confidence of face recognition using opencv

Asked Jun 21 '16 at 10:19

Active Jun 21 '16 at 10:26

Viewed 1,249 times

I tried to recognize faces using eugene face and Local Binary Pattern Histogram algorithms with OpenCV Python.The confidence level achieved with eugene face recognition was 2000,3000 etc. What should be the confidence level if the images were properly recognized ?

for image_path in image_paths:
 predict_image_pil = Image.open(image_path).convert('L')
 predict_image = np.array(predict_image_pil, 'uint8')
 faces = faceCascade.detectMultiScale(predict_image)
 for (x, y, w, h) in faces:
    nbr_predicted, conf = recognizer.predict(predict_image[y: y + h, x: x + w])
    nbr_actual = int(os.path.split(image_path)[1].split(".")[0].replace("subject", ""))
    if nbr_actual == nbr_predicted:
        print "{} is Correctly Recognized with confidence {}".format(nbr_actual, conf)
    else:
        print "{} is Incorrect Recognized as {}".format(nbr_actual,         nbr_predicted)
    cv2.imshow("Recognizing Face", predict_image[y: y + h, x: x + w])

edited Jun 21 '16 at 10:26

asked Jun 21 '16 at 10:19

N.Chandimali

Could you please give a minimal code example or link to the function you used? – Martin Thoma Jun 21 '16 at 10:21
@N.Perera you can refer this question http://stackoverflow.com/questions/13652778/what-is-confidence-in-opencvs-facerecognizer – nawazlj Jun 21 '16 at 10:25
What is the exact meaning of "Confidence Value" and what range should be selected ? – N.Chandimali Jun 21 '16 at 10:33

confidence of face recognition using opencv

0 Answers0