabi-v7a architecture. Delete all files except libopencv_java3.so. (Deleting is optional)
Demo • See the demo given

More Related Content

OpenCV+Android.pptx

  • 1. Computer Vision Programming using Android and Open CV Vishwas Raval,
  • 2. Computer Vision in brief Computer Vision… what?
  • 3.  Computer Vision is the process of using a computer based algorithm to identify patterns in the data of images  Basic Steps:  Process the image  Use an algorithm to identify a pattern  Present that pattern in a meaningful way What is Computer Vision?
  • 5. An “Image” and A “Frame”  Both images and frames are made up of individual pixels organized in a 2 dimensional array.  For a color image, each pixel can be anything from 8 to 32 bits wide.  Most monochrome images use 8 bits per pixel.  A frame is a single image in a video sequence. X Y pixel
  • 6. “Feature” - A Fundamental Concept in Computer Vision Feature (fchr) n. A prominent or distinctive aspect, quality, or characteristic: a feature of one’s personality; a feature of the landscape. http://www.thefreedictionary.com/feature  The concept of, “a feature of an object” is very important for most computer vision algorithms.  In an image or frame, a feature is a group of pixels with some unique attribute. corner points edge contrast motion
  • 7. Some Basic “Building Blocks” Algorithms in Computer Vision  Detection  Motion Detection—Finds groups of pixels (features) that are in motion (change in position from one frame to the next).  Line Detection—Finds groups of pixels (features) that are organized in straight lines, along edges.  Face Detection—Finds groups of pixels organized in a group that fits the template of a face.  Tracking  Optical Flow based tracking—A combination of algorithms used to track moving objects in a video using features.
  • 8. What is Image in Computer?
  • 11. A BEGINNERS GUIDE TOCOMPUTER VISION W H A TISIT
  • 12. A BEGINNERS GUIDE TOCOMPUTER VISION W H A TISIT
  • 13. For more precision – Using floating values
  • 15. Why is it challenging?
  • 20. What is OpenCV?  Open source Computer Vision library BSD License http://opencv.org  Originally developed by Intel  Has more than 2500 optimized algorithms  Supports a lot of different languages C, C++, Python, Java but is written natively in C++  Cross platform also available for Android and iOS
  • 21. Open CV – At Glance
  • 23. What it is used for?  Human-Computer Interaction (HCI)  Object Recognition  Face Recognition  Gesture Recognition  Motion Tracking  Image Processing  Mobile Robotics  … and so on
  • 26. OpenCV: pros & cons Specificity OpenCV was made for image processing, Matlab is quite generic Processing Speed 30+ frames/second in real time image processing with OpenCV. Around 4-5 frames/second in Matlab Efficient Matlab needs more system resources than OpenCV  Price (!)
  • 27. OpenCV: pros & cons  Easy of use Matlab won hands down!  Integrated Development Environment (IDE) you can use Eclipse, Netbeans, Visual Studio, Qt, XCode, Android Studio … even a simple text editor for OpenCV  Matlab has its own IDE  Automatic memory management in OpenCV
  • 29. Modules OpenCV has a modular structure: the package includes several shared or static libraries core basic structures and algorithms imgproc image processing algorithms (such as image filtering, geometrical image transformations, histograms, etc.) video video analysis (such as motion estimation and object tracking)
  • 30. Modules highgui basic operation to read/write/encode images; in C, C++ and Python it provides also basic UI capabilities calib3d camera calibration and 3D reconstruction features2d 2D features framework (feature detectors, descriptors, and descriptor matchers) objdetect detection of objects and other items (e.g., faces, eyes, mugs, people, …)
  • 31. Modules  ml machine learning classes used for statistical classification, regression and clustering of data  gpu GPU-accelerated algorithms  photo computational photography  ccl OpenCL-accelerated algorithms
  • 32. Data Structures  We speak about Java API  All the OpenCV classes and methods are placed into the org.opencv.* packages  Mat: The primary image structure in OpenCV 2.x overcomes the “old” IplImage/CvMat problem of (OpenCV x/C API) automatic memory management (more or less in C++) two data parts:  matrix header (contains information about the matrix)  a pointer to the matrix containing the pixel values
  • 33. Data Structures Point 2D point defined by x, y coordinates  Point first = new Point(2, 3); Size 2D size structure specify the size (width and height) of an image or rectangle Rect 2D rectangle object
  • 34. Basic Image I/O  Highgui.imread loads an image from file and return the corresponding Mat object  Highui.imwrite save an image on disk
  • 35. Basic Drawing Operations  Core.circle draws a simple or filled circle with a given center and radius on a given image  Core.line draws a line between two point in the given image  Core.ellipse draws an ellipse outline, a filled ellipse, an elliptic arc, a filled ellipse sector, …  Core.rectangle draws a rectangle outline or a filled rectangle note that negative thickness will fill the rectangle
  • 36. Color Spaces  Imgproc.cvtColor converts an input image from one color space to another examples:  Important! Images in OpenCV uses BGR instead of RGB  cvtColor(src, dest, Imgproc.COLOR_RGB2GRAY);  cvtColor(src, dest, Imgproc.COLOR_HSV2BGR);  cvtColor(src, dest, Imgproc.COLOR_RGB2BGR);
  • 38. Configuring Open CV in Android Studio 1. Extract the downloaded zip file. 2. Open Android Studio and create a new project with package of your choice. 3. Then select File ->New -> Import Module 4. You need to select the OpenCV SDK location. Select OpenCV-android-sdk/sdk/java. Then select Next and Finish. OpenCV sdk is imported as a module.
  • 40. Configuring Open CV in Android Studio But it may throw error. Lets see how to fix this. 5. In the project explorer change the project view from Android to Project. Open Project -> openCVLibrary -> build.gradle 6. Change the compileSdkVersion, targetSdkVersion and buildToolsVersion value to the latest version you use. Then sync the project. The errors will be gone.
  • 42. Configuring Open CV in Android Studio 7. Switch back to Android view in Project explorer. Right click on the app module and select Open Module Settings. 8. For the app module in the Dependencies tab, select Add -> Module Dependency -> openCVLibrary
  • 44. Add Native Library 1. Now we need to add native JNI libraries in our project. These libraries should be added in jniLibs directory. Create a new jniLibs directory in app-> src -> main. 2. Open the extracted OpenCV SDK directory. Switch to OpenCV-android-sdk/sdk/native/libs directory.
  • 45. Add Native Library 3. You will find directories for many CPU architectures. Copy the required architecture directory to the jniLibs directory. (for eg. Copy x86_64 and armeabi-v7a because if your Android emulator has x86_64 architecture and Phone has armeabi-v7a architecture. Delete all files except libopencv_java3.so. (Deleting is optional)
  • 46. Demo • See the demo given