520eee26e3
Merge in RR/image-prediction from integrate-image-extraction-new-pyinfra to master
Squashed commit of the following:
commit 8470c065c71ea2a985aadfc399fb32c693e3a90f
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Thu Aug 18 09:19:52 2022 +0200
add key script
commit 8f6eb1e79083fb32fb7bedac640c10b6fd411899
Merge: 27fd7de c1b9629
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Thu Aug 18 09:17:50 2022 +0200
Merge branch 'master' of ssh://git.iqser.com:2222/rr/image-prediction into integrate-image-extraction-new-pyinfra
commit 27fd7de39a59d0d88fbddb471dd7797b61223ece
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Wed Aug 17 13:15:09 2022 +0200
update pyinfra
commit ca58f85642598dc15e286074982e7cedae9a1355
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Tue Aug 16 16:16:10 2022 +0200
update pdf2image-service
commit f43795cee0e211e14ac5f9296b01d440ae759c55
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Mon Aug 15 10:32:02 2022 +0200
update pipeline script to also work with figure detection metadata
commit 2b2da1b60ce56fb006cf2f6b65aeda9774391b2a
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Fri Aug 12 13:37:48 2022 +0200
add new pyinfra, add optional image classifcation under key dataCV if figure metadata is present on storage
commit bae25bedbd3a262a9d00e18a1b19f4ee6f1eb924
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Wed Aug 10 13:27:41 2022 +0200
tidy-up
commit 287b0ebc8a952e506185d13508eaa386d0420704
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Wed Aug 10 12:57:35 2022 +0200
update server logic for new pyinfra, add extraction from scanned PDF with figure detection logic
commit 3225cefaa25e4559b105397bc06c867a22806ba8
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Wed Aug 10 10:37:31 2022 +0200
integrate new pyinfra logic
commit 46926078342b0680a7416560bb69bec037cf8038
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Wed Aug 3 13:15:27 2022 +0200
add image extraction for scanned PDFs WIP
commit 1b3b11b6f9044d44cb9a822a78197a2ebc6f306a
Author: Julius Unverfehrt <julius.unverfehrt@iqser.com>
Date: Wed Aug 3 09:41:06 2022 +0200
add pyinfra and pdf2image as git submodule
36 lines
1.1 KiB
Python
36 lines
1.1 KiB
Python
import abc
|
|
|
|
from image_prediction.image_extractor.extractor import ImageMetadataPair
|
|
from image_prediction.info import Info
|
|
|
|
from image_prediction.transformer.transformer import Transformer
|
|
from pdf2img.default_objects.image import ImagePlus
|
|
|
|
|
|
class Formatter(Transformer):
|
|
@abc.abstractmethod
|
|
def format(self, obj):
|
|
raise NotImplementedError
|
|
|
|
def transform(self, obj):
|
|
raise NotImplementedError()
|
|
|
|
def __call__(self, obj):
|
|
return self.format(obj)
|
|
|
|
|
|
def format_image_plus(image: ImagePlus) -> ImageMetadataPair:
|
|
enum_metadata = {
|
|
Info.PAGE_WIDTH: image.info.pageInfo.width,
|
|
Info.PAGE_HEIGHT: image.info.pageInfo.height,
|
|
Info.PAGE_IDX: image.info.pageInfo.number,
|
|
Info.ALPHA: image.info.alpha,
|
|
Info.WIDTH: image.info.boundingBox.width,
|
|
Info.HEIGHT: image.info.boundingBox.height,
|
|
Info.X1: image.info.boundingBox.x0,
|
|
Info.X2: image.info.boundingBox.x1,
|
|
Info.Y1: image.info.boundingBox.y0,
|
|
Info.Y2: image.info.boundingBox.y1,
|
|
}
|
|
return ImageMetadataPair(image.aspil(), enum_metadata)
|