ocr-service

Original：🇨🇳 Chinese

Translated

2 scriptsChecked / no sensitive code detected

High-precision Optical Character Recognition (OCR) service. Supports text detection and extraction for multi-language, multi-format images, and provides text area coordinates and confidence scores, suitable for document digitization and image content analysis.

2installs

Sourcelin-a1/skills-agent

Added on2026-05-02

NPX Install

npx skill4agent add lin-a1/skills-agent ocr-service

SKILL.md Content (Chinese)

View Translation Comparison →

Features

Extract text content from images, supporting multiple image formats and languages.

Calling Method

python

from services.ocr_service.client import OCRServiceClient

client = OCRServiceClient()

# Health check
status = client.health_check()

# OCR recognition
image_base64 = client.image_to_base64("/path/to/image.jpg")
result = client.ocr(image_base64)

# Get recognition results
texts = result["rec_texts"]    # ["Recognized text 1", "Recognized text 2", ...]
scores = result["rec_scores"]  # [0.98, 0.95, ...]

Return Format

json

{
  "doc_preprocessor_res": {"angle": 0},
  "dt_polys": [[x1,y1], [x2,y2], ...],
  "rec_texts": ["Recognized text 1", "Recognized text 2"],
  "rec_scores": [0.98, 0.95]
}

Field Description

```
rec_texts
```
: List of recognized texts
```
rec_scores
```
: Confidence score for each text block
```
dt_polys
```
: Coordinates of detected text areas