我希望为车辆编号检测创建训练有素的数据。假设车辆编号由具有特殊字符的数字0到9组成。请参考示例图片vehicle plate image。我正在使用此图片创建经过训练的数据training image。用于生成训练数据的python代码如下。
import sys
import numpy as np
import cv2
import os
# module level variables ##########################################################################
MIN_CONTOUR_AREA = 100
RESIZED_IMAGE_WIDTH = 20
RESIZED_IMAGE_HEIGHT = 30
###################################################################################################
def main():
imgTrainingNumbers = cv2.imread("training1.png") # read in training numbers image
if imgTrainingNumbers is None: # if image was not read successfully
print "error: image not read from file \n\n" # print error message to std out
os.system("pause") # pause so user can see error message
return # and exit function (which exits program)
# end if
imgGray = cv2.cvtColor(imgTrainingNumbers, 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
cv2.imshow("imgThresh", imgThresh) # show threshold image for reference
imgThreshCopy = imgThresh.copy() # make a copy of the thresh image, this in necessary b/c findContours modifies the image
_,npaContours, 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
# declare empty numpy array, we will use this to write to file later
# zero rows, enough cols to hold all image data
npaFlattenedImages = np.empty((0, RESIZED_IMAGE_WIDTH * RESIZED_IMAGE_HEIGHT))
intClassifications = [] # declare empty classifications list, this will be our list of how we are classifying our chars from user input, we will write to file at the end
# possible chars we are interested in are digits 0 through 9, put these in list intValidChars
intValidChars = [ord('0'), ord('1'), ord('2'), ord('3'), ord('4'), ord('5'), ord('6'), ord('7'), ord('8'), ord('9'),ord('♿')]
for npaContour in npaContours: # for each contour
if cv2.contourArea(npaContour) > MIN_CONTOUR_AREA: # if contour is big enough to consider
[intX, intY, intW, intH] = cv2.boundingRect(npaContour) # get and break out bounding rect
# draw rectangle around each contour as we ask user for input
cv2.rectangle(imgTrainingNumbers, # draw rectangle on original training image
(intX, intY), # upper left corner
(intX+intW,intY+intH), # lower right corner
(0, 0, 255), # red
2) # thickness
imgROI = imgThresh[intY:intY+intH, intX:intX+intW] # crop char out of threshold image
imgROIResized = cv2.resize(imgROI, (RESIZED_IMAGE_WIDTH, RESIZED_IMAGE_HEIGHT)) # resize image, this will be more consistent for recognition and storage
cv2.imshow("imgROI", imgROI) # show cropped out char for reference
cv2.imshow("imgROIResized", imgROIResized) # show resized image for reference
cv2.imshow("training_numbers.png", imgTrainingNumbers) # show training numbers image, this will now have red rectangles drawn on it
intChar = cv2.waitKey(0) # get key press
if intChar == 27: # if esc key was pressed
sys.exit() # exit program
elif intChar in intValidChars: # else if the char is in the list of chars we are looking for . . .
intClassifications.append(intChar) # append classification char to integer list of chars (we will convert to float later before writing to file)
npaFlattenedImage = imgROIResized.reshape((1, RESIZED_IMAGE_WIDTH * RESIZED_IMAGE_HEIGHT)) # flatten image to 1d numpy array so we can write to file later
npaFlattenedImages = np.append(npaFlattenedImages, npaFlattenedImage, 0)
cv2.imshow("imgROI", npaFlattenedImages)
# add current flattened impage numpy array to list of flattened image numpy arrays
# end if
# end if
# end for
fltClassifications = np.array(intClassifications, np.float32) # convert classifications list of ints to numpy array of floats
npaClassifications = fltClassifications.reshape((fltClassifications.size, 1))
print npaClassifications
# flatten numpy array of floats to 1d so we can write to file later
print "\n\ntraining complete !!\n"
# np.savetxt(str(raw_input('Insert the name of the file (ex: "a.txt"): ')), npaClassifications,delimiter="\t") # write flattened images to file
# np.savetxt((raw_input('a.txt')), npaFlattenedImages)
np.savetxt('testimage_1.txt',npaFlattenedImages) #
np.savetxt('test1_1.txt',npaClassifications)
cv2.destroyAllWindows()
#save(data)
#'a.txt'
#return data # remove windows from memory
#def save(data):
# np.savetxt(str(input('Insert name of the list(ex: a.txt): ')), npaFlattenedImages)
# return
if __name__ == "__main__":
main()
我收到错误
intValidChars = [ord('0'), ord('1'), ord('2'), ord('3'), ord('4'), ord('5'), ord('6'), ord('7'), ord('8'), ord('9'),ord('♿')]
TypeError: ord() expected a character, but string of length 3 found
我如何克服这个错误？
答案 0 :(得分：1)
在python 2中，您可以尝试：
u'♿'
例如：
>>> ord(u'♿')
9855
由于您使用ord()结果作为按键和标签之间的映射，因此您无法使用♿作为按键。我会尝试使用另一个ascii char来识别这种情况（如ord('a')）。
您可以稍后在从键盘阅读时替换a：
elif intChar in intValidChars:
if intChar == ord('a'):
intChar = ord('♿')
intClassifications.append(intChar)
但可能，只要您记得翻译预测结果，训练功能甚至不需要它。