delivery (gaussian blur)
A delivery typeset over a synthetic photographic background, gaussian blur. Softened by a recorded Gaussian radius, which is what an out-of-focus capture looks like. 29 words, each with an exact bounding box in the companion JSON.
Specifications
- Document
- delivery
- Variant
- blur
- Word Count
- 29
- Font
- consola.ttf
- Box Format
- axis-aligned [x0,y0,x1,y1] in pixels
- Source Plate
- nss-receipt-counter_00001_.png
- Synthetic
- true
- Disclosure
- Synthetic. Background is AI-generated; all text was typeset programmatically.
- Schema Version
- 1
- Transform Gaussian Blur Radius Px
- 1.8
- Alt Text
- A delivery typeset over a synthetic photographic background, gaussian blur
- Alt Text Source
- description
Testing contract
Expected to pass- Scenario
- Run OCR over the image and compare every word and every box against the companion JSON in this group.
- Expected result
- 29 words are recoverable at their recorded boxes for the blur variant; the recorded transform is gaussian blur radius px 1.8. The boxes were transformed WITH the image, so the answer stays exact however damaged the picture is, and a miss is the recogniser's rather than the fixture's.
What is a .png file?
PNG (Portable Network Graphics) is a raster image format using lossless DEFLATE compression. It supports full 8- or 16-bit-per-channel truecolor, palette, and greyscale modes with an optional alpha channel, but no animation. It is the standard choice for screenshots, logos, and graphics with sharp edges or transparency.
How to use this file
Use an example PNG to test image decoders, alpha-compositing, thumbnail generators, and format converters, or to verify that a pipeline preserves transparency and color depth on round-trip.
How to use this file for testing
“delivery (gaussian blur)” is a deterministic Novus Examples fixture for OCR testing. Image-only 'scanned' documents paired with their text source, for measuring OCR accuracy against a known ground truth.
Documented properties for this file: PNG · 643,407 bytes. Compare results against paired or grouped companions on this page when present (clean↔damaged, searchable↔scanned, or format twins) so scores stay reproducible across runs.
Download the file once, keep the path stable in CI or local scripts, and treat the spec table as the contract: dimensions, seeds, field lists, and roles are intentional. Corrupt or invalid samples are labelled as such, expect parsers to fail loudly rather than silently accept them.
For image AI or enhancement tools, run the model or filter on this file and diff against the clean or ground-truth companion in the same group when available. Keep seeds and documented damage parameters in your evaluation notes so regressions are attributable.
Run OCR on the scanned or image twin and score the output against the searchable or text ground truth on this page; the documented rotation, grain, and text content are the reference.
Code examples
<img src="ocr-delivery-blur.png" alt="Example image" width="640" loading="lazy">Related files
- pngBusiness Card (OCR fixture)A rendered business card with a name, title, company, email, phone, and address, paired with a matching vCard so you can measure OCR and contact-extraction accuracy against a known ground truth.
- vcfBusiness Card: vCard (.vcf)The vCard (.vcf) ground truth for the business-card image: the same name, title, company, email, phone, and address in structured form. The positive reference for testing OCR-to-contact extraction.
- pnginvoice (gaussian blur)A invoice typeset over a synthetic photographic background, gaussian blur. Softened by a recorded Gaussian radius, which is what an out-of-focus capture looks like. 33 words, each with an exact bounding box in the companion JSON.
- pnginvoice (low contrast)A invoice typeset over a synthetic photographic background, low contrast. Gain and offset applied so the text sits close to the ground, which is where thresholding fails. 33 words, each with an exact bounding box in the companion JSON.
- pnginvoice (rotated -7 degrees)A invoice typeset over a synthetic photographic background, rotated -7 degrees. Rotated, with every word box rotated with it, so skew correction can be scored rather than eyeballed. 33 words, each with an exact bounding box in the companion JSON.
- pnginvoice (rotated +3 degrees)A invoice typeset over a synthetic photographic background, rotated +3 degrees. A slight skew of the kind a phone photo of a docket actually has. 33 words, each with an exact bounding box in the companion JSON.
Generated by generation/ocr_fixtures_wave.py. Free for any use, no attribution required, license.