def recognizeCharacters(self, image):
global RESIZED_IMAGE_WIDTH, RESIZED_IMAGE_HEIGHT, kNearest
self.text = ""
informations = []
grayBlurredImage = cv2.GaussianBlur(
ImageProcessor.convertImageToGray(image), (5, 5),
0) # convert the image to gray and blur it...
thresholdedImage = cv2.adaptiveThreshold(
grayBlurredImage, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
cv2.THRESH_BINARY_INV, 11, 2)
image, contours, hierarchy = cv2.findContours(thresholdedImage.copy(),
cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
for contour in contours:
information = Information()
information.contour = contour
information.contourArea = cv2.contourArea(information.contour)
if information.isContourValid():
information.boundingRectangle = cv2.boundingRect(
information.contour)
information.calculateRectangle()
informations.append(information)
informations.sort(key=operator.attrgetter(
"rectangle.x")) # sort contours from left to right...
del self.rectangles[:] # clearing the list "rectangles"...
for information in informations:
image = thresholdedImage[
information.rectangle.y:information.rectangle.y +
information.rectangle.height,
information.rectangle.x:information.rectangle.x +
information.rectangle.width]
image = cv2.resize(image,
(RESIZED_IMAGE_WIDTH, RESIZED_IMAGE_HEIGHT))
numpyArray = numpy.float32(
image.reshape(
(1, RESIZED_IMAGE_WIDTH * RESIZED_IMAGE_HEIGHT
))) # convert type of numpy array from int to float...
returnValue, result, neighborResponse, distance = kNearest.findNearest(
numpyArray, k=1
) # result = vector with results of prediction (regression or classification) for each input sample... it is a single-precision floating-point vector with number_of_samples elements...
if distance > 4712875:
continue
self.text = self.text + str(chr(int(result[0][0])))
self.rectangles.append(information.rectangle)
print "=" + str(distance) + "=" # for debugging purpose...
if len(self.text.strip()) != 0:
print self.text + "\n"
def recognizeCharacters(self, image):
global text, kNearest
text = ""
informations = []
validInformations = []
imgGray = cv2.cvtColor(image,
cv2.COLOR_BGR2GRAY) # get grayscale image
imgBlurred = cv2.GaussianBlur(imgGray, (5, 5), 0) # blur
# filter image from grayscale to black and white
imgThresh = cv2.adaptiveThreshold(
imgBlurred, # input image
255, # make pixels that pass the threshold full white
cv2.
ADAPTIVE_THRESH_GAUSSIAN_C, # use gaussian rather than mean, seems to give better results
cv2.
THRESH_BINARY_INV, # invert so foreground will be white, background will be black
11, # size of a pixel neighborhood used to calculate threshold value
2) # constant subtracted from the mean or weighted mean
imgThreshCopy = imgThresh.copy(
) # make a copy of the thresh image, this in necessary b/c findContours modifies the image
imgContours, contours, npaHierarchy = cv2.findContours(
imgThreshCopy, # input image, make sure to use a copy since the function will modify this image in the course of finding contours
cv2.RETR_EXTERNAL, # retrieve the outermost contours only
cv2.CHAIN_APPROX_SIMPLE
) # compress horizontal, vertical, and diagonal segments and leave only their end points
for contour in contours:
information = Information()
information.contour = contour
information.boundingRectangle = cv2.boundingRect(
information.contour)
information.calculateRectangle()
information.contourArea = cv2.contourArea(information.contour)
informations.append(information)
for information in informations:
if information.isContourValid():
validInformations.append(information)
validInformations.sort(key=operator.attrgetter(
"rectangle.x")) # sort contours from left to right
for information in validInformations:
# cv2.rectangle(image, (information.x, information.y), (information.x + information.width, information.y + information.height), (0, 255, 0), 2)
imgROI = imgThresh[
information.rectangle.y:information.rectangle.y +
information.rectangle.height,
information.rectangle.x:information.rectangle.x +
information.rectangle.width]
imgROIResized = cv2.resize(
imgROI, (self.RESIZED_IMAGE_WIDTH, self.RESIZED_IMAGE_HEIGHT)
) # resize image, this will be more consistent for recognition and storage
npaROIResized = imgROIResized.reshape(
(1, self.RESIZED_IMAGE_WIDTH * self.RESIZED_IMAGE_HEIGHT
)) # flatten image into 1d numpy array
npaROIResized = np.float32(
npaROIResized
) # convert from 1d numpy array of ints to 1d numpy array of floats
retval, npaResults, neigh_resp, dists = kNearest.findNearest(
npaROIResized, k=1)
if dists > 4712875:
continue
self.rectangles.append(information.rectangle)
print "=" + str(dists) + "="
text = text + str(chr(int(
npaResults[0][0]))) # append current char to full string
if len(text.strip()) != 0:
print text + "\n"
return image
