Salient Object — Binary Mask (512px)
The binary ground-truth segmentation mask for the salient robot (white = foreground). Compute IoU / F-score of a predicted mask against this file.
Specifications
- Width
- 512
- Height
- 512
- Mode
- L
- Role
- ground-truth mask
- Foreground
- white
- Background
- black
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
“Salient Object — Binary Mask (512px)” is a deterministic Novus Examples fixture for Image segmentation, Subject detection. RGB scenes paired with class or instance masks and documented class IDs and bounding boxes — for scoring semantic and instance segmentation against a known ground truth.
Documented properties for this file: 512×512 · ground-truth mask. 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.
Use the RGB input with its mask or soft-alpha companion. Class IDs and edge kinds are documented in specs — score IoU or boundary error against that ground truth, not a hand label.
Code examples
<img src="salient-mask.png" alt="Example image" width="640" loading="lazy">Related files
- pngPortrait Subject — Binary Mask (512px)The binary ground-truth mask for the portrait subject (white = foreground) — the reference for scoring a portrait cut-out or background blur.
- pngPortrait Subject — Input (512px)A cat 'portrait' on a busy background — a portrait-style subject-detection and matting input, paired with its ground-truth mask.
- pngFruit Still Life on Clutter — Instances (512px)The same four-object fruit still life on a cluttered background — the hard input for instance segmentation and object detection. The indexed instance mask gives per-object ground truth.
- pngFruit Still Life on White — Instances (512px)A four-object fruit still life (apple, orange, banana, grapes) on white — the easy input for instance segmentation and object detection, paired with an indexed instance mask.
- pngIndexed Instance Mask — 4 Objects (512px)An indexed (palette) instance mask for the fruit still life: background = 0 and each fruit painted with its own instance id. Per-object class and normalised bounding box are listed in the specs.
- pngApple — Ground-Truth Alpha Mask (512px)The binary ground-truth alpha mask (white = subject, black = background) for the cluttered-background apple — compute IoU or boundary F-score of a predicted mask against this file.
Generated by generation/images_ai.py. Free for any use, no attribution required — license.