README.md

@@ -10,7 +10,7 @@ python -m pdf_segmented input.xcf output.pdf
 
 Takes as input a [GIMP](https://www.gimp.org/) XCF file with one layer per page (bottom layer = first page).
 
-Pixels will be considered to be foreground if they are fully black (#000000) and all 8 of their adjacent pixels are also fully black or fully white. All remaining pixels will be considered to be background. This is most easily accomplished by selecting all colour graphics in GIMP, inverting the selection (Ctrl+I), then applying the [Threshold tool](https://docs.gimp.org/3.0/en/gimp-tool-threshold.html).
+All black pixels (#000000) will be considered to be foreground, and all remaining pixels will be considered to be background. This is most easily accomplished by selecting all colour graphics in GIMP, inverting the selection (Ctrl+I), then applying the [Threshold tool](https://docs.gimp.org/3.0/en/gimp-tool-threshold.html).
 
 The foreground will be compressed losslessly using [JBIG2](https://en.wikipedia.org/wiki/JBIG2). The background will be compressed lossily using [JPEG](https://en.wikipedia.org/wiki/JPEG). JPEG quality can be controlled using the `--jpeg-quality` option; the default is the Pillow default (75% at time of writing).
 
@@ -18,10 +18,10 @@ Additional compression algorithms are supported (JPEG 2000, PNG); see `--help` f
 
 ## Dependencies
 
-* [Python 3](https://www.python.org/) (tested using 3.13.7)
+* [Python 3](https://www.python.org/) (tested using 3.13.3)
-	* [NumPy](https://numpy.org/) (tested using 2.3.2)
+	* [NumPy](https://numpy.org/) (tested using 2.2.5)
-	* [Pillow](https://pillow.readthedocs.io/en/stable/) (tested using 11.3.0)
+	* [Pillow](https://pillow.readthedocs.io/en/stable/) (tested using 11.2.1)
-	* [pikepdf](https://pikepdf.readthedocs.io/en/latest/) (tested using 9.10.2)
+	* [pikepdf](https://pikepdf.readthedocs.io/en/latest/) (tested using 9.7.0)
 * [DjVuLibre](https://djvu.sourceforge.net/) (tested using 3.5.28) – for DjVu output
-* [ImageMagick](https://imagemagick.org/) (tested using 7.1.2.3)
+* [ImageMagick](https://imagemagick.org/) (tested using 7.1.1.47)
 * [jbig2enc](https://github.com/agl/jbig2enc) (tested using 0.30) – for JBIG2

pdf_segmented/compression/__init__.py

@@ -43,8 +43,8 @@ class CompressionOptions:
 
 @dataclass
 class CompressedPage:
-	fg: Optional[CompressedLayer]
+	fg: CompressedLayer
-	bg: Optional[CompressedLayer]
+	bg: CompressedLayer
 
 def compress_pages(
 	input_pages: InputPages,
@@ -104,9 +104,6 @@ def compress_layer(
 	tempdir: str
 ) -> CompressedLayer:
 	
-	if layer is None:
-		return None
-	
 	# Compress the given layer
 	if compression == 'iw44':
 		return iw44_compress_layer(layer=layer, dpi=input_pages.dpi, tempdir=tempdir)

pdf_segmented/output/djvu.py

@@ -42,19 +42,16 @@ def djvu_write_pages(
 				# Combine foreground and background
 				_, page_djvu_file = tempfile.mkstemp(suffix='.djvu', dir=tempdir)
 				
+				# TODO: Handle case where empty background or foreground
 				args = ['djvumake', page_djvu_file, 'INFO={},{},{}'.format(input_pages.width, input_pages.height, round(input_pages.dpi))]
-				if compressed_page.fg:
 				args.append('Sjbz={}'.format(compressed_page.fg.filename))
-				if compressed_page.bg:
 				args.append('BG44={}'.format(compressed_page.bg.filename))
 				subprocess.run(args, check=True, capture_output=True)
 				
 				djvu_page_files.append(page_djvu_file)
 			finally:
 				# Clean up
-				if compressed_page.bg:
 				compressed_page.bg.cleanup()
-				if compressed_page.fg:
 				compressed_page.fg.cleanup()
 		
 		# Combine pages

pdf_segmented/output/pdf.py

@@ -42,14 +42,13 @@ def pdf_write_pages(
 		page = pdf.add_blank_page(page_size=(width_pt, height_pt))
 		
