Learn how to integrate our OCR services into your application
import requests
filename = "test.jpg"
api_key = ""
response = requests.post(
"http://localhost:8000/api/ocr/trocr",
headers={"Bearer": api_key},
files={"image": open(filename, "rb")},
)
if response.status_code == 200:
result = response.json()
print(
f"""
Text: {result['text']}
Confidence: {result['confidence']}
Language: {result['language']}
Language Confidence: {result['languageConfidence']}
Processing Time: {result['processingTime']}ms
"""
)
else:
print(f"Error: {response.reason}")
{
"text": "Hello world!",
"confidence": 0.76,
"language": "en",
"languageConfidence": 0.98,
"processingTime": 19.123
}
POST https://alphapen.tech/api/trocr
TrOCR endpoint for text recognition
POST https://alphapen.tech/api/postocr
Post-processing OCR endpoint
POST https://alphapen.tech/api/pipeline
Complete OCR pipeline endpoint
text
The extracted text from the image
confidence
Confidence score of the OCR result (0-1)
language
Detected language code
languageConfidence
Confidence score of language detection (0-1)
processingTime
Time taken to process the request in milliseconds