How does automatic redaction work?

You select a clip and pick a redaction preset, faces, license plates, or both. The Visylix native engine decodes the clip (H.264 or H.265 input), runs the relevant AI model (Face AI for faces, ANPR for plates), applies a box blur to each detected region on the luma plane and averages the UV planes, then re-encodes with OpenH264. Output is H.264 MP4 with a SHA-256 integrity hash. The whole pipeline is native C++, no FFmpeg subprocess, no PyAV, so a 10-minute clip redacts in roughly 90 seconds on a typical VMS host.

How precise is the redaction region?

Detections return bounding boxes from the AI model, then a polygon-precise clip is applied using ray-casting point-in-polygon tests. This means only pixels inside the detected region are blurred, background context is preserved. For faces, the polygon tracks head rotation frame-to-frame. For plates, the polygon follows the plate's bounding quad. No rectangular over-blur, no accidentally covered evidence.

Is the redaction reversible?

No. The redaction re-encodes the video with blurred regions baked into the compressed bitstream. There is no reverse transform. This is intentional, redaction is only valid for compliance and evidence sharing if it cannot be undone. The SHA-256 hash on the output file provides tamper-evidence: if a single byte changes after redaction, the hash changes, and downstream systems can detect it.

Can I redact a long clip or a batch of clips?

Yes. Every redaction is an async job queued in the engine. You POST a job, get a job ID, and poll the status endpoint for progress percentage and estimated time remaining. Cancel at any time, partially-rendered output is discarded. For long investigations, you can queue dozens of jobs and the engine chews through them in parallel based on available GPU / CPU resources.

Which tier includes redaction?

Face redaction is included on Scale and Enterprise (requires Face AI). Plate redaction is included on Scale and Enterprise with the ANPR add-on (requires ANPR). Enterprise tier gets both face and plate redaction together, plus polygon editing tools for manual redaction of arbitrary regions (useful for exposed whiteboards, screens, or sensitive documents captured in frame).

Faces on Scale · Plates on Scale + ANPR · Both on Enterprise

Redact faces and plates automatically. Ship evidence confidently.

Polygon-precise face and license-plate blur. Native C++ pipeline, no FFmpeg subprocess. H.264 and H.265 input, H.264 output, SHA-256 integrity hash. GDPR and FOIA compliant by default.

Start Free Trial See pricing

Original clip

Faces + plates redacted

Why automatic redaction is the only economical path.

Manual frame-by-frame redaction costs more than most investigations are worth. Automation changes the calculus.

GDPR and FOIA compliance, solved

GDPR Article 17 ("right to be forgotten") and FOIA redaction requirements both require that identifiable third parties be masked before release. Manual frame-by-frame redaction is prohibitively expensive, Visylix automates it with court-ready integrity hashes.

Evidence sharing without exposing bystanders

Security teams routinely share footage with law enforcement, insurance adjusters, and legal counsel. Automatic redaction of non-subject faces and plates removes the privacy-exposure risk from every export, no more accidentally publishing a bystander's identity.

Irreversible by design

Visylix redaction is baked into the compressed bitstream. There is no reverse transform, no "unblur" button. The SHA-256 hash on the output file proves nobody modified the redaction after the fact, critical for chain-of-custody in regulated industries.

How Visylix redaction works under the hood.

No subprocess fork-bombs. No intermediate MP4 writes. Just a tight native pipeline.

Face redaction

Face AI detects every face in frame, tracks them across motion, and applies a luma box blur plus UV plane averaging. Polygon-precise clipping means only facial pixels are redacted, background preserved.

License plate redaction

ANPR detects plates, including partial and angled views. Polygon follows the plate quad frame-to-frame. Ideal for public release of traffic footage or sharing evidence across jurisdictions.

Polygon precision

Ray-casting point-in-polygon test means the blur follows the exact detected region, not a loose rectangle. Head rotation tracked. Plate quads tracked. No accidental over-blur of surrounding evidence.

Native engine, no subprocess

Native C++ pipeline: decode → detect → blur → OpenH264 encode. Zero FFmpeg subprocess, zero PyAV. 10-minute clip redacts in ~90 seconds on a typical VMS host.

SHA-256 integrity hash

Every redacted output file is hashed with SHA-256 at write time. The hash is stored with the clip metadata and included in exported bundles. Tamper-evident by construction.

Async job queue

POST a job, poll progress, cancel if needed. Queue dozens of jobs for long investigations. Engine parallelizes across available GPU / CPU. Partial output discarded on cancel.

The redaction pipeline.

Four stages, one process, zero external tools.

Decode

H.264 or H.265 input decoded by the native engine. No re-muxing, no intermediate file. Direct frame access to detectors.

Detect

Face AI and/or ANPR run inline. Bounding boxes produced per frame. Tracker maintains identity continuity across motion.

Blur

Luma plane: box blur over the detected polygon. UV planes: averaging to desaturate. Polygon-precise, evidence around the face or plate preserved.

Encode

OpenH264 encodes the modified frames back to H.264 MP4. SHA-256 computed incrementally. Output written with integrity hash.

Use case, Hospital

“A patient requested all footage in which they appeared, then asked us to scrub other patients from the clips before release. Before Visylix, that would have been a week of manual frame editing. We turned it around in a day.”

Regional hospital, 340 cameras. HIPAA-compliant workflow: clip selection → auto-redact non-subject faces → SHA-256 integrity bundle → sealed release to patient counsel.

Built for regulated workflows.

GDPR Article 17

“Right to be forgotten” mandates removal of identifiable PII. Visylix redaction provides irreversible face masking with cryptographic proof.

FOIA redaction

Public-records release of surveillance footage requires non-subject masking. Automate the highest-cost step in FOIA response.

HIPAA 164.514

De-identification of protected health information. Visylix face redaction aligns with the Safe Harbor method for video PHI.

Evidence chain-of-custody

SHA-256 integrity hash on every output file. Tamper-evident. Pair with Evidence Lock for full court-admissibility workflow.

Stop paying paralegals to blur faces.

Scale includes face redaction. Add ANPR for plates. Enterprise bundles both , plus polygon editing for arbitrary regions.

Start Free Trial See pricing