Skip to content
ai-supply.store
ОбзорКатегорииРейтингиСообществоAgent APIFAQ
ВойтиБесплатная регистрация
catalog / Vision & Image / EasyOCR — Ready-to-Use OCR for 80+ Languages
◆SkillVision & ImageFree

EasyOCR — Ready-to-Use OCR for 80+ Languages

One-line OCR for 80+ languages including Latin, Chinese, Arabic, Devanagari, and Cyrillic — no training required.

@ai-supply
Установки245k
⟳ upstream v1.7.2 · updated 1y ago
↗ Исходный репозиторий
← More Vision & ImageVision & Image leaderboard →How we grade security →Source ↗
! Grade B · 75/100 · ReviewSecurity assessment
✓No compromise signals15capabilities surfaced1known CVE7of 20 OWASP controls clear
Suspicious code patternsExternal endpoints declaredExternal endpoints declaredExternal endpoints declared
scanned 18d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

EasyOCR

EasyOCR provides production-ready optical character recognition for over 80 languages with a minimal API. Built on CRAFT text detection and a ResNet-LSTM-CTC recognition backbone, it handles complex scripts, mixed-language text, and degraded images robustly.

Key Features

  • 80+ language support out of the box (Latin, CJK, Arabic, Cyrillic, Devanagari, …)
  • GPU and CPU inference with automatic device selection
  • Single-line API: readtext(image) returns bounding boxes + text + confidence
  • Paragraph mode for flowing text reconstruction
  • Allowlist/blocklist for domain-specific vocabularies (ID numbers, license plates)
  • CLI: easyocr -l en -f image.jpg --detail 1

Quick Start

import easyocr

reader = easyocr.Reader(["en", "fr"])  # load once
results = reader.readtext("invoice.png")

for bbox, text, confidence in results:
    print(f"{text!r:40s} {confidence:.2f}")

Install via ai-supply

npx ai-supply add easyocr-multilingual-ocr

Curated mirror of the open-source EasyOCR (Apache-2.0). Get it from the source.

Rating rank
#1
of 12 in Vision & Image
Install rank
#6
of 12 in Vision & Image
Security score
75/100 · B
review
Security rank
#7
of 12 in Vision & Image
Installs
245k
cat avg 279k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Vision & Image leaderboard →
! Security: Review · 7575/100 · grade Bscanned 18d ago
✓ no compromise signals16 risk-surface · 8/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · med confidence (static)
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → badge.fury.io, img.shields.io, twitter.com, www.jaided.ai, huggingface.co, pytorch.org., pytorch.org, arxiv.org +15
30 scripts

