cv2.error:easyOCR reader.readtext()函数中OpenCV代码出现未知C++异常

Question

我曾尝试在车牌检测模型中使用easyOCR读取文本。但有时会出现一个名为的错误

File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packagesflaskapp.py", line 2073, in wsgi_app
response = self.full_dispatch_request()
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packagesflaskapp.py", line 1518, in full_dispatch_request
rv = self.handle_user_exception(e)
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packagesflaskapp.py", line 1516, in full_dispatch_request
rv = self.dispatch_request()
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packagesflaskapp.py", line 1502, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**req.view_args)
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packagesdashdash.py", line 1344, in dispatch
response.set_data(func(*args, outputs_list=outputs_list))
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packagesdash_callback.py", line 151, in add_context
output_value = func(*func_args, **func_kwargs)  # %% callback invoked %%
File "E:Git Projectssimple-flask-webAppindex.py", line 305, in update_output
return [[parse_contents(list_of_contents, list_of_names)], [parse_image(list_of_contents)]]
File "E:Git Projectssimple-flask-webAppindex.py", line 122, in parse_image
numberplate = number_plate(original_img)
File "E:Git Projectssimple-flask-webAppindex.py", line 289, in number_plate
ocr_result = reader.readtext(region)
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packageseasyocreasyocr.py", line 385, in readtext
horizontal_list, free_list = self.detect(img, min_size, text_threshold,
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packageseasyocreasyocr.py", line 275, in detect
text_box_list = get_textbox(self.detector, img, canvas_size, mag_ratio,
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packageseasyocrdetection.py", line 95, in get_textbox
bboxes_list, polys_list = test_net(canvas_size, mag_ratio, detector,
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packageseasyocrdetection.py", line 55, in test_net
boxes, polys, mapper = getDetBoxes(
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packageseasyocrcraft_utils.py", line 236, in getDetBoxes
boxes, labels, mapper = getDetBoxes_core(textmap, linkmap, text_threshold, link_threshold, low_text, estimate_num_chars)
File "C:UsersMY-PCAppDataLocalProgramsPythonPython39libsite-packageseasyocrcraft_utils.py", line 31, in getDetBoxes_core
nLabels, labels, stats, centroids = cv2.connectedComponentsWithStats(text_score_comb.astype(np.uint8), connectivity=4)
cv2.error: Unknown C++ exception from OpenCV code

但有时它能正常工作。运行两三次后，出现了此错误
这是产生错误的代码。

for idx, box in enumerate(boxes):
print(box)
roi = box * [height, width, height, width]
print(roi)
region = image[int(roi[0]):int(roi[2]), int(roi[1]):int(roi[3])]
reader = easyocr.Reader(['en'])
ocr_result = reader.readtext(region)
print(ocr_result)
plt.imshow(cv2.cvtColor(region, cv2.COLOR_BGR2RGB))
for result in ocr_result:
print(np.sum(np.subtract(result[0][2],result[0][1])))
print(result[1])

正在寻找解决此问题的方案

Answer 1

尝试早期版本的opencv-python。我在其他地方看到了它，它解决了我和你一样经常犯的错误。我认为4.5.4.60有效。