Skip to content
LionrapidLionRapid Docs

Ocr Detect

POST
/ocr/detect
curl --request POST \
  --url https://example.com/ocr/detect \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "image": "example", "model": "paddleocr-vl", "variant": "example", "min_confidence": 0.5 }'

Fast text detection triage — returns bounding boxes, no OCR recognition.

Runs classic PaddleOCR DBNet (~50 ms) to detect text regions in an image. Use this to triage multi-image documents before sending only text-bearing pages to expensive full OCR (2–30 s each).

Only supported by paddleocr-vl (the only deployment with the classic PaddleOCR detector loaded alongside the VL pipeline).

Authorizations

Section titled “Authorizations”

Request Bodyrequired

Section titled “Request Bodyrequired”
Media typeapplication/json
OCRDetectRequest
object
image
required
Image

Base64-encoded image (JPEG, PNG, or PDF page)

string
model
Model

Model name (only paddleocr-vl supports detect)

string
default: paddleocr-vl
variant
Any of:
string
<= 64 characters
min_confidence
Min Confidence

Minimum confidence threshold for text regions

number
default: 0.5 <= 1

Responses

Section titled “Responses”

200

Section titled “200”

Successful Response

Media typeapplication/json
OCRDetectResponse
object
has_text
required
Has Text

Whether any text regions were detected

boolean
num_regions
required
Num Regions

Number of detected text regions

integer
regions
Regions

Detected text regions with bounding boxes

Array<object>
DetectedRegion
object
bbox
required
Bbox

Bounding box [x, y, width, height] in pixels

Array<number>
>= 4 items <= 4 items
confidence
required
Confidence

Detection confidence score (0–1)

number
<= 1
processing_time_ms
required
Processing Time Ms

End-to-end processing time in milliseconds

integer
Examplegenerated
{
  "has_text": true,
  "num_regions": 1,
  "regions": [
    {
      "bbox": [
        1
      ],
      "confidence": 1
    }
  ],
  "processing_time_ms": 1
}

422

Section titled “422”

Validation Error

Media typeapplication/json
HTTPValidationError
object
detail
Detail
Array<object>
ValidationError
object
loc
required
Location
Array
msg
required
Message
string
type
required
Error Type
string
input
Input
ctx
Context
object
Examplegenerated
{
  "detail": [
    {
      "loc": [
        "example"
      ],
      "msg": "example",
      "type": "example",
      "input": "example",
      "ctx": {}
    }
  ]
}