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 12 pip requirements declared · JaidedAI-EasyOCR-363afb1/requirements.txtrisk surface
•Dependency manifest — 10 pip requirements declared · JaidedAI-EasyOCR-363afb1/trainer/craft/requirements.txtrisk surface
•Vulnerable dependencies — 84 known vulnerabilities in: scipy@1.6.1, torch@1.8.1, pillow@9.5.0, pillow@9.3.0, opencv-python@4.5.3.56, torch@1.13.1 (CWE-1395)known CVE · -25 pts
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · JaidedAI-EasyOCR-363afb1/easyocr/dict/id.txt (CWE-77)risk surface
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — destructive rm -rf / · JaidedAI-EasyOCR-363afb1/Dockerfile (CWE-78)risk surface
•Suspicious code patterns — dynamic code execution · JaidedAI-EasyOCR-363afb1/easyocr/DBNet/DBNet.py (CWE-95)risk surface
•Suspicious code patterns — unsafe yaml.load · JaidedAI-EasyOCR-363afb1/easyocr/easyocr.py (CWE-502)risk surface
•Suspicious code patterns — OS command execution · JaidedAI-EasyOCR-363afb1/easyocr/scripts/compile_dbnet_dcn.py (CWE-78)risk surface
•Suspicious code patterns — pickle deserialization · JaidedAI-EasyOCR-363afb1/trainer/utils.py (CWE-502)risk surface
⚠LLM06Excessive Agencymedium
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · JaidedAI-EasyOCR-363afb1/Dockerfilerisk surface
•External endpoints declared — 14 distinct host(s) · JaidedAI-EasyOCR-363afb1/README.mdrisk surface
•External endpoints declared — 2 distinct host(s) · JaidedAI-EasyOCR-363afb1/custom_model.mdrisk surface
•External endpoints declared — 3 distinct host(s) · JaidedAI-EasyOCR-363afb1/easyocr/DBNet/README.mdrisk surface
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · JaidedAI-EasyOCR-363afb1/easyocr/dict/cs.txt (CWE-272)risk surface
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · JaidedAI-EasyOCR-363afb1/easyocr/dict/en.txt (CWE-272)risk surface
•External endpoints declared — 4 distinct host(s) · JaidedAI-EasyOCR-363afb1/releasenotes.mdrisk surface
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · JaidedAI-EasyOCR-363afb1/trainer/train.py (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM02Sensitive Information DisclosurePassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM07System Prompt LeakagePassed
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 12 pip requirements declared · JaidedAI-EasyOCR-363afb1/requirements.txtrisk surface
•Dependency manifest — 10 pip requirements declared · JaidedAI-EasyOCR-363afb1/trainer/craft/requirements.txtrisk surface
•Vulnerable dependencies — 84 known vulnerabilities in: scipy@1.6.1, torch@1.8.1, pillow@9.5.0, pillow@9.3.0, opencv-python@4.5.3.56, torch@1.13.1 (CWE-1395)known CVE · -25 pts
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · JaidedAI-EasyOCR-363afb1/easyocr/dict/id.txt (CWE-77)risk surface
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — destructive rm -rf / · JaidedAI-EasyOCR-363afb1/Dockerfile (CWE-78)risk surface
•Suspicious code patterns — dynamic code execution · JaidedAI-EasyOCR-363afb1/easyocr/DBNet/DBNet.py (CWE-95)risk surface
•Suspicious code patterns — unsafe yaml.load · JaidedAI-EasyOCR-363afb1/easyocr/easyocr.py (CWE-502)risk surface
•Suspicious code patterns — OS command execution · JaidedAI-EasyOCR-363afb1/easyocr/scripts/compile_dbnet_dcn.py (CWE-78)risk surface
•Suspicious code patterns — pickle deserialization · JaidedAI-EasyOCR-363afb1/trainer/utils.py (CWE-502)risk surface
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (10) · hygiene / uncategorized
•Unrecognized file type — '.gitignore' is not on the allowlist · JaidedAI-EasyOCR-363afb1/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · JaidedAI-EasyOCR-363afb1/Dockerfilerisk surface
•Unrecognized file type — '.in' is not on the allowlist · JaidedAI-EasyOCR-363afb1/MANIFEST.inrisk surface
•Unrecognized file type — '.cpp' is not on the allowlist · JaidedAI-EasyOCR-363afb1/easyocr/DBNet/assets/ops/dcn/src/deform_conv_cpu.cpprisk surface
•Unrecognized file type — '.h' is not on the allowlist · JaidedAI-EasyOCR-363afb1/easyocr/DBNet/assets/ops/dcn/src/deform_conv_cpu_kernel.hrisk surface
•Unrecognized file type — '.cu' is not on the allowlist · JaidedAI-EasyOCR-363afb1/easyocr/DBNet/assets/ops/dcn/src/deform_conv_cuda_kernel.curisk surface
•Suspicious network references — suspicious TLD (22 URLs) · JaidedAI-EasyOCR-363afb1/easyocr/config.pyrisk surface
•Unrecognized file type — '.cfg' is not on the allowlist · JaidedAI-EasyOCR-363afb1/setup.cfgrisk surface
•Unrecognized file type — '.pickle' is not on the allowlist · JaidedAI-EasyOCR-363afb1/unit_test/data/EasyOcrUnitTestPackage.picklerisk surface
•Opaque binary content — non-text payload not statically analyzable · JaidedAI-EasyOCR-363afb1/unit_test/data/EasyOcrUnitTestPackage.picklerisk surface
✔ verified source · pinned JaidedAI-EasyOCR-363afb1
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/easyocr-multilingual-ocr/check). Click a policy:

Consume EasyOCR — Ready-to-Use OCR for 80+ Languages programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/easyocr-multilingual-ocr

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/easyocr-multilingual-ocr/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add easyocr-multilingual-ocr

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/easyocr-multilingual-ocr/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "easyocr-multilingual-ocr" })
OpenAPI spec →
vlatest
! Security: Review · 751mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Бесплатные AI-возможности с проверкой безопасности — skills, MCP, плагины, агенты, датасеты и другое. У каждой своя оценка безопасности и контроль актуальности, и всё создано как для людей, так и для агентов.

api · v3.1status · all green
Контакты
support@ai-supply.storesecurity@ai-supply.store
Каталог
  • Обзор
  • Категории
  • Рейтинги
  • Бенчмарки
  • Безопасность
  • Scan a repo
Сообщество
  • Сообщество
  • FAQ
Для агентов
  • Быстрый старт (60s)
  • Авторизовать агента
  • Agent API
  • Спецификация OpenAPI
Для разработчиков
  • Опубликовать
  • Панель управления
Аккаунт
  • Создать аккаунт
  • Войти
  • Настройки
Правовые документы
  • Условия использования
  • Соглашение издателя
  • Правила допустимого использования
  • Конфиденциальность