hetianle / ocr-mobilephone-captured-form-image-recognition Goto Github PK

conda install -c simonflueckiger tesserocr
python main.py

But the result was the following error.
Ran out of input error is BMP image opening together. why?

I also tried test_recognition.py. What is the recognition rate of handwritten numbers?
With the existing accuracy, it seems that we could hardly read the numbers in the existing image.

`(py37gpu_resnet) C:\ProgramData\Anaconda3\envs\py37gpu_resnet\OCR-MobilePhone-captured-form-image-recognition-master>python main.py
2480 1250
2000 1008.0645161290322

Turn RGB image to gray!
Image edge enhancement !
Turn gray image to binary image!
Searching table areas!
starting searching lines!!
Process start , searching horizontal line!
process started ,, searching vertical line!
Start searching cross points!
Traceback (most recent call last):
File "main.py", line 16, in
main_program()
File "main.py", line 9, in main_program
img_proc=Imgprocessing(new_file)
File "C:\ProgramData\Anaconda3\envs\py37gpu_resnet\OCR-MobilePhone-captured-form-image-recognition-master\formrecognition\imgprocessing.py", line 54, in init
self.feature_point=self.search_feature_point(self.lines)
File "C:\ProgramData\Anaconda3\envs\py37gpu_resnet\OCR-MobilePhone-captured-form-image-recognition-master\formrecognition\imgprocessing.py", line 229, in search_feature_point
t1.start()
File "C:\ProgramData\Anaconda3\envs\py37gpu_resnet\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\ProgramData\Anaconda3\envs\py37gpu_resnet\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\py37gpu_resnet\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\py37gpu_resnet\lib\multiprocessing\popen_spawn_win32.py", line 89, in init
reduction.dump(process_obj, to_child)
File "C:\ProgramData\Anaconda3\envs\py37gpu_resnet\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'Imgprocessing.search_feature_point..process'

(py37gpu_resnet) C:\ProgramData\Anaconda3\envs\py37gpu_resnet\OCR-MobilePhone-captured-form-image-recognition-master>Traceback (most recent call last):
File "", line 1, in
File "C:\ProgramData\Anaconda3\envs\py37gpu_resnet\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "C:\ProgramData\Anaconda3\envs\py37gpu_resnet\lib\multiprocessing\spawn.py", line 115, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input`