Nyumbani/Dokumentasyonu/breadcrumb.imageRedaction

Ufichaji wa Picha — Mwongozo wa Matumizi

Gundua na funika taarifa binafsi ndani ya skani, picha, na picha za skrini. Mwongozo huu unaelekeza katika mtiririko wa kupakia, kuchambua, kuficha, na kupakua, mipaka ya ukubwa na muundo, uungwaji mkono wa lugha za OCR, na wito wa msingi wa API.

Fungua programu ya wavuti Feature overview

Mtiririko wa kazi: kupakia, kuchambua, kuficha, kupakua

Kila picha hupitia hatua nne zilezile, iwe unatumia programu ya wavuti, unaita API moja kwa moja, au unaita zana ya anonym_legal_redact_image kupitia seva ya MCP.

1. Pakia

Chagua faili ya PNG au JPG. Programu hukagua aina na ukubwa wa faili dhidi ya kikomo cha upakiaji cha mpango wako kabla ya kutuma chochote kwa seva.

2. Chambua

OCR (Tesseract) husoma maandishi kwenye picha na kurekodi mahali kila sehemu ya maandishi ipo. Maandishi hayo yaliyotolewa kisha hupitia kigunduzi kile kile cha PII kinachotumika kwa nyaraka, kikirejesha vyuo vilivyopatikana na nafasi zake — hakuna kilichofichwa bado.

3. Ficha

Rudia ombi ukiweka mode kuwa "redact" ili kufunika kila eneo lililogunduliwa kwa sanduku thabiti jeusi lililochorwa moja kwa moja kwenye pikseli za picha. Huu ni ufichaji wa kuonekana wa mwelekeo mmoja, si usimbaji fiche unaoweza kutenduliwa.

4. Pakua

Picha iliyofichwa hurejeshwa kama faili (PNG au aina ya awali ya maudhui) ambayo unahifadhi kwenye kifaa chako — hakuna kinachobakia kwenye seva baada ya jibu kutumwa.

Mipaka ya ukubwa na pikseli

PNG na JPG (JPEG) pekee ndizo zinazoungwa mkono. Miundo mingine ya raster kama TIFF, BMP, WebP, na GIF haiungwi mkono kwa sasa.
Picha zina kikomo cha 20 MB upande wa seva. Kikomo cha mpango wako mwenyewe kinaweza kuwa cha chini zaidi — mpango wa Basic huweka kikomo cha upakiaji kwa 5 MB (Pro 10 MB, Business 20 MB); mpango wa bure hauhusishi kabisa ufichaji wa picha.
Mwonekano jumla (upana × urefu) una kikomo cha megapikseli 150. Upakiaji unaozidi kikomo hicho hukataliwa kabla ya uchakataji.

Uungwaji mkono wa lugha za OCR

OCR huendeshwa kwenye Tesseract. Sehemu ya lugha katika API hukubali msimbo wa ISO 639-1 (chaguo-msingi "en" kwa Kiingereza) uliolinganishwa na kifurushi cha lugha cha Tesseract — lugha takribani thelathini zimelinganishwa, ikiwa ni pamoja na Kijerumani, Kifaransa, Kihispania, Kiitaliano, Kireno, Kiholanzi, Kipolandi, Kirusi, Kiukreni, Kiarabu, Kiebrania, Kihindi, Kijapani, Kikorea, Kichina, Kithai, Kivietinamu, na Kituruki. Upatikanaji halisi hutegemea vifurushi vipi vya Tesseract vimesakinishwa kwenye mwenyeji wa OCR; lugha isiyopatikana hurudi kwa Kiingereza.

Rejeleo la API

Ufichaji wa picha unapatikana moja kwa moja kupitia API kwa miunganisho isiyopitia programu ya wavuti, na pia kupitia seva ya MCP kama zana ya anonym_legal_redact_image (hali "analyze" au "redact") kwa wateja wa MCP kama Claude.

POST /api/presidio/image

Authentication: Jithibitishe kwa funguo ya Bearer katika kichwa cha Authorization (funguo ya API au kipindi kilichothibitishwa, sawa na sehemu za mwisho za uchambuzi wa maandishi). Maombi bila funguo halali hurejesha 401.

Request body: Tuma mwili wa multipart/form-data. Sehemu za lazima: file (picha ya PNG au JPG) na mode ("analyze" au "redact"). Sehemu za hiari: language (msimbo wa lugha ya OCR ISO 639-1, chaguo-msingi "en"), entities (mfululizo wa JSON wa aina za vyuo vya kuzuia ugunduzi), score_threshold, na fill_color (mode ya redact pekee, chaguo-msingi "black"), operator (redact mode only: "redact" | "replace" | "mask", default "redact"), and mask_char (redact mode with operator="mask" only, default "*").

