/
classify.py
68 lines (56 loc) · 2.33 KB
/
classify.py
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
# import the necessary packages
from __future__ import print_function
from sklearn.externals import joblib
from hog import HOG
import dataset_classify
import argparse
import mahotas
import cv2
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model", required=True, help="path to where the model will be stored")
ap.add_argument("-i", "--image", required= True, help="path to the image file")
args = vars(ap.parse_args())
# load the model
model = joblib.load(args["model"])
# initialize the HOG descriptor
hog = HOG(orientations=9, pixelsPerCell=(4,4), cellsPerBlock=(2,2), normalize=True)
# load the image and convert it to grayscale
image = cv2.imread(args["image"])
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# blur the image, find edges, and then find contours along the edged regions
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
edged = cv2.Canny(blurred, 30, 150)
(cnts, _) = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# sort the contours by their x-axis position, ensuring that we read the numbers from
# left to right
cnts = sorted([(c, cv2.boundingRect(c)[0]) for c in cnts], key=lambda x: x[1])
# loop over the contours
for (c, _) in cnts:
# compute the bounding box for the rectangle
(x, y, w, h) = cv2.boundingRect(c)
# if the width is at least 7 pixels and the height is at least 20 pixels, the contour
# is likely a digit
if w >= 7 and h >= 20:
# crop the ROI and then threshold the grayscale ROI to reveal the digit
roi = gray[y:y + h, x:x + w]
thresh = roi.copy()
T = mahotas.thresholding.otsu(roi)
thresh[thresh > T] = 255
thresh = cv2.bitwise_not(thresh)
# deskew the image center its extent
thresh = dataset_classify.deskew(thresh, 32)
thresh = dataset_classify.center_extent(thresh, (32,32))
# cv2.imshow("thresh", thresh)
# cv2.waitKey(0)
# print(thresh.shape)
# extract features from the image and classify it
hist = hog.describe(thresh)
digit = model.predict(hist.reshape(1, -1))[0]
print("I think that number is: {}".format(digit))
# draw a rectangle around the digit, the show what the digit was classified as
cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 1)
cv2.putText(image, str(digit), (x - 10, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 255, 0), 2)
cv2.imshow("image", image)
cv2.waitKey(0)