Why does Tesseract fail to recognize 6 out of 26 of my alphabetic keyboard keys even with several parameter tunings? - image-processing

Question

TL;DR I'm using:
adaptive thresholding
segmenting by keys (width/height ratio) - see green boxes in image result
psm 10 to treat each key as a character
but it fails to recognize some keys, falsely identifies others or identifies 2 for 1 char (see the L character in the image result, it's an L and P), etc.
Note: I cropped the image and re-ran the results to get it to fit on this site, but before cropping it did slightly better (recognized more keys, fewer false positives, etc).
I just want it to recognize the alphabet keys. Ultimately I will want it to work for realtime video.
config:
'-l eng --oem 1 --psm 10 -c tessedit_char_whitelist="ABCDEFGHIJKLMNOPQRSTUVWXYZ"'
I've tried scaling the image differently, scaling the individual key segments, using opening/closing/etc but it doesn't recognize all the keys.
original image
image result
Update: new results if I make the image straighter (bird's eye) and remove the whitelisting, it manages to detect all for the most part (although it thinks the O is a 0 and the I is a |, which is understandable). Why is this and how could I make this adaptive enough for a dynamic video when it is so sensitive to these conditions?
Code:
import pytesseract
import numpy as np
try:
from PIL import Image
except ImportError:
import Image
import cv2
from tqdm import tqdm
from collections import defaultdict
def get_missing_chars(dict):
capital_alphabet = [chr(ascii) for ascii in range(65, 91)]
return [let for let in capital_alphabet if let not in dict]
def draw_box_and_char(img, contour_dims, c, box_col, text_col):
x, y, w, h = contour_dims
top_left = (x, y)
bot_right = (x + w, y+h)
font_offset = 3
text_pos = (x+h//2+12, y+h-font_offset)
img_copy = img.copy()
cv2.rectangle(img_copy, top_left, bot_right, box_col, 2)
cv2.putText(img_copy, c, text_pos, cv2.FONT_HERSHEY_SIMPLEX, fontScale=.5, color=text_col, thickness=1, lineType=cv2.LINE_AA)
return img_copy
def detect_keys(img):
scaling = .25
img = cv2.resize(img, None, fx=scaling, fy=scaling, interpolation=cv2.INTER_AREA)
print("img shape", img.shape)
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ratio_min = 0.7
area_min = 1000
nbrhood_size = 1001
bias = 2
# adapt to different lighting
bin_img = cv2.adaptiveThreshold(gray_img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,\
cv2.THRESH_BINARY_INV, nbrhood_size, bias)
items = cv2.findContours(bin_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = items[0] if len(items) == 2 else items[1]
key_contours = []
for c in contours:
x, y, w, h = cv2.boundingRect(c)
ratio = h/w
area = cv2.contourArea(c)
# square-like ratio, try to get character
if ratio > ratio_min and area > area_min:
key_contours.append(c)
detected = defaultdict(int)
n_kept = 0
img_copy = cv2.cvtColor(bin_img, cv2.COLOR_GRAY2RGB)
let_to_contour = {}
n_contours = len(key_contours)
# offset to get smaller square within the key segment for easier char recognition
offset = 10
show_each_char = False
for _, c in tqdm(enumerate(key_contours), total=n_contours):
x, y, w, h = cv2.boundingRect(c)
ratio = h/w
area = cv2.contourArea(c)
base = np.zeros(bin_img.shape, dtype=np.uint8)
base.fill(255)
n_kept += 1
new_y = y+offset
new_x = x+offset
new_h = h-2*offset
new_w = w-2*offset
base[new_y:new_y+new_h, new_x:new_x+new_w] = bin_img[new_y:new_y+new_h, new_x:new_x+new_w]
segment = cv2.bitwise_not(base)
# try scaling up individual keys
# scaling = 2
# segment = cv2.resize(segment, None, fx=scaling, fy=scaling, interpolation=cv2.INTER_CUBIC)
# psm 10: treats the segment as a single character
custom_config = r'-l eng --oem 1 --psm 10 -c tessedit_char_whitelist="ABCDEFGHIJKLMNOPQRSTUVWXYZ"'
d = pytesseract.image_to_data(segment, config=custom_config, output_type='dict')
conf = d['conf']
c = d['text'][-1]
if c:
# sometimes recognizes multiple keys even though there is only 1
for sub_c in c:
# save character and contour to draw on image and show bounds/detection
if sub_c not in let_to_contour or (sub_c in let_to_contour and conf > let_to_contour[sub_c]['conf']):
let_to_contour[sub_c] = {'conf': conf, 'cont': (new_x, new_y, new_w, new_h)}
else:
c = "?"
text_col = (0, 0, 255)
if show_each_char:
contour_dims = (new_x, new_y, new_w, new_h)
box_col = (0, 255, 0)
text_col = (0, 0, 0)
segment_with_boxes = draw_box_and_char(segment, contour_dims, c, box_col, text_col)
cv2.imshow('segment', segment_with_boxes)
cv2.waitKey(0)
cv2.destroyAllWindows()
# draw boxes around recognized keys
for c, data in let_to_contour.items():
box_col = (0, 255, 0)
text_col = (0, 0, 0)
img_copy = draw_box_and_char(img_copy, data['cont'], c, box_col, text_col)
detected = {k: 1 for k in let_to_contour}
for det in let_to_contour:
print(det, let_to_contour[det])
print("total detected: ", let_to_contour.keys())
missing = get_missing_chars(detected)
print(f"n_missing: {len(missing)}")
print(f"chars missing: {missing}")
return img_copy
if __name__ == "__main__":
img_file = "keyboard.jpg"
img = cv2.imread(img_file)
img_with_detected_keys = detect_keys(img)
cv2.imshow("detected", img_with_detected_keys)
cv2.waitKey(0)
cv2.destroyAllWindows()