Does not recognize digit '7'

[lagerfeuer]

I've been trying to read some Sudokus and so far all digits have been recognized except 7.
Is this a font issue maybe? All the images I have tried, no 7 was recognized.

Edit: Maybe related #130

Example:

Link to the image

 curl -o sudoku.png https://upload.wikimedia.org/wikipedia/commons/thumb/f/ff/Sudoku-by-L2G-20050714.svg/1200px-Sudoku-by-L2G-20050714.svg.png
 easyocr -l en -f sudoku.png

([[42, 34], [100, 34], [100, 114], [42, 114]], '5', 0.9198901653289795)
([[174, 34], [234, 34], [234, 114], [174, 114]], '3', 0.5189616680145264)
([[704, 166], [762, 166], [762, 246], [704, 246]], '5', 0.8919380307197571)
([[44, 168], [104, 168], [104, 246], [44, 246]], '6', 0.8406975865364075)
([[568, 168], [630, 168], [630, 246], [568, 246]], '9', 0.7890614867210388)
([[445, 175], [499, 175], [499, 243], [445, 243]], '_', 0.8146840333938599)
([[176, 300], [234, 300], [234, 376], [176, 376]], '9', 0.8461765646934509)
([[968, 302], [1026, 302], [1026, 378], [968, 378]], '6', 0.9359095692634583)
([[44, 432], [102, 432], [102, 510], [44, 510]], '8', 0.9884797930717468)
([[1098, 432], [1156, 432], [1156, 510], [1098, 510]], '3', 0.5310271382331848)
([[572, 434], [630, 434], [630, 510], [572, 510]], '6', 0.9405879974365234)
([[46, 564], [108, 564], [108, 638], [46, 638]], '4', 0.6061235070228577)
([[702, 564], [762, 564], [762, 642], [702, 642]], '3', 0.617751955986023)
([[1100, 566], [1158, 566], [1158, 640], [1100, 640]], '_', 0.9189348220825195)
([[441, 569], [493, 569], [493, 637], [441, 637]], '8', 0.4214801788330078)
([[570, 694], [628, 694], [628, 772], [570, 772]], '2', 0.9453338384628296)
([[1098, 696], [1158, 696], [1158, 772], [1098, 772]], '6', 0.8925315737724304)
([[834, 826], [894, 826], [894, 906], [834, 906]], '2', 0.9729335308074951)
([[176, 830], [236, 830], [236, 906], [176, 906]], '6', 0.9366582036018372)
([[966, 830], [1024, 830], [1024, 904], [966, 904]], '8', 0.9889897704124451)
([[700, 956], [762, 956], [762, 1036], [700, 1036]], '9', 0.7338930368423462)
([[1098, 958], [1156, 958], [1156, 1036], [1098, 1036]], '5', 0.9352748394012451)
([[439, 961], [505, 961], [505, 1029], [439, 1029]], '4', 0.5053627490997314)
([[572, 962], [634, 962], [634, 1038], [572, 1038]], '_', 0.8581225872039795)
([[570, 1090], [630, 1090], [630, 1168], [570, 1168]], '8', 0.9891173839569092)
([[1096, 1090], [1154, 1090], [1154, 1166], [1096, 1166]], '9', 0.6340051293373108)

[rkcosmos]

try using allowlist = '0123456789'

[lagerfeuer]

@rkcosmos should have mentioned that I tried that, without success. Result is the same as above, minus the _ false positives.

[rkcosmos]

one possible workaround is telling EasyOCR to use different model. For example, if you use
reader = easyocr.Reader(['ch_sim','en']), it's going to use simplified Chinese model. If reader = easyocr.Reader(['ru','en']), it's Cyrillic model. All models support number 0123456789 and they are trained with different data/font. One model might be better than other. Just remember to use allowlist.

Note that EasyOCR is probably too general for your use case. For Sudoku, there might be better open source digit recognition model.

[lagerfeuer]

Tried both ch_sim and ru, neither worked. All of them seem to have a problem with the number 7.
Either that or it's the way the sevens appear in the Sudoku.

[poonyapat]

I tried reducing text_threshold to 0.5, using allowlist with 0-9, and blur with (3,3) kernel before OCR. Not sure why blurring help this issue but I tried and it worked.

[lagerfeuer]

@poonyapat good suggestion. using your settings, 7 is recognized, but still not everything. playing around with the parameters might lead me to a satisfying result.

[haiderasad]

I tried reducing text_threshold to 0.5, using allowlist with 0-9, and blur with (3,3) kernel before OCR. Not sure why blurring help this issue but I tried and it worked.

how to set blur ? can you give example

[haiderasad]

try using allowlist = '0123456789'

can you please tell if you found the solution to recognize separate digits? it only recognizes digits which are combined with letters

[nuiva]

I also encountered this issue and blurring helped. Here's a full example.

test2.png

import cv2          # opencv-python==4.5.2.52
import easyocr      # easyocr==1.3.2
img1 = cv2.imread("test2.png")
img2 = cv2.blur(img1, (3,3))
reader = easyocr.Reader(["en"])
results1 = reader.readtext(img1, allowlist="0123456789")
results2 = reader.readtext(img2, allowlist="0123456789")
print(results1) # []
print(results2) # [([[26, 0], [50, 0], [50, 30], [26, 30]], '7', 0.9999988079074598)]

[juanchosaravia]

I'm having a similar issue, here the image to recognize:

the result can't recognize there is a 7 there and it replaced 7 with a Z producing:
YLJ-BZM-WTG

[beuaaa]

I also encountered this issue and mag_ratio=2 worked.

results = reader.readtext(img, mag_ratio=2)