#include <thresholder.h>

Public Member Functions
	ImageThresholder ()
virtual	~ImageThresholder ()
virtual void	Clear ()
	Destroy the Pix if there is one, freeing memory.
bool	IsEmpty () const
	Return true if no image has been set.
void	SetImage (const unsigned char *imagedata, int width, int height, int bytes_per_pixel, int bytes_per_line)
void	SetRectangle (int left, int top, int width, int height)
virtual void	GetImageSizes (int left, int top, int width, int height, int imagewidth, int imageheight)
bool	IsColor () const
	Return true if the source image is color.
bool	IsBinary () const
	Returns true if the source image is binary.
int	GetScaleFactor () const
void	SetSourceYResolution (int ppi)
int	GetSourceYResolution () const
int	GetScaledYResolution () const
void	SetEstimatedResolution (int ppi)
int	GetScaledEstimatedResolution () const
void	SetImage (const Pix *pix)
virtual void	ThresholdToPix (Pix **pix)
Pix *	GetPixRect ()
Pix *	GetPixRectGrey ()
Protected Member Functions
virtual void	Init ()
	Common initialization shared between SetImage methods.
bool	IsFullImage () const
	Return true if we are processing the full image.
void	OtsuThresholdRectToPix (const unsigned char imagedata, int bytes_per_pixel, int bytes_per_line, Pix *pix) const
void	ThresholdRectToPix (const unsigned char imagedata, int bytes_per_pixel, int bytes_per_line, const int thresholds, const int hi_values, Pix *pix) const
void	RawRectToPix (Pix **pix) const
	Copy the raw image rectangle, taking all data from the class, to the Pix.
Protected Attributes
Pix *	pix_
const unsigned char *	image_data_
	Exactly one of pix_ and image_data_ is not NULL.
int	image_width_
int	image_height_
int	image_bytespp_
int	image_bytespl_
int	scale_
int	yres_
int	estimated_res_
int	rect_left_
int	rect_top_
int	rect_width_
int	rect_height_

Detailed Description

Base class for all tesseract image thresholding classes. Specific classes can add new thresholding methods by overriding ThresholdToPix. Each instance deals with a single image, but the design is intended to be useful for multiple calls to SetRectangle and ThresholdTo* if desired.

Definition at line 34 of file thresholder.h.

Constructor & Destructor Documentation

tesseract::ImageThresholder::ImageThresholder ( )

Definition at line 31 of file thresholder.cpp.

  : pix_(NULL),
    image_data_(NULL),
    image_width_(0), image_height_(0),
    image_bytespp_(0), image_bytespl_(0),
    scale_(1), yres_(300), estimated_res_(300) {
  SetRectangle(0, 0, 0, 0);
}

tesseract::ImageThresholder::~ImageThresholder ( ) [virtual]

Definition at line 40 of file thresholder.cpp.

                                    {
  Clear();
}

Member Function Documentation

void tesseract::ImageThresholder::Clear ( ) [virtual]

Destroy the Pix if there is one, freeing memory.

Definition at line 45 of file thresholder.cpp.

                             {
  if (pix_ != NULL) {
    pixDestroy(&pix_);
    pix_ = NULL;
  }
  image_data_ = NULL;
}

void tesseract::ImageThresholder::GetImageSizes	(	int *	left,
		int *	top,
		int *	width,
		int *	height,
		int *	imagewidth,
		int *	imageheight
	)		`[virtual]`

Get enough parameters to be able to rebuild bounding boxes in the original image (not just within the rectangle). Left and top are enough with top-down coordinates, but the height of the rectangle and the image are needed for bottom-up.

Definition at line 99 of file thresholder.cpp.

                                                                        {
  *left = rect_left_;
  *top = rect_top_;
  *width = rect_width_;
  *height = rect_height_;
  *imagewidth = image_width_;
  *imageheight = image_height_;
}

Pix * tesseract::ImageThresholder::GetPixRect ( )

Get a clone/copy of the source image rectangle. The returned Pix must be pixDestroyed. This function will be used in the future by the page layout analysis, and the layout analysis that uses it will only be available with Leptonica, so there is no raw equivalent.

