​
Overview

When extracting content with layout information, Pulse API returns bounding box coordinates for text, tables, and images. This spatial data enables precise document understanding and region-based extraction.

​
Bounding Box Format

Bounding boxes are returned as normalized coordinates (0-1 range) in an 8-point format: 
[x1, y1, x2, y2, x3, y3, x4, y4]
Where:
  • (x1, y1) = Top-left corner
  • (x2, y2) = Top-right corner
  • (x3, y3) = Bottom-right corner
  • (x4, y4) = Bottom-left corner
Coordinates are normalized to 0-1 range, making them resolution-independent. To convert to pixels, multiply by the page width/height.

​
Response Structure

The extraction response includes the following arrays: 
{
  "Footer": [],
  "Header": [],
  "Images": [],
  "Tables": [],
  "Text": [],
  "Title": [],
  "Page Number": []
}
Not all fields will be present in every response. The API only includes arrays for elements that were detected in the document.

​
Example Response

Here’s a real example of bounding box data: 
{
  "Images": [
    {
      "bounding_box": [0.01014957264957265, 0.01744186046511628, 0.09241452991452992, 0.01744186046511628, 0.09241452991452992, 0.10719476744186046, 0.01014957264957265, 0.10719476744186046],
      "confidence": "N/A",
      "page_number": 1
    },
    {
      "bounding_box": [0.2013888888888889, 0.005813953488372093, 0.32425213675213677, 0.005087209302325582, 0.3247863247863248, 0.08829941860465117, 0.20192307692307693, 0.08866279069767442],
      "confidence": "N/A",
      "page_number": 1
    }
  ],
  "Tables": [],
  "Text": [
    {
      "average_word_confidence": 0.973,
      "bounding_box": [0.026709401709401708, 0.0872093023255814, 0.06891025641025642, 0.07885174418604651, 0.07425213675213675, 0.09084302325581395, 0.03205128205128205, 0.09956395348837209],
      "content": "0a-NCRI",
      "page_number": 1
    },
    {
      "average_word_confidence": 0.994,
      "bounding_box": [0.2548076923076923, 0.1587936046511628, 0.3680555555555556, 0.16388081395348839, 0.36698717948717946, 0.17732558139534885, 0.2537393162393162, 0.17223837209302326],
      "content": "0a-Dalia Kundu",
      "page_number": 1
    }
  ],
  "Title": [
    {
      "average_word_confidence": 0.995,
      "bounding_box": [0.21955128205128205, 0.1224563953488372, 0.4577991452991453, 0.1348110465116279, 0.45566239316239315, 0.1537063953488372, 0.21741452991452992, 0.14171511627906977],
      "content": "0a-Doctor Prescription",
      "page_number": 1
    }
  ]
}

​
Field Descriptions

​
Text Array

Each text element contains:
  • content: The extracted text
  • bounding_box: 8-point coordinate array
  • page_number: Page where the text appears
  • average_word_confidence: OCR confidence score (0-1)

​
Title Array

Each title element contains:
  • content: The title text
  • bounding_box: 8-point coordinate array
  • page_number: Page where the title appears
  • average_word_confidence: OCR confidence score (0-1)

​
Header Array

Each header element contains:
  • content: The header text
  • bounding_box: 8-point coordinate array
  • page_number: Page where the header appears
  • average_word_confidence: OCR confidence score (0-1)
Each footer element contains:
  • content: The footer text
  • bounding_box: 8-point coordinate array
  • page_number: Page where the footer appears
  • average_word_confidence: OCR confidence score (0-1)

​
Images Array

Each image element contains:
  • bounding_box: 8-point coordinate array
  • page_number: Page where the image appears
  • confidence: Detection confidence (if available)

​
Tables Array

Each table element contains:
  • bounding_box: 8-point coordinate array
  • page_number: Page where the table appears
  • content: Table content (in HTML format)

​
Page Number Array

Each page number element contains:
  • content: The page number text
  • bounding_box: 8-point coordinate array
  • page_number: Page where it appears
  • average_word_confidence: OCR confidence score (0-1)
Tables are extracted and returned in HTML format, preserving the structure and making it easy to parse or display.

​
Converting Coordinates

To convert normalized coordinates to pixel coordinates: 
def normalize_to_pixels(bbox, page_width, page_height):
    """Convert normalized bounding box to pixel coordinates."""
    return [
        bbox[0] * page_width,   # x1
        bbox[1] * page_height,  # y1
        bbox[2] * page_width,   # x2
        bbox[3] * page_height,  # y2
        bbox[4] * page_width,   # x3
        bbox[5] * page_height,  # y3
        bbox[6] * page_width,   # x4
        bbox[7] * page_height   # y4
    ]

# Example: Convert for a standard letter-size page at 72 DPI
page_width = 612  # 8.5 inches * 72 DPI
page_height = 792  # 11 inches * 72 DPI

normalized_bbox = [0.1, 0.1, 0.3, 0.1, 0.3, 0.15, 0.1, 0.15]
pixel_bbox = normalize_to_pixels(normalized_bbox, page_width, page_height)

​
Next Steps

Extract Endpoint

Enable bounding box extraction

Schema Extraction

Combine with structured data