Real-time Barcode Detection with Python, OpenCV, and Pyzbar

In the previous article we generated barcodes; this tutorial shows how a supermarket checkout can recognize them using Python.

First, we open the webcam with OpenCV and define a decode function that uses pyzbar to locate barcodes, draw bounding boxes, and overlay the decoded text and type on the image.

# coding=utf-8
# mac 需要通过命令终端安装zbar
import cv2
import pyzbar.pyzbar as pyzbar

img_path="/Users/XXX/Downloads/test-imgs/"

def decode(image):
    barcodes = pyzbar.decode(image)
    for barcode in barcodes:
        (x, y, w, h) = barcode.rect
        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 0, 255), 2)
        barcodeData = barcode.data.decode("utf-8")
        barcodeType = barcode.type
        text = "Text:" + barcodeData
        text2 = "Type:" + barcodeType
        font = cv2.FONT_HERSHEY_SIMPLEX
        cv2.putText(image, text, (30, 30), font, 0.8, (0, 255, 0), 2)
        cv2.putText(image, text2, (30, 80), font, 0.8, (0, 255, 0), 2)
    return image

Next, the camera function captures frames in a loop, applies decode, resizes the result, displays it, and exits when the user presses q. After the loop the final frame is saved to disk.

def camera():
    camera = cv2.VideoCapture(0)
    while True:
        ret, img = camera.read()
        img = decode(img)
        img = cv2.resize(img, None, fx=0.5, fy=0.5, interpolation=cv2.INTER_CUBIC)
        cv2.imshow("camera", img)
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break
    camera.release()
    cv2.destroyAllWindows()
    cv2.imwrite(img_path+"test01.jpg", img)

if __name__ == '__main__':
    camera()

Finally, a separate snippet demonstrates how to read a saved image, convert it to RGB, and decode any barcodes it contains, printing the extracted text.

import cv2
import pyzbar.pyzbar as pyzbar

image = cv2.imread("/Users/XXX/Downloads/test-imgs.png")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
texts = pyzbar.decode(gray)
for text in texts:
    tt = text.data.decode("utf-8")
    print(tt)

These examples provide a complete, runnable guide for real‑time barcode recognition that can be integrated with a hardware scanner to match stored barcodes and retrieve product prices.