CODEWITHSUNDEEP
pythonopencvcomputer-vision
Alessandro Ceccarelli
Alessandro Ceccarelli

Reputation: 1945

Draw multiple rectangles in an image

I am trying to locate rectangles in an image, and apply a classifier to recognize numbers inside each one, using a previously trained classifier:

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()

features = x_train[:8000, :, :]
labels = y_train[:8000]
list_hog_fd = []

for feature in features:
    fd = hog(feature.reshape((28, 28)), orientations=9, pixels_per_cell=(14, 14), cells_per_block=(1, 1), visualise=False)
    list_hog_fd.append(fd)
hog_features = np.array(list_hog_fd, 'float64')


clf = LinearSVC()
clf.fit(hog_features, labels)

imPath = "/Users/alessandro/Downloads/prova prova(2).jpg"
im = cv2.imread(imPath)

# Convert to grayscale and apply Gaussian filtering
im_gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
im_gray = cv2.GaussianBlur(im_gray, (5, 5), 0)

# Threshold the image
ret, im_th = cv2.threshold(im_gray, 90, 255, cv2.THRESH_BINARY_INV)

# Find contours in the image
ctrs, hier = cv2.findContours(im_th.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Get rectangles contains each contour
rects = [cv2.boundingRect(ctr) for ctr in ctrs]

From this point onwards it works perfectly, with my own image, but whenever I start the for loop, it generates empty "roi"s, returning the error "error:

OpenCV(4.0.0) /Users/travis/build/skvark/opencv-python/opencv/modules/imgproc/src/resize.cpp:3784: error: (-215:Assertion failed) !ssize.empty() in function 'resize'"

At line "roi = cv2.resize(roi, (28, 28), interpolation=cv2.INTER_AREA)".

# For each rectangular region, calculate HOG features and predict
# the digit using Linear SVM.
for rect in rects:

    # Draw the rectangles
    cv2.rectangle(im, (rect[0], rect[1]), (rect[0] + rect[2], rect[1] + rect[3]), (0, 255, 0), 3) 

    # Make the rectangular region around the digit
    leng = int(rect[3] * 1.6)
    pt1 = int(rect[1] + rect[3] // 2 - leng // 2)
    pt2 = int(rect[0] + rect[2] // 2 - leng // 2)
    roi = im_th[pt1:pt1+leng, pt2:pt2+leng]

    # Resize the image
    roi = cv2.resize(roi, (28, 28), interpolation=cv2.INTER_AREA)
    roi = cv2.dilate(roi, (3, 3))

    #Calculate the HOG features
    roi_hog_fd = hog(roi, orientations=9, pixels_per_cell=(14, 14), cells_per_block=(1, 1), visualise=False)
    nbr = clf.predict(np.array([roi_hog_fd], 'float64'))
    cv2.putText(im, str(int(nbr[0])), (rect[0], rect[1]),cv2.FONT_HERSHEY_DUPLEX, 2, (0, 255, 255), 3)

cv2.imshow("Resulting Image with Rectangular ROIs", im)
cv2.waitKey()

How can I fix the code?

P.s. For reference, check http://hanzratech.in/2015/02/24/handwritten-digit-recognition-using-opencv-sklearn-and-python.html

Upvotes: 1

Views: 6264

Answers (1)

Martin
Martin

Reputation: 3385

This happens when you copy code.

Steps to solution

1) If you copy code, try to understand what is happening

2) Realize that copying code is not magical. It simply doesnt have to work everywhere

3) If there is error, google the error and try to find out why the error happens

4) If you copy code from tutorial and it doesnt work, dont ask at StackOverflow

5) Your problem is on the lines

# Make the rectangular region around the digit
leng = int(rect[3] * 1.6)
pt1 = int(rect[1] + rect[3] // 2 - leng // 2)
pt2 = int(rect[0] + rect[2] // 2 - leng // 2)
roi = im_th[pt1:pt1+leng, pt2:pt2+leng]

Make sure 

roi

has image dimensions and that it has any pixels in it. You can test it by simply printing the shape like this

print(im_th.shape)
# Make the rectangular region around the digit
leng = int(rect[3] * 1.6)
pt1 = int(rect[1] + rect[3] // 2 - leng // 2)
pt2 = int(rect[0] + rect[2] // 2 - leng // 2)
roi = im_th[pt1:pt1+leng, pt2:pt2+leng]
print(roi.shape)

You will see what is happening

Upvotes: 1

Related Questions