Hi,
On 14/02/2023 21:16, Flávio. wrote:
Thanks, i'm still trying to figure it out. It seems when the PIL image
is saved, unfortunately it saves a temp file to disk. My goal is to not
write to disk, because this application will read a lot of files and I
want to spare my SSD. My code receives byte data from a Dart program (I
checked it is correct). So far the py file looks like this but i'm not
getting anything in return.
At this point I maybe ought to reply off list, but you could also save
the images to a "tmpfs" on Linux if you don't want to deal with stdin
and have the images never hit the disk/ssd:
https://www.kernel.org/doc/html/v5.7/filesystems/tmpfs.html
In any case - when you write that PIL 'saves a temp file to disk', what
lead you to that conclusion? The code below really shouldn't do that.
Regards,
Merlijn
def main():
base64_image = sys.stdin.read()
image_bytes = base64.b64decode(base64_image)
with io.BytesIO(image_bytes) as input:
pil_image = Image.open(input)
with io.BytesIO() as output:
pil_image.save(output, format='PNG', compress=0,
compress_level=0) # using disk!
output.seek(0)
env = os.environ.copy()
env['OMP_THREAD_LIMIT'] = '1'
p = subprocess.Popen([tesseractPath, '-', '-','-l','por'],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
env=env)
output, stderr = p.communicate(output.read())
stderr = stderr.decode('utf-8')
if stderr:
logger.warning('tesseract_baselines stderr: %s', stderr)
else:
sys.stdout(output.encode('utf-8').strip())
if __name__ == '__main__':
main()
On Tuesday, February 14, 2023 at 4:11:13 PM UTC-3 Merlijn Wajer wrote:
Hi,
On 14/02/2023 19:10, Flávio. wrote:
> Sorry, how can I do that? I'm trying to send image binary data,
not a
> path. The goal is to not write a file to disk and use only
memory. Could
> you please write a code that sends the data (binary) to the stdin of
> tesseract? it can be in Python, Dart or Java :( I've tried
ChatGPT but
> it is wrong and gets lost
Normally I'd say 'left as an exercises to the reader' but I so
happen to
have a snippet around that ought to give you a general idea.
This uses io.BytesIO in Python 3 to save the image (stream) to, it
contains an uncompressed PNG (compression will just slow things down).
It assumes that the variable "pil_image" contains a PIL.Image object.
The code to use just one core in Tesseract is of course entirely
optional. I didn't *test* this to work (I modified it a bit - it works
in another setting), but it should work in theory:
> with io.BytesIO() as output:
> pil_image.save(output, format='PNG', compress=0, compress_level=0)
> output.seek(0)
>
> # Let's just use one core in tesseract
> env = os.environ.copy()
> env['OMP_THREAD_LIMIT'] = '1'
>
> p = subprocess.Popen(['tesseract', '-', '-'],
> stdin=subprocess.PIPE,
> stdout=subprocess.PIPE,
> stderr=subprocess.PIPE,
> env=env)
> output, stderr = p.communicate(output.read())
> stderr = stderr.decode('utf-8')
>
> if stderr:
> logger.warning('tesseract_baselines stderr: %s', stderr)
Regards,
Merlijn
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send
an email to [email protected]
<mailto:[email protected]>.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/ebd9d42d-244c-4a6b-8ab8-c1efd87db501n%40googlegroups.com
<https://groups.google.com/d/msgid/tesseract-ocr/ebd9d42d-244c-4a6b-8ab8-c1efd87db501n%40googlegroups.com?utm_medium=email&utm_source=footer>.
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/eefc7136-dd31-cdc8-4a54-4e69c265c1df%40archive.org.
