OCR(opencv vs tesseract)

opencv:
For object detection, you're just trying to figure out whether the object is in the frame, and approximately where it's located. The OpenCv features framework is great for this


tesseract:
If your documents have a fixed structured (consistent layout of text fields) then tesseract-ocr is all you need.


I found tesseract easy to use for font based OCR while OpenCV is good for recognizing hand writing.

The following steps worked well with me:

1.Obtain grayscale of image.
2.Perform canny edge detection on grayscale image.
3.Apply gaussian blur on grayscale image(store in seperate matrix)
4.Input matrices from steps 2 & 3 into SWT algorithm
5.Binarize(threshhold) resulting image.
6.Feed image to tesseract.
Please note, for step 4 you will need to build the c++ library in the link and then import into your android project with JNI wrappers. Also, you will need to do micro tweaking for all steps to get the best results. But, this should at least get you started.

some discuss about opencv  vs tesseract on ocr
http://stackoverflow.com/questions/11489824/how-do-i-choose-between-tesseract-and-opencv

image processing to improve tesseract OCR accuracy
1.fix DPI (if needed) 300 DPI is minimum
2.fix text size (e.g. 12 pt should be ok)
3.try to fix text lines (deskew and dewarp text)
4.try to fix illumination of image (e.g. no dark part of image
5.binarize and de-noise image

and some advice
Three points to improve the readability of the image: 1)Resize the image with variable height and width(multiply 0.5 and 1 and 2 with image height and width). 2)Convert the image to Gray scale format(Black and white). 3)Remove the noise pixels and make more clear(Filter the image).

//Resize
 
public Bitmap Resize(Bitmap bmp, int newWidth, int newHeight)
        {

                Bitmap temp = (Bitmap)bmp;

                Bitmap bmap = new Bitmap(newWidth, newHeight, temp.PixelFormat);

                double nWidthFactor = (double)temp.Width / (double)newWidth;
                double nHeightFactor = (double)temp.Height / (double)newHeight;

                double fx, fy, nx, ny;
                int cx, cy, fr_x, fr_y;
                Color color1 = new Color();
                Color color2 = new Color();
                Color color3 = new Color();
                Color color4 = new Color();
                byte nRed, nGreen, nBlue;

                byte bp1, bp2;

                for (int x = 0; x < bmap.Width; ++x)
                {
                    for (int y = 0; y < bmap.Height; ++y)
                    {

                        fr_x = (int)Math.Floor(x * nWidthFactor);
                        fr_y = (int)Math.Floor(y * nHeightFactor);
                        cx = fr_x + 1;
                        if (cx >= temp.Width) cx = fr_x;
                        cy = fr_y + 1;
                        if (cy >= temp.Height) cy = fr_y;
                        fx = x * nWidthFactor - fr_x;
                        fy = y * nHeightFactor - fr_y;
                        nx = 1.0 - fx;
                        ny = 1.0 - fy;

                        color1 = temp.GetPixel(fr_x, fr_y);
                        color2 = temp.GetPixel(cx, fr_y);
                        color3 = temp.GetPixel(fr_x, cy);
                        color4 = temp.GetPixel(cx, cy);

                        // Blue
                        bp1 = (byte)(nx * color1.B + fx * color2.B);

                        bp2 = (byte)(nx * color3.B + fx * color4.B);

                        nBlue = (byte)(ny * (double)(bp1) + fy * (double)(bp2));

                        // Green
                        bp1 = (byte)(nx * color1.G + fx * color2.G);

                        bp2 = (byte)(nx * color3.G + fx * color4.G);

                        nGreen = (byte)(ny * (double)(bp1) + fy * (double)(bp2));

                        // Red
                        bp1 = (byte)(nx * color1.R + fx * color2.R);

                        bp2 = (byte)(nx * color3.R + fx * color4.R);

                        nRed = (byte)(ny * (double)(bp1) + fy * (double)(bp2));

                        bmap.SetPixel(x, y, System.Drawing.Color.FromArgb
                (255, nRed, nGreen, nBlue));
                    }
                }



                bmap = SetGrayscale(bmap);
                bmap = RemoveNoise(bmap);

                return bmap;

        }



//SetGrayscale
 
public Bitmap SetGrayscale(Bitmap img)
        {

            Bitmap temp = (Bitmap)img;
            Bitmap bmap = (Bitmap)temp.Clone();
            Color c;
            for (int i = 0; i < bmap.Width; i++)
            {
                for (int j = 0; j < bmap.Height; j++)
                {
                    c = bmap.GetPixel(i, j);
                    byte gray = (byte)(.299 * c.R + .587 * c.G + .114 * c.B);

                    bmap.SetPixel(i, j, Color.FromArgb(gray, gray, gray));
                }
            }
            return (Bitmap)bmap.Clone();

        }

//RemoveNoise
 
 public Bitmap RemoveNoise(Bitmap bmap)
        {

            for (var x = 0; x < bmap.Width; x++)
            {
                for (var y = 0; y < bmap.Height; y++)
                {
                    var pixel = bmap.GetPixel(x, y);
                    if (pixel.R < 162 && pixel.G < 162 && pixel.B < 162)
                        bmap.SetPixel(x, y, Color.Black);
                }
            }

            for (var x = 0; x < bmap.Width; x++)
            {
                for (var y = 0; y < bmap.Height; y++)
                {
                    var pixel = bmap.GetPixel(x, y);
                    if (pixel.R > 162 && pixel.G > 162 && pixel.B > 162)
                        bmap.SetPixel(x, y, Color.White);
                }
            }

            return bmap;
        }

你可能感兴趣的:(opencv)