tesseract: tesseract::ImageThresholder Class Reference

#include <thresholder.h>

Public Member Functions
	ImageThresholder ()

virtual	~ImageThresholder ()

virtual void	Clear ()
	Destroy the Pix if there is one, freeing memory. More...

bool	IsEmpty () const
	Return true if no image has been set. More...

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. More...

bool	IsBinary () const
	Returns true if the source image is binary. More...

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 (PageSegMode pageseg_mode, Pix **pix)

virtual Pix *	GetPixRectThresholds ()

Pix *	GetPixRect ()

virtual Pix *	GetPixRectGrey ()

Protected Member Functions
virtual void	Init ()
	Common initialization shared between SetImage methods. More...

bool	IsFullImage () const
	Return true if we are processing the full image. More...

void	OtsuThresholdRectToPix (Pix src_pix, Pix *out_pix) const

void	ThresholdRectToPix (Pix src_pix, int num_channels, const int thresholds, const int hi_values, Pix *pix) const

Protected Attributes
Pix *	pix_

int	image_width_

int	image_height_

int	pix_channels_

int	pix_wpl_

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 36 of file thresholder.h.

Constructor & Destructor Documentation

◆ ImageThresholder()

tesseract::ImageThresholder::ImageThresholder ( )

Definition at line 32 of file thresholder.cpp.

   : pix_(NULL),
     image_width_(0), image_height_(0),
     pix_channels_(0), pix_wpl_(0),
     scale_(1), yres_(300), estimated_res_(300) {
   SetRectangle(0, 0, 0, 0);
 }

◆ ~ImageThresholder()

tesseract::ImageThresholder::~ImageThresholder ( )

virtual

Definition at line 40 of file thresholder.cpp.

                                     {
   Clear();
 }

Member Function Documentation

◆ Clear()

void tesseract::ImageThresholder::Clear ( )

virtual

Destroy the Pix if there is one, freeing memory.

Definition at line 45 of file thresholder.cpp.

                              {
   pixDestroy(&pix_);
 }

◆ GetImageSizes()

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 132 of file thresholder.cpp.

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

◆ GetPixRect()

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 228 of file thresholder.cpp.

                                   {
   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;
   }
 }

◆ GetPixRectGrey()

Pix * tesseract::ImageThresholder::GetPixRectGrey ( )

virtual

Definition at line 245 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;
 }

◆ GetPixRectThresholds()

Pix * tesseract::ImageThresholder::GetPixRectThresholds ( )

virtual

Definition at line 201 of file thresholder.cpp.

                                             {
   if (IsBinary()) return NULL;
   Pix* pix_grey = GetPixRectGrey();
   int width = pixGetWidth(pix_grey);
   int height = pixGetHeight(pix_grey);
   int* thresholds;
   int* hi_values;
   OtsuThreshold(pix_grey, 0, 0, width, height, &thresholds, &hi_values);
   pixDestroy(&pix_grey);
   Pix* pix_thresholds = pixCreate(width, height, 8);
   int threshold = thresholds[0] > 0 ? thresholds[0] : 128;
   pixSetAllArbitrary(pix_thresholds, threshold);
   delete [] thresholds;
   delete [] hi_values;
   return pix_thresholds;
 }

◆ GetScaledEstimatedResolution()

int tesseract::ImageThresholder::GetScaledEstimatedResolution ( ) const

inline

Definition at line 106 of file thresholder.h.

                                            {
     return scale_ * estimated_res_;
   }

◆ GetScaledYResolution()

int tesseract::ImageThresholder::GetScaledYResolution ( ) const

inline

Definition at line 93 of file thresholder.h.

                                    {
     return scale_ * yres_;
   }

◆ GetScaleFactor()

int tesseract::ImageThresholder::GetScaleFactor ( ) const

inline

Definition at line 79 of file thresholder.h.