Definition at line 182 of file thresholder.cpp.

                                  {
  if (pix_ != NULL) {
    if (IsFullImage()) {
      // Just clone the whole thing.
      return pixClone(pix_);
    } else {
      // Crop to the given rectangle.
      Box* box = boxCreate(rect_left_, rect_top_, rect_width_, rect_height_);
      Pix* cropped = pixClipRectangle(pix_, box, NULL);
      boxDestroy(&box);
      return cropped;
    }
  }
  // The input is raw, so we have to make a copy of it.
  Pix* raw_pix;
  RawRectToPix(&raw_pix);
  return raw_pix;
}

Pix * tesseract::ImageThresholder::GetPixRectGrey ( )

Get a clone/copy of the source image rectangle, reduced to greyscale. The returned Pix must be pixDestroyed. This function will be used in the future by the page layout analysis, and the layout analysis that uses it will only be available with Leptonica, so there is no raw equivalent.

Definition at line 206 of file thresholder.cpp.

                                      {
  Pix* pix = GetPixRect();  // May have to be reduced to grey.
  int depth = pixGetDepth(pix);
  if (depth != 8) {
    Pix* result = depth < 8 ? pixConvertTo8(pix, false)
                            : pixConvertRGBToLuminance(pix);
    pixDestroy(&pix);
    return result;
  }
  return pix;
}

int tesseract::ImageThresholder::GetScaledEstimatedResolution ( ) const [inline]

Definition at line 106 of file thresholder.h.

                                           {
    return scale_ * estimated_res_;
  }

int tesseract::ImageThresholder::GetScaledYResolution ( ) const [inline]

Definition at line 93 of file thresholder.h.

                                   {
    return scale_ * yres_;
  }

int tesseract::ImageThresholder::GetScaleFactor ( ) const [inline]

Definition at line 79 of file thresholder.h.

                             {
    return scale_;
  }

int tesseract::ImageThresholder::GetSourceYResolution ( ) const [inline]

Definition at line 90 of file thresholder.h.

                                   {
    return yres_;
  }

void tesseract::ImageThresholder::Init ( ) [protected, virtual]

Common initialization shared between SetImage methods.

Definition at line 173 of file thresholder.cpp.

                            {
  SetRectangle(0, 0, image_width_, image_height_);
}

bool tesseract::ImageThresholder::IsBinary ( ) const [inline]

Returns true if the source image is binary.

Definition at line 75 of file thresholder.h.

                        {
    return image_bytespp_ == 0;
  }

bool tesseract::ImageThresholder::IsColor ( ) const [inline]

Return true if the source image is color.

Definition at line 70 of file thresholder.h.

                       {
    return image_bytespp_ >= 3;
  }

bool tesseract::ImageThresholder::IsEmpty ( ) const

Return true if no image has been set.

Definition at line 54 of file thresholder.cpp.

                                     {
  if (pix_ != NULL)
    return false;
  return image_data_ == NULL;
}

bool tesseract::ImageThresholder::IsFullImage ( ) const [inline, protected]

Return true if we are processing the full image.

Definition at line 147 of file thresholder.h.

                           {
    return rect_left_ == 0 && rect_top_ == 0 &&
           rect_width_ == image_width_ && rect_height_ == image_height_;
  }

void tesseract::ImageThresholder::OtsuThresholdRectToPix	(	const unsigned char *	imagedata,
		int	bytes_per_pixel,
		int	bytes_per_line,
		Pix **	pix
	)		const `[protected]`

Otsu threshold the rectangle, taking everything except the image buffer pointer from the class, to the output Pix.

Definition at line 220 of file thresholder.cpp.

                                                               {
  int* thresholds;
  int* hi_values;
  OtsuThreshold(imagedata, bytes_per_pixel, bytes_per_line,
                rect_left_, rect_top_, rect_width_, rect_height_,
                &thresholds, &hi_values);

  // Threshold the image to the given IMAGE.
  ThresholdRectToPix(imagedata, bytes_per_pixel, bytes_per_line,
                     thresholds, hi_values, pix);
  delete [] thresholds;
  delete [] hi_values;
}

void tesseract::ImageThresholder::RawRectToPix ( Pix ** pix ) const [protected]

Copy the raw image rectangle, taking all data from the class, to the Pix.

