Getting bounding boxes on words instead of letters
up vote
0
down vote
favorite
I am trying to put bounding boxes on each word which are there in a document. I have succeeded in putting bounding boxes on more or less each letter, but am unable to put bounding boxes on each word. I am using the code below for the same
im_ns = cv.imread('image.jpg')
gray = cv.cvtColor(im_ns,cv.COLOR_BGR2GRAY)
blurred_g = cv.GaussianBlur(gray,(11,11),0)
ret, th1 = cv.threshold(blurred_g,127,255,cv.THRESH_BINARY)
th2 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_MEAN_C,cv.THRESH_BINARY,11,2)
th3 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,11,2)
th3_1 = cv.adaptiveThreshold(th3,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,11,2)
plt.figure(figsize=(30,25))
plt.imshow(th3_1)
th3_er = cv.erode(th3_1,None,iterations=1)
th3_di = cv.dilate(th3_er,None,iterations=1)
labels = measure.label(th3_di1, neighbors=8, background=255)
mask = np.zeros(th3_di1.shape, dtype="uint8")
for lab in np.unique(labels):
if lab == 0:
continue
labelMask = np.zeros(th3_di.shape, dtype="uint8")
labelMask[labels == lab] = 255
numPixels = cv.countNonZero(labelMask)
if numPixels > 13:
mask = cv.add(mask, labelMask)
cnts = cv.findContours(mask.copy(), cv.RETR_EXTERNAL,cv.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
cnts = contours.sort_contours(cnts)[0]
t = th3_di.copy()
for (i, c) in enumerate(cnts):
(x,y,w,h) = cv.boundingRect(c)
cv.rectangle(t,(x,y),(x+w,y+h),(0,255),2)
cv.imshow("Image", t)
cv.waitKey(10000)
cv.destroyAllWindows()
The output of the above code can be seen in the link below
opencv image-processing image-segmentation
add a comment |
up vote
0
down vote
favorite
I am trying to put bounding boxes on each word which are there in a document. I have succeeded in putting bounding boxes on more or less each letter, but am unable to put bounding boxes on each word. I am using the code below for the same
im_ns = cv.imread('image.jpg')
gray = cv.cvtColor(im_ns,cv.COLOR_BGR2GRAY)
blurred_g = cv.GaussianBlur(gray,(11,11),0)
ret, th1 = cv.threshold(blurred_g,127,255,cv.THRESH_BINARY)
th2 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_MEAN_C,cv.THRESH_BINARY,11,2)
th3 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,11,2)
th3_1 = cv.adaptiveThreshold(th3,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,11,2)
plt.figure(figsize=(30,25))
plt.imshow(th3_1)
th3_er = cv.erode(th3_1,None,iterations=1)
th3_di = cv.dilate(th3_er,None,iterations=1)
labels = measure.label(th3_di1, neighbors=8, background=255)
mask = np.zeros(th3_di1.shape, dtype="uint8")
for lab in np.unique(labels):
if lab == 0:
continue
labelMask = np.zeros(th3_di.shape, dtype="uint8")
labelMask[labels == lab] = 255
numPixels = cv.countNonZero(labelMask)
if numPixels > 13:
mask = cv.add(mask, labelMask)
cnts = cv.findContours(mask.copy(), cv.RETR_EXTERNAL,cv.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
cnts = contours.sort_contours(cnts)[0]
t = th3_di.copy()
for (i, c) in enumerate(cnts):
(x,y,w,h) = cv.boundingRect(c)
cv.rectangle(t,(x,y),(x+w,y+h),(0,255),2)
cv.imshow("Image", t)
cv.waitKey(10000)
cv.destroyAllWindows()
The output of the above code can be seen in the link below
opencv image-processing image-segmentation
Maybe you can do morphological dilation to merge the letters using a small structure element. Then the connected components are words. Since there is blank space between words, it's less likely that different words are merged.
