如何正确阅读easyocr的文本？

Question

I am trying to read images from a camera module and so far I got to process the image this way using adaptive filtering. Besides, I did a lot of manipulation to crop the ROI and read the text. However, it is reading the number but not the units beside the numbers, which are comparatively small in size. How do I solve this problem?

import easyocr 
import cv2
import numpy as np

import matplotlib.pyplot as plt
import time
import urllib.request
url = 'http://192.168.137.108/cam-hi.jpg'
while True:
    img_resp=urllib.request.urlopen(url)
    imgnp=np.array(bytearray(img_resp.read()),dtype=np.uint8)
    image = cv2.imdecode(imgnp,-1)
    image = cv2.medianBlur(image,7)
    gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)    #to gray convert
    th3 = cv2.adaptiveThreshold(gray_image,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,\
                cv2.THRESH_BINARY,11,2) #adaptive threshold gaussian filter used
    kernel = np.ones((5,5),np.uint8)
    opening = cv2.morphologyEx(th3, cv2.MORPH_OPEN, kernel)
    

    x = 0   #to save the position, width and height for contours(later used)
    y = 0
    w = 0
    h = 0

    cnts = cv2.findContours(opening, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    cnts = cnts[0] if len(cnts) == 2 else cnts[1]
    threshold =  10
    font = cv2.FONT_HERSHEY_SIMPLEX  
    org = (50, 50) 
    fontScale = 1 
    color = (0, 0, 0)
    thickness = 2
        
    for c in cnts:
        
        approx = cv2.approxPolyDP(c,0.01*cv2.arcLength(c,True),True)
        area = cv2.contourArea(c)   
        if  len(approx) == 4 and area > 100000:   #manual area value used to find ROI for rectangular contours
        
            cv2.drawContours(image,[c], 0, (0,255,0), 3)
            n = approx.ravel()
            font = cv2.FONT_HERSHEY_SIMPLEX
            (x, y, w, h) = cv2.boundingRect(c)
            old_img = opening[y:y+h, x:x+w]  #selecting the ROI
            width, height = old_img.shape
            cropped_img = old_img[50:int(width/2), 0:height] #cropping half of the frame of ROI to just focus on the number
            
            new = reader.readtext(cropped_img)   #reading text using easyocr
            if(new == []): 
                text = 'none'
            else:
                text = new
                print(text)
#                 cv2.rectangle(cropped_img, tuple(text[0][0][0]), tuple(text[0][0][2]), (0, 0, 0), 2)
                if(text[0][2] > 0.5): #checking the confidence level
                    
                    cv2.putText(cropped_img, text[0][1], org, font, fontScale, color, thickness, cv2.LINE_AA)        
            cv2.imshow('frame1',cropped_img)
    key = cv2.waitKey(5) 

    if key == 27:
        break

cv2.waitKey(0)
cv2.destroyAllWindows()
    
    

Answer 1

This is the best I could get. The Greek symbol ' mu ' is identified as ' p '. I also tried searching for Greek language model related to easyocr but could not find any.

Here is what I did:

• Performed Otsu Threshold on the entire image
• Selected contour with largest area and cropped it
• Converted the cropped image to LAB color space
• Manually performed binary threshold on A-channel

I got the following:

Passed this image as input to easyocr :

from easyocr import Reader
reader = Reader(['en'])

# input is the cropped image
results = reader.readtext(crop_img)

# convert to LAB space
lab = cv2.cvtColor(crop_img, cv2.COLOR_BGR2LAB)

# threshold on A-channel
r,th = cv2.threshold(lab[:,:,1],125,255,cv2.THRESH_BINARY_INV)

# create copy of cropped image
crop_img2 = crop_img.copy()

# draw only first 5 results for clarity
# borrowed from: https://pyimagesearch.com/2020/09/14/getting-started-with-easyocr-for-optical-character-recognition/
for (bbox, text, prob) in results[:5]:
  (tl, tr, br, bl) = bbox
  tl = (int(tl[0]), int(tl[1]))
  tr = (int(tr[0]), int(tr[1]))
  br = (int(br[0]), int(br[1]))
  bl = (int(bl[0]), int(bl[1]))
  crop_img2 = cv2.rectangle(crop_img2, tl, br, (0, 0, 255), 3)
  crop_img2 = cv2.putText(crop_img2, text, (tl[0], tl[1] - 20), cv2.FONT_HERSHEY_SIMPLEX, 1.1, (0, 0, 0), 5)

Answer 2

If you try to clear the image and pass path to below method it work try

def text_extraction(image, lang_code='en'):
    reader = easyocr.Reader([lang_code], gpu=False)
    roi = cv2.imread(image)#[85:731, 265:1275]
    output = reader.readtext(roi)
    # it returns list of tuple with ([x,y coordinates],text,text_threshold)
    return output