Image-recognition-using-python/test.py at main · SecundoAS/Image-recognition-using-python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
import cv2
import pytesseract as tess
tess.pytesseract.tesseract_cmd = r'../tesseract.exe'
from PIL import Image

thres = 0.50

classNames = []

classFile = './models/coco.names'

with open(classFile, 'rt') as f:
    classNames = f.read().rstrip('\n').split('\n')

configPath = './models/ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt'
weightsPath = './models/frozen_inference_graph.pb'

# Image
img = cv2.imread("./images/torketommel.jpg")
#
# with open(img, 'rb') as imagefile:
#     base64string = base64.b64encode(imagefile.read()).decode('ascii')

# print(base64string)


# image = Image.open('./images/oppvaskmaskin.jpg')
# text = tess.image_to_string(image)
# print(text)

# Character (Text) Recognition

try:
    if cv2.resize is None:
        img = cv2.resize(img, (270, 270))
    net = cv2.dnn_DetectionModel(weightsPath, configPath)
    net.setInputSize(320, 320)
    net.setInputScale(1.0 / 127.5)
    net.setInputMean((127.5, 127.5, 127.5))
    net.setInputSwapRB(True)

    # def getObjects(thres, nms, draw=True, objects=None):
    # if objects is None:
    objects = []

    classIds, confs, bbox = net.detect(img, confThreshold=thres)
    print(classIds, confs, bbox)

    if len(objects) == 0:
        objects = classNames

    objectInfo = []

    if len(classIds) != 0:
        for classId, confidence, box in zip(classIds.flatten(), confs.flatten(), bbox):
            className = classNames[classId - 1]
            if className in objects:
                objectInfo.append([className])
                print(objectInfo)
                # if draw:
                cv2.rectangle(img, box, color=(0, 255, 0), thickness=2)
                cv2.putText(img, className.upper(), (box[0] + 10, box[1] + 30),
                            cv2.FONT_HERSHEY_COMPLEX, 1, (0, 255, 0), 2)
                cv2.putText(img, str(round(confidence * 100, 2)), (box[0] + 200, box[1] + 30),
                            cv2.FONT_HERSHEY_COMPLEX, 1, (0, 255, 0), 2)

        cv2.imshow("Result", img)
        cv2.waitKey(0)
        cv2.destroyAllWindows()  # destroys the window showing image


except Exception as e:
    print(str(e))


# if __name__ == "__main__":
#
#     cap = cv2.VideoCapture(0)
#
#     cap.set(3, 640)
#
#     cap.set(4, 480)
#
#     # cap.set(10,70)
#
#     while True:
#
#         success, img = cap.read()
#
#         result, objectInfo = getObjects(img, 0.45, 0.2, objects=[])
#
#         print(objectInfo)
#
#         cv2.imshow("Output", img)
#
#         if cv2.waitKey(50) & 0xFF == ord('q'):
#             break
#
# cap.release()
#
# cv2.destroyAllWindows()