# hiroi-sora/PaddleOCR-json

OCR离线图片文字识别命令行windows程序，以JSON字符串形式输出结果，方便别的程序调用。提供各种语言API。由 PaddleOCR C++ 编译。

Repository: https://github.com/hiroi-sora/PaddleOCR-json
Canonical: https://ross.abutalabs.com/products/paddleocr-json
Language: C++
License: Apache-2.0
License Family: permissive
Topics: paddleocr, ocr, json-api, paddlepaddle
Last push: 2025-04-07T14:43:56+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 15, release rhythm 8, longevity 100
- inputs: {"age_days": 1618, "days_push": 513, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1542, forks 203 (observed 2026-08-28T04:05:01.145941+00:00)

## What it is
An offline OCR command-line executable compiled from PaddleOCR C++ that recognizes text in images and outputs results as JSON strings. It can be invoked as a subprocess or over TCP, with ready-made APIs for Python and other languages.

## Use cases
- extract text from images offline
- add OCR to my app without writing C++
- batch convert screenshots to text
- recognize text from clipboard images
- call OCR over TCP from another program
- read text from handwriting or stylized fonts

## When to choose
- you need fast, offline OCR with no Python runtime or internet connection
- you want a drop-in OCR engine callable from any language via subprocess or TCP
- you need good accuracy on hard cases like handwriting, small text, or cluttered backgrounds
- you have an AVX-capable x86-64 CPU on Windows or Linux

## When to avoid
- your CPU lacks the AVX instruction set (use RapidOCR- instead)
- you need GPU acceleration or a lightweight deployment footprint (369MB unpacked)
- you need a pure Python OCR pipeline you can modify directly

## Facets
- artifact type: cli-tool
- maturity: active
- function: ocr, cli, image-processing
- domain: computer-vision, image-processing, developer-tools
- platform: windows, cli
- tags: paddleocr, offline-ocr, text-recognition, subprocess, -output, tcp-server, python-api, command-line, linux, docker

## Member repositories
- hiroi-sora/PaddleOCR-json (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:01.145941+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:44.651539+00:00, confidence not recorded.
  - readme: https://github.com/hiroi-sora/PaddleOCR-json (fetched 2026-08-28T04:05:01.145941+00:00, sha 18f4a644b350)
- Data as of 2026-08-30T08:39:29.467469+00:00.