Matthias Bisping 9f18ef9cd1 Pull request #13: Image representation info
Merge in RR/image-prediction from image_representation_metadata to master

Squashed commit of the following:

commit bfe92b24a2959a72c0e913ef051476c01c285ad0
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Thu May 12 11:24:12 2022 +0200

    updated comment

commit f5721560f3fda05a8ad45d0b5e406434204c1177
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Thu May 12 11:16:02 2022 +0200

    unskip server predict test

commit 41d94199ede7d58427b9e9541605a94f962c3dc4
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Thu May 12 11:15:48 2022 +0200

    added hash image encoder that produces representations by hashing

commit 84a8b0a290081616240c3876f8db8a1ae8592096
Merge: 1624ee4 6030f40
Author: Matthias Bisping <matthias.bisping@iqser.com>
Date:   Thu May 12 10:18:56 2022 +0200

    Merge branch 'master' of ssh://git.iqser.com:2222/rr/image-prediction

commit 1624ee40376b84a4519025343f913120c464407a
Author: Matthias Bisping <Matthias.Bisping@iqser.com>
Date:   Mon Apr 25 16:51:13 2022 +0200

    Pull request #11: fixed assignment

    Merge in RR/image-prediction from image_prediction_service_overhaul_xref_and_empty_result_fix_fix to master

    Squashed commit of the following:

    commit 7312e57d1127b081bfdc6e96311e8348d3f8110d
    Author: Matthias Bisping <matthias.bisping@iqser.com>
    Date:   Mon Apr 25 16:45:12 2022 +0200

        logging setup changed

    commit 955e353d74f414ee2d57b234bdf84d32817d14bf
    Author: Matthias Bisping <matthias.bisping@iqser.com>
    Date:   Mon Apr 25 16:37:52 2022 +0200

        fixed assignment
2022-05-12 11:49:19 +02:00

76 lines
2.8 KiB
Python

import math
from operator import itemgetter
from image_prediction.config import CONFIG
from image_prediction.transformer.transformer import Transformer
from image_prediction.utils import get_logger
logger = get_logger()
class ResponseTransformer(Transformer):
def transform(self, data):
logger.debug("ResponseTransformer.transform")
return build_image_info(data)
def build_image_info(data: dict) -> dict:
def compute_geometric_quotient():
page_area_sqrt = math.sqrt(abs(page_width * page_height))
image_area_sqrt = math.sqrt(abs(x2 - x1) * abs(y2 - y1))
return image_area_sqrt / page_area_sqrt
page_width, page_height, x1, x2, y1, y2, width, height, alpha = itemgetter(
"page_width", "page_height", "x1", "x2", "y1", "y2", "width", "height", "alpha"
)(data)
quotient = round(compute_geometric_quotient(), 4)
min_image_to_page_quotient_breached = bool(quotient < CONFIG.filters.image_to_page_quotient.min)
max_image_to_page_quotient_breached = bool(quotient > CONFIG.filters.image_to_page_quotient.max)
min_image_width_to_height_quotient_breached = bool(
width / height < CONFIG.filters.image_width_to_height_quotient.min
)
max_image_width_to_height_quotient_breached = bool(
width / height > CONFIG.filters.image_width_to_height_quotient.max
)
classification = data["classification"]
representation = data["representation"]
min_confidence_breached = bool(max(classification["probabilities"].values()) < CONFIG.filters.min_confidence)
image_info = {
"classification": classification,
"representation": representation,
"position": {"x1": x1, "x2": x2, "y1": y1, "y2": y2, "pageNumber": data["page_idx"] + 1},
"geometry": {"width": width, "height": height},
"alpha": alpha,
"filters": {
"geometry": {
"imageSize": {
"quotient": quotient,
"tooLarge": max_image_to_page_quotient_breached,
"tooSmall": min_image_to_page_quotient_breached,
},
"imageFormat": {
"quotient": round(width / height, 4),
"tooTall": min_image_width_to_height_quotient_breached,
"tooWide": max_image_width_to_height_quotient_breached,
},
},
"probability": {"unconfident": min_confidence_breached},
"allPassed": not any(
[
max_image_to_page_quotient_breached,
min_image_to_page_quotient_breached,
min_image_width_to_height_quotient_breached,
max_image_width_to_height_quotient_breached,
min_confidence_breached,
]
),
},
}
return image_info