Multi-Image Cropping

Feature Overview

The multi-image cropping function can automatically recognize multiple independent images or tickets contained in one page of a document and separately crop them into independent sub-documents. This is particularly useful for scenarios such as processing reimbursement attachments or scans containing multiple receipts.

Use Cases

1. Expense Receipt Pasting Scenario

An A4 paper with multiple tickets laid flat:

Train tickets
Flight itineraries
Multiple taxi invoices
Restaurant invoices

Through the multi-image cropping function, each ticket can be separately recognized and cropped, facilitating subsequent classification and amount extraction.

API Parameter Configuration

Enable Multi-Image Cropping Function

Set crop_flag=true in the upload interface to enable the multi-image cropping function:

curl -X POST \
  -H "x-ti-app-id: <your-app-id>" \
  -H "x-ti-secret-code: <your-secret-code>" \
  -F "file=@/path/to/multi-image-document.pdf" \
  "https://docflow.textin.ai/api/app-api/sip/platform/v2/file/upload?workspace_id=<your-workspace-id>&crop_flag=true"

Parameter Description

Parameter Name	Type	Default Value	Description
`crop_flag`	boolean	false	Whether to enable multi-image cropping function

Example Code

import requests
import json

def upload_with_crop(file_path, workspace_id, app_id, secret_code):
    """
    Upload file and enable multi-image cropping function
    """
    url = "https://docflow.textin.ai/api/app-api/sip/platform/v2/file/upload"
    
    headers = {
        "x-ti-app-id": app_id,
        "x-ti-secret-code": secret_code
    }
    
    params = {
        "workspace_id": workspace_id,
        "crop_flag": "true"  # Enable multi-image cropping function
    }
    
    with open(file_path, 'rb') as file:
        files = {'file': file}
        response = requests.post(url, headers=headers, params=params, files=files)
    
    return response.json()

def fetch_crop_results(workspace_id, batch_number, app_id, secret_code):
    """
    Query multi-image cropping results
    """
    url = "https://docflow.textin.ai/api/app-api/sip/platform/v2/file/fetch"
    
    headers = {
        "x-ti-app-id": app_id,
        "x-ti-secret-code": secret_code
    }
    
    params = {
        "workspace_id": workspace_id,
        "batch_number": batch_number
    }
    
    response = requests.get(url, headers=headers, params=params)
    return response.json()

def parse_crop_coordinates(from_parent_position_list):
    """
    Parse cropping coordinate information
    Coordinate format: [x1, y1, x2, y2, x3, y3, x4, y4]
    Represents the four vertex coordinates of a rectangle
    """
    if len(from_parent_position_list) != 8:
        return None
    
    coordinates = {
        "top_left": (from_parent_position_list[0], from_parent_position_list[1]),
        "top_right": (from_parent_position_list[2], from_parent_position_list[3]),
        "bottom_right": (from_parent_position_list[4], from_parent_position_list[5]),
        "bottom_left": (from_parent_position_list[6], from_parent_position_list[7])
    }
    
    # Calculate bounding box
    x_coords = [coord[0] for coord in coordinates.values()]
    y_coords = [coord[1] for coord in coordinates.values()]
    
    bbox = {
        "x_min": min(x_coords),
        "y_min": min(y_coords),
        "x_max": max(x_coords),
        "y_max": max(y_coords),
        "width": max(x_coords) - min(x_coords),
        "height": max(y_coords) - min(y_coords)
    }
    
    return {"coordinates": coordinates, "bbox": bbox}

# Usage example
if __name__ == "__main__":
    # Configuration information
    WORKSPACE_ID = "your-workspace-id"
    APP_ID = "your-app-id"
    SECRET_CODE = "your-secret-code"
    FILE_PATH = "/path/to/multi-image-document.pdf"
    
    # Upload file and enable multi-image cropping
    upload_result = upload_with_crop(FILE_PATH, WORKSPACE_ID, APP_ID, SECRET_CODE)
    print("Upload result:", json.dumps(upload_result, indent=2, ensure_ascii=False))
    
    # Get batch number
    batch_number = upload_result.get("result", {}).get("batch_number")
    
    if batch_number:
        # Query multi-image cropping results
        fetch_result = fetch_crop_results(WORKSPACE_ID, batch_number, APP_ID, SECRET_CODE)
        print("Multi-image cropping result:", json.dumps(fetch_result, indent=2, ensure_ascii=False))
        
        # Parse coordinate information
        files = fetch_result.get("result", {}).get("files", [])
        for file in files:
            child_files = file.get("child_files", [])
            for child in child_files:
                if child.get("task_type") == 3:  # Sub-file generated by multi-image cropping
                    position_list = child.get("from_parent_position_list")
                    if position_list:
                        coord_info = parse_crop_coordinates(position_list)
                        print(f"Coordinate information for sub-file {child.get('name')}:", coord_info)

Return Result Description