{"id":281,"date":"2016-06-24T14:05:48","date_gmt":"2016-06-24T12:05:48","guid":{"rendered":"https:\/\/zaven.co\/blog\/?p=281"},"modified":"2025-04-08T19:55:20","modified_gmt":"2025-04-08T17:55:20","slug":"opencv-advanced-android-development-edge-detection","status":"publish","type":"post","link":"https:\/\/zaven.co\/blog\/opencv-advanced-android-development-edge-detection\/","title":{"rendered":"OpenCV in advanced Android development: Edge detection"},"content":{"rendered":"

In the last Android development tutorial we\u2019ve cover light source detection using OpenCV<\/a>. This time we\u2019ll cover edge detection<\/strong>, which allows us to distinguish objects from background. This task is usually the starting point to more advanced content analysis (e.g. determining object features, quantities etc.).
\n<\/p>\n

Edge detection OpenCV<\/h2>\n

Again, OpenCV makes it easier by providing the Imgproc.Canny()<\/code> method, which does all the work for us. The method itself, nomen omen<\/em>, uses Canny\u2019s algorithm to perform this task.<\/p>\n

\nprivate void detectEdges(Bitmap bitmap) {\n\tMat rgba = new Mat();\n\tUtils.bitmapToMat(bitmap, rgba);\n\n\tMat edges = new Mat(rgba.size(), CvType.CV_8UC1);\n\tImgproc.cvtColor(rgba, edges, Imgproc.COLOR_RGB2GRAY, 4);\n\tImgproc.Canny(edges, edges, 80, 100);\n\n\t\/\/ Don't do that at home or work it's for visualization purpose.\n\tBitmapHelper.showBitmap(this, bitmap, imageView);\n\tBitmap resultBitmap = Bitmap.createBitmap(edges.cols(), edges.rows(), Bitmap.Config.ARGB_8888);\n\tUtils.matToBitmap(edges, resultBitmap);\n\tBitmapHelper.showBitmap(this, resultBitmap, detectEdgesImageView);\n}\n\n<\/code><\/pre>\n
The process is pretty straight-forward:<\/p>\n
    \n
  1. Read the bitmap<\/li>\n
  2. Covert to greyscale<\/li>\n
  3. Apply Canny\u2019s algorithm<\/li>\n<\/ol>\n
    As always, we start by create an array from the initial bitmap.<\/p>\n
    \nMat rgba = new Mat();\nUtils.bitmapToMat(bitmap, rgba);\n<\/code><\/pre>\n
    Next make an array, in which all the calculation results will be saved, and convert the picture to greyscale. And at the end use the Imgproc.Canny()<\/code> method to detect edges<\/strong>.<\/p>\n
    \nMat edges = new Mat(rgba.size(), CvType.CV_8UC1);\nImgproc.cvtColor(rgba, edges, Imgproc.COLOR_RGB2GRAY, 4);\nImgproc.Canny(edges, edges, 80, 100);\n<\/code><\/pre>\n
    The Imgproc.Canny()<\/code> method takes the following parameters:<\/p>\n