Recherche avancée

Sur d’autres sites (6049)

• YUV420p to other formats, color shift problems

  1er juin 2013, par Sam

  So I'm writing a color detection application using an AR Drone. The drone sends my python/opencv socket server an image from its camera in YUV420p format.

  What I do to access the image as an opencv IPLImage is the following (and yes this is inefficient but I didn't / don't want to have to write new conversion tools myself) :

  1. Save the yuv image to a file (some_image.yuv)
  2. subprocess.call(insert ffmpeg call here)
  3. Read the resultant file (bmp, png, it doesn't matter) back in using cv.LoadImage

  My problem right now is a very noticable color shift. I'm waving a red felt sheet in these pictures. The first one shows a heavy yellow tint. The second isn't as bad but is very rare — mostly when I have the red sheet it's heavily tinted.

  • Tinted image : http://i.stack.imgur.com/BQikM.png
  • Less-tinted image : http://i.stack.imgur.com/ezHyy.png

  I'm wondering both of these things :

  1. if there's either a better way to do this
  2. If the color tinting issue can be resolved

  My ffmpeg conversion line looks something like

  ffmpeg -s 640x480 -vcodec rawvideo -f rawvideo -pix_fmt yuv420p -i image.yuv -vcodec bmp -f image2 output.bmp

  I've also tried :

  ffmpeg -f rawvideo -s 640x480 -pix_fmt yuv420p -vf colormatrix=bt709:bt601 -i image.yuv -f image -vcodec png output.png

  The color shift is always there, unfortunately !

  The color shift is my big problem right now as I later convert the image to HSV and use thresholding to choose a color range that works for me.

• Unable to recognize text with 100 % accuracy in a jpg file using Tess4J

  21 février 2013, par sonali mishra

  I want to split a .flv video file into .jpg/png frames of good resolution & then want to recognize the character sequence in it using Tess4J tool (JNA wrapper around Tesseract).

  Currently I tried the ffmpeg command line tool to split the .flv video file into jpg images.The ffmpeg command I used is :

  ffmpeg -i myinput.flv myoutput%d.jpg

  It is giving me the output image having the detail :

  Image Dimensions : 1280 * 696

  Horizontal resolution : 96 dpi

  Vertical resolution : 96 dpi

  bit depth : 24

  My Problem is :
  I tried to recognize the characters in the video frames(jpg image files which i splitted) using the following code snippet using Tess4J, it is recognizing the characters, but not identifying with 100 % accuracy. It is adding some junk characters as well which is not there in the image.

  Java code snippet I am using :

  import java.io.BufferedWriter
  
  
  
  import java.io.File;
  
  
  
  import java.io.FileWriter;
  
  
  
  import java.io.IOException; 
  
  
  
  import net.sourceforge.tess4j.Tesseract;
  
  
  
  import net.sourceforge.tess4j.TesseractException;
  
  
  
  public class TesseractDemo {
  
  
  
  public static void main(String[] args) {
  
  
  
      File imageFile = new File("D:\\myinput1.jpg");
  
  
  
      Tesseract instance = Tesseract.getInstance();
  
  
  
      // Tesseract1 instance = new Tesseract1();
  
  
  
      try {
  
  
  
          String result = instance.doOCR(imageFile);
  
  
  
          System.out.println(result);
  
  
  
          // write in a file
  
          try {
  
              File file = new File("D:\\myoutput1.txt");
  
              BufferedWriter out = new BufferedWriter(new FileWriter(file));
  
              out.write(result);
  
              out.close();
  
          } catch (IOException ex) {
  
          }
  
  
  
      } catch (TesseractException ep) {
  
          System.err.println(ep.getMessage());
  
      }
  
  
  
  }

  }

  Note : In Tess4J site they have told that the image you are using for doing OCR should be of more than 200 dpi(dot per inch). How to get the jpg image of more than 200 dpi using ffmpeg ??

  Any body having any java code snippet or any suggestion in this regard please help.

• Show a tcp video stream (from FFPLAY / FFMPEG) in an C# application

  27 août 2013, par Rob Quist

  I try to make my Parrot AR Drone 2.0 work with a windows machine.

  I have a simple C# application to control it - but now i want the video stream inside of my application.

  If i execute ffplay tcp://192.168.1.1:5555 it connects to the videostream and shows a window with the video.

  How can i get this video iside of my application ? Like, a simple 'frame' or 'image' that gets filled with that content ?

  I have never worked that much with C# so any help would be awesome.