Response: Katika mode ya analyze, jibu ni JSON: vyuo vilivyogunduliwa (aina, nafasi ya maandishi, na alama ya uhakika) pamoja na sehemu ya tokens_charged. Katika mode ya redact, jibu ni picha iliyofichwa yenyewe (binary, Content-Type image/png au aina ya awali) pamoja na gharama ya token iliyorejeshwa katika kichwa cha X-Tokens-Charged.

Maswali Yanayoulizwa Mara kwa Mara

Ni miundo gani ya picha inayoungwa mkono?

PNG na JPG (JPEG) pekee. Miundo mingine ya raster kama TIFF, BMP, WebP, na GIF haiungwi mkono kwa sasa.

Ni mipaka gani ya ukubwa na mwonekano?

20 MB na megapikseli 150 za mwonekano jumla, zikiwekewa kikomo zaidi na kikomo cha upakiaji cha mpango wako mwenyewe (5 MB kwenye Basic, 10 MB kwenye Pro, 20 MB kwenye Business).

Je, ufichaji wa picha unahitaji mpango wa kulipia?

Ndiyo. Ufichaji wa picha unahitaji mpango wa Basic au zaidi. Mpango wa bure unaunga mkono uanonimishaji wa maandishi tu.

Je, ufichaji unaweza kutenduliwa?

Hapana. Ufichaji hufunika eneo lililogunduliwa kwa sanduku jeusi lisilopenyeza moja kwa moja kwenye pikseli za picha — ufichaji wa mwelekeo mmoja wa kuonekana, si usimbaji fiche unaoweza kutenduliwa kama unavyotoa kifaa cha kuanonimisha maandishi.

Nifanyeje kupiga simu API moja kwa moja badala ya kutumia programu ya wavuti?

Tuma ombi la POST kwa /api/presidio/image na funguo ya Bearer katika kichwa cha Authorization na mwili wa multipart/form-data unaojumuisha file na mode ("analyze" au "redact"). Angalia sehemu ya rejeleo la API hapo juu kwa orodha kamili ya sehemu na umbo la jibu.

Jaribu ufichaji wa picha

Pakia skani, picha, au picha ya skrini na uone PII zilizogunduliwa zikifunikwa ndani ya sekunde chache.

Fungua programu ya wavuti

Limitations / Important note

OCR-based text extraction is probabilistic; low-quality scans and handwriting lower detection recall.
Redaction is a visual, one-way black box over the detected region — not reversible encryption.
This page is informational and is not legal advice.

How we measure — our methodology

About this page

We update this page when our platform or the law changes.

Read our founder note for how we work.

Each change shows up in the timestamp at the top.

We follow these rules

GDPR (EU 2016/679).
ISO/IEC 27001:2022, held by our hosting provider.
NIS2 (EU 2022/2555).
HIPAA safe harbor under 45 CFR § 164.514(b)(2).

Our promise

We do not sell your data.

We do not train models on your text.

We store your files in Germany.

You can delete your account at any time.

You own your work.

Where we run

Our company HQ is in Saarbrücken, Germany. Our servers run in Hetzner's Falkenstein datacenter.

Hetzner holds ISO 27001 certification.

All data stays in the EU.

Backups run every day.

Need help?

Email support@anonym.legal.

We reply within one business day.

How we test

Automated checks run on every release.

Each surface gets its own sweep script and report.

Human reviewers spot-check the output each week.

We test detection against sample documents before each release.

A failing unit or integration run stops the release.

What we never do

We never sell your information to third parties.
We never train models on what you upload.
We never keep your work after you delete it.
We never share keys with any outside firm.
We never run ads inside the product.

Plans in plain words

We sell credits, not seats.

One credit covers one short job.

Long jobs use a few credits each.

Paid plans can buy top-up credits.

Credits reset at the end of each cycle.

Read the plans page for current rates.

Who built this

A small team of engineers and lawyers built this.

We ship from Europe and work in the open.

Our founder note spells out why we started.

Where to start

How the parts fit

A browser add-on cleans text inside Chrome.

A Word plug-in handles drafts in Office.

A small desktop tool works on whole folders.

An agent protocol link feeds large models safely.

All four share one core engine and one rule set.

Words from our team

We started this work after a lunch about cookies.

One friend kept getting odd ads on her phone.

We asked why a court file leaked through a draft.

We sketched the first build on a napkin that week.

By month three we had a tiny demo for a friend.

She used it on her first case the next day.

Common questions we hear

Can the tool read scanned PDFs? Yes, with OCR.

Does it work on long files? Yes, in small chunks.

Can I roll my own rule set? Yes, save it as a preset.

Does it run offline? The desktop build runs offline.

Do you keep my files? No, the cloud build wipes after each run.

Will it learn from my work? No, we never train on inputs.

A short tour of the workflow

Upload a file or paste a snippet of prose.

Pick the entities you want gone from the draft.

Choose a method: replace, mask, hash, encrypt, or redact.

Press run and watch the side panel show each hit.

Skim the result and tweak any rule that misfired.

Save the cleaned file or send it to a teammate.