– Kaiwen Chang
Nov 23 at 13:47
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
I am trying to put bounding boxes on each word which are there in a document. I have succeeded in putting bounding boxes on more or less each letter, but am unable to put bounding boxes on each word. I am using the code below for the same
im_ns = cv.imread('image.jpg')
gray = cv.cvtColor(im_ns,cv.COLOR_BGR2GRAY)
blurred_g = cv.GaussianBlur(gray,(11,11),0)
ret, th1 = cv.threshold(blurred_g,127,255,cv.THRESH_BINARY)
th2 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_MEAN_C,cv.THRESH_BINARY,11,2)
th3 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,11,2)
th3_1 = cv.adaptiveThreshold(th3,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,11,2)
plt.figure(figsize=(30,25))
plt.imshow(th3_1)
th3_er = cv.erode(th3_1,None,iterations=1)
th3_di = cv.dilate(th3_er,None,iterations=1)
labels = measure.label(th3_di1, neighbors=8, background=255)
mask = np.zeros(th3_di1.shape, dtype="uint8")
for lab in np.unique(labels):
if lab == 0:
continue
labelMask = np.zeros(th3_di.shape, dtype="uint8")
labelMask[labels == lab] = 255
numPixels = cv.countNonZero(labelMask)
if numPixels > 13:
mask = cv.add(mask, labelMask)
cnts = cv.findContours(mask.copy(), cv.RETR_EXTERNAL,cv.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
cnts = contours.sort_contours(cnts)[0]
t = th3_di.copy()
for (i, c) in enumerate(cnts):
(x,y,w,h) = cv.boundingRect(c)
cv.rectangle(t,(x,y),(x+w,y+h),(0,255),2)
cv.imshow("Image", t)
cv.waitKey(10000)
cv.destroyAllWindows()
The output of the above code can be seen in the link below
opencv image-processing image-segmentation
I am trying to put bounding boxes on each word which are there in a document. I have succeeded in putting bounding boxes on more or less each letter, but am unable to put bounding boxes on each word. I am using the code below for the same
im_ns = cv.imread('image.jpg')
gray = cv.cvtColor(im_ns,cv.COLOR_BGR2GRAY)
blurred_g = cv.GaussianBlur(gray,(11,11),0)
ret, th1 = cv.threshold(blurred_g,127,255,cv.THRESH_BINARY)
th2 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_MEAN_C,cv.THRESH_BINARY,11,2)
th3 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,11,2)
th3_1 = cv.adaptiveThreshold(th3,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,11,2)
plt.figure(figsize=(30,25))
plt.imshow(th3_1)
th3_er = cv.erode(th3_1,None,iterations=1)
th3_di = cv.dilate(th3_er,None,iterations=1)
labels = measure.label(th3_di1, neighbors=8, background=255)
mask = np.zeros(th3_di1.shape, dtype="uint8")
for lab in np.unique(labels):
if lab == 0:
continue
labelMask = np.zeros(th3_di.shape, dtype="uint8")
labelMask[labels == lab] = 255
numPixels = cv.countNonZero(labelMask)
if numPixels > 13:
mask = cv.add(mask, labelMask)
cnts = cv.findContours(mask.copy(), cv.RETR_EXTERNAL,cv.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
cnts = contours.sort_contours(cnts)[0]
t = th3_di.copy()
for (i, c) in enumerate(cnts):
(x,y,w,h) = cv.boundingRect(c)
cv.rectangle(t,(x,y),(x+w,y+h),(0,255),2)
cv.imshow("Image", t)
cv.waitKey(10000)
cv.destroyAllWindows()
The output of the above code can be seen in the link below
opencv image-processing image-segmentation
opencv image-processing image-segmentation
asked Nov 22 at 16:07
Arindam Bose
283
283
Maybe you can do morphological dilation to merge the letters using a small structure element. Then the connected components are words. Since there is blank space between words, it's less likely that different words are merged.
– Kaiwen Chang
Nov 23 at 13:47
add a comment |
Maybe you can do morphological dilation to merge the letters using a small structure element. Then the connected components are words. Since there is blank space between words, it's less likely that different words are merged.
– Kaiwen Chang
Nov 23 at 13:47
Maybe you can do morphological dilation to merge the letters using a small structure element. Then the connected components are words. Since there is blank space between words, it's less likely that different words are merged.
– Kaiwen Chang
Nov 23 at 13:47
Maybe you can do morphological dilation to merge the letters using a small structure element. Then the connected components are words. Since there is blank space between words, it's less likely that different words are merged.
– Kaiwen Chang
Nov 23 at 13:47
add a comment |
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53434729%2fgetting-bounding-boxes-on-words-instead-of-letters%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Maybe you can do morphological dilation to merge the letters using a small structure element. Then the connected components are words. Since there is blank space between words, it's less likely that different words are merged.
– Kaiwen Chang
Nov 23 at 13:47