Definition at line 272 of file thresholder.cpp.

                                                   {
  if (image_bytespp_ < 4) {
    // Go via a tesseract image structure (doesn't copy the data)
    // and use ToPix.
    IMAGE image;
    int bits_per_pixel = image_bytespp_ * 8;
    if (image_bytespp_ == 0)
      bits_per_pixel = 1;
    image.capture(const_cast<uinT8*>(image_data_),
                  image_width_, rect_top_ + rect_height_, bits_per_pixel);
    if (IsFullImage()) {
      *pix = image.ToPix();
    } else {
      IMAGE rect;
      rect.create(rect_width_, rect_height_, bits_per_pixel);
      // The capture chopped the image off at top+height, so copy
      // the rectangle with y = 0 to get a rectangle of height
      // starting at the bottom, since copy_sub_image uses bottom-up coords.
      copy_sub_image(&image, rect_left_, 0, rect_width_, rect_height_,
                     &rect, 0, 0, true);
      *pix = rect.ToPix();
    }
  } else {
    *pix = pixCreate(rect_width_, rect_height_, 32);
    uinT32* data = pixGetData(*pix);
    int wpl = pixGetWpl(*pix);
    const uinT8* imagedata = image_data_ + rect_top_ * image_bytespl_ +
                             rect_left_ * image_bytespp_;
    for (int y = 0; y < rect_height_; ++y) {
      const uinT8* linedata = imagedata;
      uinT32* line = data + y * wpl;
      for (int x = 0; x < rect_width_; ++x) {
        line[x] = (linedata[0] << 24) | (linedata[1] << 16) |
                  (linedata[2] << 8) | linedata[3];
        linedata += 4;
      }
      imagedata += image_bytespl_;
    }
  }
}

void tesseract::ImageThresholder::SetEstimatedResolution ( int ppi ) [inline]

Definition at line 101 of file thresholder.h.

                                       {
    estimated_res_ = ppi;
  }

void tesseract::ImageThresholder::SetImage	(	const unsigned char *	imagedata,
		int	width,
		int	height,
		int	bytes_per_pixel,
		int	bytes_per_line
	)

SetImage makes a copy of only the metadata, not the underlying image buffer. It promises to treat the source as read-only in either case, but in return assumes that the Pix or image buffer remain valid throughout the life of the ImageThresholder. Greyscale of 8 and color of 24 or 32 bits per pixel may be given. Palette color images will not work properly and must be converted to 24 bit. Binary images of 1 bit per pixel may also be given but they must be byte packed with the MSB of the first byte being the first pixel, and a one pixel is WHITE. For binary images set bytes_per_pixel=0.

Definition at line 70 of file thresholder.cpp.

                                                                         {
  if (pix_ != NULL)
    pixDestroy(&pix_);
  pix_ = NULL;
  image_data_ = imagedata;
  image_width_ = width;
  image_height_ = height;
  image_bytespp_ = bytes_per_pixel;
  image_bytespl_ = bytes_per_line;
  scale_ = 1;
  estimated_res_ = yres_ = 300;
  Init();
}

void tesseract::ImageThresholder::SetImage ( const Pix * pix )

Pix vs raw, which to use? Implementations should provide the ability to source and target Pix where possible. A future version of Tesseract may choose to use Pix as its internal representation and discard IMAGE altogether. Because of that, an implementation that sources and targets Pix may end up with less copies than an implementation that does not. NOTE: Opposite to SetImage for raw images, SetImage for Pix clones its input, so the source pix may be pixDestroyed immediately after.

Definition at line 112 of file thresholder.cpp.

