Face Detection Bounding Box Converter

Build a simple utility that converts face detection results to OpenCV-compatible bounding box format.

Requirements

Create a Python module that converts dlib rectangle objects (from face detection) into OpenCV bounding box tuples with the format (x, y, width, height).

Your solution should:

• Accept a single dlib rectangle and return a bounding box tuple
• Handle multiple rectangles, preserving their order
• Produce output compatible with OpenCV drawing functions

Test Cases

• Given a dlib rectangle with coordinates (50, 100, 150, 200), the output is (50, 100, 100, 100) representing x=50, y=100, w=100, h=100 @test
• Given a list of three dlib rectangles, the function returns three corresponding bounding box tuples in the same order @test
• The output format is compatible with OpenCV's cv2.rectangle() function which expects (x, y, w, h) format @test

Implementation

@generates

API

def convert_detection_to_bbox(rect):
    """
    Convert a face detection rectangle to OpenCV bounding box format.

    Args:
        rect: A dlib rectangle object representing a detected face

    Returns:
        tuple: A 4-element tuple (x, y, w, h) where:
            - x: left coordinate
            - y: top coordinate
            - w: width
            - h: height
    """
    pass

def convert_detections_to_bboxes(rects):
    """
    Convert multiple face detection rectangles to OpenCV bounding box format.

    Args:
        rects: A list of dlib rectangle objects

    Returns:
        list: A list of tuples, each containing (x, y, w, h)
    """
    pass

Dependencies { .dependencies }

imutils { .dependency }

Provides utilities for converting between dlib and OpenCV coordinate formats.

dlib { .dependency }

Face detection library that outputs rectangle objects.