                              {
     return scale_;
   }

◆ GetSourceYResolution()

int tesseract::ImageThresholder::GetSourceYResolution ( ) const

inline

Definition at line 90 of file thresholder.h.

                                    {
     return yres_;
   }

◆ Init()

void tesseract::ImageThresholder::Init ( )

protectedvirtual

Common initialization shared between SetImage methods.

Definition at line 219 of file thresholder.cpp.

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

◆ IsBinary()

bool tesseract::ImageThresholder::IsBinary ( ) const

inline

Returns true if the source image is binary.

Definition at line 75 of file thresholder.h.

                         {
     return pix_channels_ == 0;
   }

◆ IsColor()

bool tesseract::ImageThresholder::IsColor ( ) const

inline

Return true if the source image is color.

Definition at line 70 of file thresholder.h.

                        {
     return pix_channels_ >= 3;
   }

◆ IsEmpty()

bool tesseract::ImageThresholder::IsEmpty ( ) const

Return true if no image has been set.

Definition at line 50 of file thresholder.cpp.

                                      {
   return pix_ == NULL;
 }

◆ IsFullImage()

bool tesseract::ImageThresholder::IsFullImage ( ) const

inlineprotected

Return true if we are processing the full image.

Definition at line 152 of file thresholder.h.

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

◆ OtsuThresholdRectToPix()

void tesseract::ImageThresholder::OtsuThresholdRectToPix	(	Pix *	src_pix,
		Pix **	out_pix
	)		const

protected

Definition at line 258 of file thresholder.cpp.

                                                                    {
   PERF_COUNT_START("OtsuThresholdRectToPix")
   int* thresholds;
   int* hi_values;
 
   int num_channels = OtsuThreshold(src_pix, rect_left_, rect_top_, rect_width_,
                                    rect_height_, &thresholds, &hi_values);
   // only use opencl if compiled w/ OpenCL and selected device is opencl
 #ifdef USE_OPENCL
   OpenclDevice od;
   if ((num_channels == 4 || num_channels == 1) &&
       od.selectedDeviceIsOpenCL() && rect_top_ == 0 && rect_left_ == 0 ) {
     od.ThresholdRectToPixOCL((unsigned char*)pixGetData(src_pix), num_channels,
                              pixGetWpl(src_pix) * 4, thresholds, hi_values,
                              out_pix /*pix_OCL*/, rect_height_, rect_width_,
                              rect_top_, rect_left_);
   } else {
 #endif
     ThresholdRectToPix(src_pix, num_channels, thresholds, hi_values, out_pix);
 #ifdef USE_OPENCL
   }
 #endif
   delete [] thresholds;
   delete [] hi_values;
 
   PERF_COUNT_END
 }

◆ SetEstimatedResolution()

void tesseract::ImageThresholder::SetEstimatedResolution ( int ppi )

inline

Definition at line 101 of file thresholder.h.

                                        {
     estimated_res_ = ppi;
   }

◆ SetImage() [1/2]

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 all the image data, so it may be deleted immediately after this call. 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 62 of file thresholder.cpp.

                                                                          {
   int bpp = bytes_per_pixel * 8;
   if (bpp == 0) bpp = 1;
   Pix* pix = pixCreate(width, height, bpp == 24 ? 32 : bpp);
   l_uint32* data = pixGetData(pix);
   int wpl = pixGetWpl(pix);
   switch (bpp) {
   case 1:
     for (int y = 0; y < height; ++y, data += wpl, imagedata += bytes_per_line) {
       for (int x = 0; x < width; ++x) {
         if (imagedata[x / 8] & (0x80 >> (x % 8)))
           CLEAR_DATA_BIT(data, x);
         else
           SET_DATA_BIT(data, x);
       }
     }
     break;
 
   case 8:
     // Greyscale just copies the bytes in the right order.
     for (int y = 0; y < height; ++y, data += wpl, imagedata += bytes_per_line) {
       for (int x = 0; x < width; ++x)
         SET_DATA_BYTE(data, x, imagedata[x]);
     }
     break;
 