                                              {
  image_data_ = NULL;
  if (pix_ != NULL)
    pixDestroy(&pix_);
  Pix* src = const_cast<Pix*>(pix);
  int depth;
  pixGetDimensions(src, &image_width_, &image_height_, &depth);
  // Convert the image as necessary so it is one of binary, plain RGB, or
  // 8 bit with no colormap.
  if (depth > 1 && depth < 8) {
    pix_ = pixConvertTo8(src, false);
  } else if (pixGetColormap(src)) {
    pix_ = pixRemoveColormap(src, REMOVE_CMAP_BASED_ON_SRC);
  } else {
    pix_ = pixClone(src);
  }
  depth = pixGetDepth(pix_);
  image_bytespp_ = depth / 8;
  image_bytespl_ = pixGetWpl(pix_) * sizeof(l_uint32);
  scale_ = 1;
  estimated_res_ = yres_ = pixGetYRes(src);
  Init();
}

void tesseract::ImageThresholder::SetRectangle	(	int	left,
		int	top,
		int	width,
		int	height
	)

Store the coordinates of the rectangle to process for later use. Doesn't actually do any thresholding.

Definition at line 88 of file thresholder.cpp.

                                                                            {
  rect_left_ = left;
  rect_top_ = top;
  rect_width_ = width;
  rect_height_ = height;
}

void tesseract::ImageThresholder::SetSourceYResolution ( int ppi ) [inline]

Definition at line 86 of file thresholder.h.

                                     {
    yres_ = ppi;
    estimated_res_ = ppi;
  }

void tesseract::ImageThresholder::ThresholdRectToPix	(	const unsigned char *	imagedata,
		int	bytes_per_pixel,
		int	bytes_per_line,
		const int *	thresholds,
		const int *	hi_values,
		Pix **	pix
	)		const `[protected]`

Threshold the rectangle, taking everything except the image buffer pointer from the class, using thresholds/hi_values to the output IMAGE.

Definition at line 239 of file thresholder.cpp.

                                                           {
  *pix = pixCreate(rect_width_, rect_height_, 1);
  uinT32* pixdata = pixGetData(*pix);
  int wpl = pixGetWpl(*pix);
  const unsigned char* srcdata = imagedata + rect_top_* bytes_per_line +
                                 rect_left_ * bytes_per_pixel;
  for (int y = 0; y < rect_height_; ++y) {
    const uinT8* linedata = srcdata;
    uinT32* pixline = pixdata + y * wpl;
    for (int x = 0; x < rect_width_; ++x, linedata += bytes_per_pixel) {
      bool white_result = true;
      for (int ch = 0; ch < bytes_per_pixel; ++ch) {
        if (hi_values[ch] >= 0 &&
            (linedata[ch] > thresholds[ch]) == (hi_values[ch] == 0)) {
          white_result = false;
          break;
        }
      }
      if (white_result)
        CLEAR_DATA_BIT(pixline, x);
      else
        SET_DATA_BIT(pixline, x);
    }
    srcdata += bytes_per_line;
  }
}

void tesseract::ImageThresholder::ThresholdToPix ( Pix ** pix ) [virtual]

Threshold the source image as efficiently as possible to the output Pix. Creates a Pix and sets pix to point to the resulting pointer. Caller must use pixDestroy to free the created Pix.

Definition at line 139 of file thresholder.cpp.

                                               {
  if (pix_ != NULL) {
    if (image_bytespp_ == 0) {
      // We have a binary image, so it just has to be cloned.
      *pix = GetPixRect();
    } else {
      if (image_bytespp_ == 4) {
        // Color data can just be passed direct.
        const uinT32* data = pixGetData(pix_);
        OtsuThresholdRectToPix(reinterpret_cast<const uinT8*>(data),
                               image_bytespp_, image_bytespl_, pix);
      } else {
        // Convert 8-bit to IMAGE and then pass its
        // buffer to the raw interface to complete the conversion.
        IMAGE temp_image;
        temp_image.FromPix(pix_);
        OtsuThresholdRectToPix(temp_image.get_buffer(),
                               image_bytespp_,
                               COMPUTE_IMAGE_XDIM(temp_image.get_xsize(),
                                                  temp_image.get_bpp()),
                               pix);
      }
    }
    return;
  }
  if (image_bytespp_ > 0) {
    // Threshold grey or color.
    OtsuThresholdRectToPix(image_data_, image_bytespp_, image_bytespl_, pix);
  } else {
    RawRectToPix(pix);
  }
}