Hi! I am new to opencv,I am working on a project trying to recognize traffic signs.The enviroment I am going to use this project is indoors, it is for a self-driving small car which will have to navigate around a track. I've decided to first rescognize the shape of the object, then create a new picture from the ROI, and try to recognize the text on that picture.I am testing it with my laptop's webcamera which captures a 640x480 frame. The first issue i have is that picture that my code is trying to find the contours on is a little bit noisy. I tried several approaches, right now I am using median blurring--> Canny edge detection -->dialation. Is there something I am misssing? It provides relatively fair results on finding shapes, but it doesn't always work as inteded.(finds non positive results) Furthermore, the text recoginition part is also working but a fairly high fail rate. So it sometimes founds absolutely nonsense words, but it sometimes founds 'STOP'. I've also tought i could is pytesseract.image_to_string or image_to_boxes. Would any of that be a better approach? Here is my code: import cv2 import pytesseract import numpy as np font = cv2.FONT_HERSHEY_COMPLEX def empty(x): print(x) pass
text recognition
def find_text(img): pytesseract.pytesseract.tesseract_cmd = 'C:\Program Files (x86)\Tesseract-OCR\tesseract.exe' ##strings to find stop = "STOP"
############################
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img=cv2.resize(img,(300,150))
##word recognition
hImg, wImg, _ = img.shape
boxes = pytesseract.image_to_data(img)
print(boxes)
for x, b in enumerate(boxes.splitlines()):
if x != 0: ##first row headings
b = b.split() ##strings
print(b)
x1, y1, w1, h1 = int(b[6]), int(b[7]), int(b[8]), int(b[9])
cv2.rectangle(img, (x1, y1), (w1 + x1, h1 + y1), (0, 0, 255), 3)
cv2.imshow("roi", img)
if len(b) == 12:
if b[11] == stop:
print("found it")
#
parameter window
cv2.namedWindow("parameters") cv2.resizeWindow("paramaters",640,240)
TRACKBARS
cv2.createTrackbar("threshold1", "parameters", 81, 255, empty) cv2.createTrackbar("threshold2", "parameters", 255, 255, empty)
#
kernel = np.ones((3, 3), np.uint8) ## maszk cap = cv2.VideoCapture(0)
while (cap.isOpened()): ret,frame = cap.read() if ret == True: ##beolvasott video értékeinek felvétele width=cap.get(cv2.CAP_PROP_FRAME_WIDTH) height=cap.get(cv2.CAP_PROP_FRAME_HEIGHT) fps=cap.get(cv2.CAP_PROP_FPS) imgcopy=frame ##másolat készítése
##GET TRACKBAR POS##
threshold1 = cv2.getTrackbarPos('threshold1', "parameters")
threshold2 = cv2.getTrackbarPos('threshold1', "parameters")
grayvideo = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
blur =cv2.bilateralFilter(grayvideo,7,200,200)
blur2 = cv2.medianBlur(grayvideo, 11)
#bilblur=cv2.bilateralFilter(grayvideo,7,50,50)
imgCanny = cv2.Canny(blur2, threshold1, threshold2)
#ret3,th3 = cv2.threshold(grayvideo,threshold1,threshold2,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
cv2.imshow("Canny", imgCanny)
blur2 = cv2.medianBlur(imgCanny,1)
cv2.imshow("blur2", blur2)
dilated = cv2.dilate(imgCanny,kernel,iterations=1)
cv2.imshow("dilated", dilated)
contours,hierarchy =cv2.findContours(dilated,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
#print(len(contours))
##area of conotur and boundig rect
for contour in contours: ##area of conotur and boundig rect
area=cv2.contourArea(contour)
if area>5000:
peri = cv2.arcLength(contour, True)
approx = cv2.approxPolyDP(contour, 0.01 * peri, True)
objCor = len(approx)
x, y, w, h = cv2.boundingRect(approx)
if objCor == 8:
Type = "octa"
roi = imgcopy[y:y + h, x:x + w]
find_text(roi)
cv2.imwrite("roi.png", roi)
else:
Type = "None"
cv2.drawContours(frame, contours, -1, (0, 255, 0), 2)
cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 1)
cv2.putText(frame, Type, (x, y), font, 0.5,
(0, 255, 255), 2)
###
#cv2.drawContours(img,contours,-1,(0,255,0),2)
cv2.imshow("frame",frame)
if cv2.waitKey(1) & 0xFF == ord('q'): break
cv2.waitKey(0)
cv2.destroyAllWindows() cap.release()
Is there any way to improve detection success? Thank you in advance :)