   case 24:
     // Put the colors in the correct places in the line buffer.
     for (int y = 0; y < height; ++y, imagedata += bytes_per_line) {
       for (int x = 0; x < width; ++x, ++data) {
         SET_DATA_BYTE(data, COLOR_RED, imagedata[3 * x]);
         SET_DATA_BYTE(data, COLOR_GREEN, imagedata[3 * x + 1]);
         SET_DATA_BYTE(data, COLOR_BLUE, imagedata[3 * x + 2]);
       }
     }
     break;
 
   case 32:
     // Maintain byte order consistency across different endianness.
     for (int y = 0; y < height; ++y, imagedata += bytes_per_line, data += wpl) {
       for (int x = 0; x < width; ++x) {
         data[x] = (imagedata[x * 4] << 24) | (imagedata[x * 4 + 1] << 16) |
                   (imagedata[x * 4 + 2] << 8) | imagedata[x * 4 + 3];
       }
     }
     break;
 
   default:
     tprintf("Cannot convert RAW image to Pix with bpp = %d\n", bpp);
   }
   pixSetYRes(pix, 300);
   SetImage(pix);
   pixDestroy(&pix);
 }

◆ SetImage() [2/2]

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

Pix vs raw, which to use? Pix is the preferred input for efficiency, since raw buffers are copied. SetImage for Pix clones its input, so the source pix may be pixDestroyed immediately after, but may not go away until after the Thresholder has finished with it.

Definition at line 148 of file thresholder.cpp.

                                               {
   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. Guarantee that we always end up with our own copy,
   // not just a clone of the input.
   if (pixGetColormap(src)) {
     Pix* tmp = pixRemoveColormap(src, REMOVE_CMAP_BASED_ON_SRC);
     depth = pixGetDepth(tmp);
     if (depth > 1 && depth < 8) {
       pix_ = pixConvertTo8(tmp, false);
       pixDestroy(&tmp);
     } else {
       pix_ = tmp;
     }
   } else if (depth > 1 && depth < 8) {
     pix_ = pixConvertTo8(src, false);
   } else {
     pix_ = pixCopy(NULL, src);
   }
   depth = pixGetDepth(pix_);
   pix_channels_ = depth / 8;
   pix_wpl_ = pixGetWpl(pix_);
   scale_ = 1;
   estimated_res_ = yres_ = pixGetYRes(pix_);
   Init();
 }

◆ SetRectangle()

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 121 of file thresholder.cpp.

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

◆ SetSourceYResolution()

void tesseract::ImageThresholder::SetSourceYResolution ( int ppi )

inline

Definition at line 86 of file thresholder.h.

                                      {
     yres_ = ppi;
     estimated_res_ = ppi;
   }

◆ ThresholdRectToPix()

void tesseract::ImageThresholder::ThresholdRectToPix	(	Pix *	src_pix,
		int	num_channels,
		const int *	thresholds,
		const int *	hi_values,
		Pix **	pix
	)		const

protected

Threshold the rectangle, taking everything except the src_pix from the class, using thresholds/hi_values to the output pix. NOTE that num_channels is the size of the thresholds and hi_values

Definition at line 291 of file thresholder.cpp.

                                                            {
   PERF_COUNT_START("ThresholdRectToPix")
   *pix = pixCreate(rect_width_, rect_height_, 1);
   uinT32* pixdata = pixGetData(*pix);
   int wpl = pixGetWpl(*pix);
   int src_wpl = pixGetWpl(src_pix);
   uinT32* srcdata = pixGetData(src_pix);
   for (int y = 0; y < rect_height_; ++y) {
     const uinT32* linedata = srcdata + (y + rect_top_) * src_wpl;
     uinT32* pixline = pixdata + y * wpl;
     for (int x = 0; x < rect_width_; ++x) {
       bool white_result = true;
       for (int ch = 0; ch < num_channels; ++ch) {
         int pixel = GET_DATA_BYTE(const_cast<void*>(
                                   reinterpret_cast<const void *>(linedata)),
                                   (x + rect_left_) * num_channels + ch);
         if (hi_values[ch] >= 0 &&
             (pixel > thresholds[ch]) == (hi_values[ch] == 0)) {
           white_result = false;
           break;
         }
       }
       if (white_result)
         CLEAR_DATA_BIT(pixline, x);
       else
         SET_DATA_BIT(pixline, x);
     }
   }
 
