qrdet 1.5

Robust QR Detector based on YOLOv7

QRDet

QRDet is a robust QR Detector based on YOLOv7.

QRDet will detect QR codes even in difficult positions or tricky images. If you are looking for a complete QR Detection + Decoding pipeline, take a look at QReader.

Installation

To install QRDet, simply run:

pip install qrdet

Usage

There is only one function you'll need to call to use QRDet, detect:

from qrdet import QRDetector
import cv2

detector = QRDetector()
image = cv2.imread(filename='resources/qreader_test_image.jpeg')
detections = detector.detect(image=image, is_bgr=True)

# Draw the detections
for (x1, y1, x2, y2), confidence in detections:
    cv2.rectangle(image, (x1, y1), (x2, y2), color=(0, 255, 0), thickness=2)
    cv2.putText(image, f'{confidence:.2f}', (x1, y1 - 10), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1,
                color=(0, 255, 0), thickness=2)
# Save the results
cv2.imwrite(filename='resources/qreader_test_image_detections.jpeg', img=image)

API Reference

QReader.detect(image, return_confidences = True, as_float = False, is_bgr = False)

• image: np.ndarray. NumPy Array containing the image to decode. The image is expected to be in uint8 format [HxWxC], RGB or BGR depending on the is_bgr parameter.

• return_confidences: bool. If True, the output will be in the format (((x1, y1, x2, y2), confidence), ...). Otherwise, it will be in the format ((x1, y1, x2, y2), ...). Default: True.

• return_confidences: bool. If True, the returned coordinates will be returned as float, with the complete precision outputted from the detection model. Otherwise, they will be rounded to the closest integer. Default: False.

• is_bgr: bool. If True the image is expected to be in BGR. Otherwise, it will be expected to be RGB. Default: False

• Returns: tuple[tuple[tuple[int, int, int, int], float], ...] | tuple[tuple[int, int, int, int]]: A tuple with the coordinates of all detected QR codes. If return_confidences is True, the output will look like: (((x1, y1, x2, y2), confidence), ...). If return_confidences is False it will look like: ((x1, y1, x2, y2), ...).

Acknowledgements

This library is based on the following projects:

• YoloV7 model for Object Detection.