 		# Write each layer to the page
+		# TODO: Handle case where empty background or foreground
 		content_instructions = []
 		pdf_write_layer(input_pages=input_pages, pdf=pdf, page=page, layer=compressed_page.bg, is_foreground=False, content_instructions=content_instructions)
 		pdf_write_layer(input_pages=input_pages, pdf=pdf, page=page, layer=compressed_page.fg, is_foreground=True, content_instructions=content_instructions)
 		
 		# Clean up
-		if compressed_page.bg:
 		compressed_page.bg.cleanup()
-		if compressed_page.fg:
 		compressed_page.fg.cleanup()
 		
 		# Generate content stream
@@ -74,9 +73,6 @@ def pdf_write_layer(
 	content_instructions,
 ) -> None:
 	
-	if layer is None:
-		return
-	
 	# Write the layer to PDF
 	if isinstance(layer, JBIG2Layer):
 		pdf_write_image(

pdf_segmented/segmentation.py

@@ -20,12 +20,12 @@ import numpy
 from PIL import Image
 
 from dataclasses import dataclass
-from typing import Generator, List, Optional
+from typing import Generator, List
 
 @dataclass
 class SegmentedPage:
-	fg: Optional[Image]
+	fg: Image
-	bg: Optional[Image]
+	bg: Image
 
 def segment_pages(input_pages: InputPages) -> Generator[SegmentedPage]:
 	for page_num, input_page in enumerate(input_pages.pages):
@@ -39,50 +39,18 @@ def segment_page(input_page: Image) -> SegmentedPage:
 	# Convert image to foreground/background
 	image_rgb = input_page.convert('RGB')
 	numpy_rgb = numpy.asarray(image_rgb)
-	
-	# Precompute black and white pixels
 	black_pixels = (numpy_rgb[:,:,0] == 0) & (numpy_rgb[:,:,1] == 0) & (numpy_rgb[:,:,2] == 0)
-	white_pixels = (numpy_rgb[:,:,0] == 255) & (numpy_rgb[:,:,1] == 255) & (numpy_rgb[:,:,2] == 255)
-	black_or_white = black_pixels | white_pixels
 	
-	# Precompute pixels with all neighbours either black or white
+	# Foreground is only black
-	bw1 = numpy.roll(black_or_white, (1, 1), (0, 1))
-	bw1[0,:] = True
-	bw1[:,0] = True
-	bw2 = numpy.roll(black_or_white, (1, 0), (0, 1))
-	bw2[0,:] = True
-	bw3 = numpy.roll(black_or_white, (1, -1), (0, 1))
-	bw3[0,:] = True
-	bw3[:,-1] = True
-	bw4 = numpy.roll(black_or_white, (0, -1), (0, 1))
-	bw4[:,-1] = True
-	bw5 = numpy.roll(black_or_white, (-1, -1), (0, 1))
-	bw5[-1,:] = True
-	bw5[:,-1] = True
-	bw6 = numpy.roll(black_or_white, (-1, 0), (0, 1))
-	bw6[-1,:] = True
-	bw7 = numpy.roll(black_or_white, (-1, 1), (0, 1))
-	bw7[-1,:] = True
-	bw7[:,0] = True
-	bw8 = numpy.roll(black_or_white, (0, 1), (0, 1))
-	bw8[:,0] = True
-	bw_neighbours = bw1 & bw2 & bw3 & bw4 & bw5 & bw6 & bw7 & bw8
-	
-	# Foreground is only black pixels with all neighbours either black or white
-	fg_pixels = black_pixels & bw_neighbours
-	
-	# Foreground - white out all non-foreground pixels
 	numpy_fg = numpy_rgb.copy()
-	numpy_fg[~fg_pixels,:] = [255, 255, 255]
+	numpy_fg[~black_pixels,:] = [255, 255, 255]
 	image_fg = Image.fromarray(numpy_fg, image_rgb.mode)
 	
-	# Background - white out all foreground pixels
+	# Background is only non-black
 	numpy_bg = numpy_rgb.copy()
-	numpy_bg[fg_pixels,:] = [255, 255, 255]
+	numpy_bg[black_pixels,:] = [255, 255, 255]
 	image_bg = Image.fromarray(numpy_bg, image_rgb.mode)
 	
-	# Handle case where empty background or foreground
+	# TODO: Handle case where empty background or foreground
-	if numpy.any(fg_pixels):
+	
 	return SegmentedPage(fg=image_fg, bg=image_bg)
-	else:
-		return SegmentedPage(fg=None, bg=image_bg)