   PERF_COUNT_END
 }

◆ ThresholdToPix()

void tesseract::ImageThresholder::ThresholdToPix	(	PageSegMode	pageseg_mode,
		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 182 of file thresholder.cpp.

                                                                          {
   if (pix_channels_ == 0) {
     // We have a binary image, but it still has to be copied, as this API
     // allows the caller to modify the output.
     Pix* original = GetPixRect();
     *pix = pixCopy(NULL, original);
     pixDestroy(&original);
   } else {
     OtsuThresholdRectToPix(pix_, pix);
   }
 }

Member Data Documentation

◆ estimated_res_

int tesseract::ImageThresholder::estimated_res_

protected

Definition at line 180 of file thresholder.h.

◆ image_height_

int tesseract::ImageThresholder::image_height_

protected

Definition at line 174 of file thresholder.h.

◆ image_width_

int tesseract::ImageThresholder::image_width_

protected

Definition at line 173 of file thresholder.h.

◆ pix_

Pix* tesseract::ImageThresholder::pix_

protected

Clone or other copy of the source Pix. The pix will always be PixDestroy()ed on destruction of the class.

Definition at line 171 of file thresholder.h.

◆ pix_channels_

int tesseract::ImageThresholder::pix_channels_

protected

Definition at line 175 of file thresholder.h.

◆ pix_wpl_

int tesseract::ImageThresholder::pix_wpl_

protected

Definition at line 176 of file thresholder.h.

◆ rect_height_

int tesseract::ImageThresholder::rect_height_

protected

Definition at line 184 of file thresholder.h.

◆ rect_left_

int tesseract::ImageThresholder::rect_left_

protected

Definition at line 181 of file thresholder.h.

◆ rect_top_

int tesseract::ImageThresholder::rect_top_

protected

Definition at line 182 of file thresholder.h.

◆ rect_width_

int tesseract::ImageThresholder::rect_width_

protected

Definition at line 183 of file thresholder.h.

◆ scale_

int tesseract::ImageThresholder::scale_

protected

Definition at line 178 of file thresholder.h.

◆ yres_

int tesseract::ImageThresholder::yres_

protected

Definition at line 179 of file thresholder.h.

The documentation for this class was generated from the following files:

ccmain/thresholder.h
ccmain/thresholder.cpp

Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ ImageThresholder()

◆ ~ImageThresholder()

Member Function Documentation

◆ Clear()

◆ GetImageSizes()

◆ GetPixRect()

◆ GetPixRectGrey()

◆ GetPixRectThresholds()

◆ GetScaledEstimatedResolution()

◆ GetScaledYResolution()

◆ GetScaleFactor()

◆ GetSourceYResolution()

◆ Init()

◆ IsBinary()

◆ IsColor()

◆ IsEmpty()

◆ IsFullImage()

◆ OtsuThresholdRectToPix()

◆ SetEstimatedResolution()

◆ SetImage() [1/2]

◆ SetImage() [2/2]

◆ SetRectangle()

◆ SetSourceYResolution()

◆ ThresholdRectToPix()

◆ ThresholdToPix()

Member Data Documentation

◆ estimated_res_

◆ image_height_

◆ image_width_

◆ pix_

◆ pix_channels_

◆ pix_wpl_

◆ rect_height_

◆ rect_left_

◆ rect_top_

◆ rect_width_

◆ scale_

◆ yres_