SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.11104 · 2020

Masked Face Recognition for Secure Authentication

arXiv · PDF · Open in the Atlas

Code that ran

7 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 1 failure of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2008.11104.json · badge: /api/ran/2008.11104.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
aqeelanwar/MaskTheFace canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
nodefluxio/automatic-masking-master community (classifier label)
classifier basis: plan_row
6 ran · 4 no recorded run
FunctionStatusWhere it lives
Convert Ran
ran; our contract draft was wrong, not the code
aqeelanwar/MaskTheFace/utils/fetch_dataset.py
code served (permissive licence) · get_code("8a001e27f9296b3a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Convert function takes a list and converts it to a dict
# by pairing consecutive elements: [k1, v1, k2, v2, ...] -> {k1: v1, k2: v2, ...}
# The function uses iter() and zip() to pair elements

# Create a simple list with alternating keys and values
lst = ['a', 1, 'b', 2, 'c', 3]

ARGS = {
    'lst': lst
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ConvertIfStringIsInt Ran
ran on a synthesized input
nodefluxio/automatic-masking-master/utils/read_cfg.py
code served (permissive licence) · get_code("fa68555bed5641ba")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function ConvertIfStringIsInt:
# - Takes one parameter: input_string
# - The parameter should be a string that might represent a number
# - Returns int if the string represents an integer, float if it represents a float, or the original string otherwise

ARGS = {
    "input_string": "42"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
color_the_mask Ran
ran on a synthesized input
nodefluxio/automatic-masking-master/utils/create_mask.py
code served (permissive licence) · get_code("64be372fe1de64d5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (4, 3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from PIL import ImageColor
import cv2

# Create a small RGBA image for mask_image
# Shape: (height=4, width=3, channels=4)
# RGBA format: R, G, B, Alpha
mask_image = np.zeros((4, 3, 4), dtype=np.uint8)
# Fill with some sample data
mask_image[:, :, 0] = 100  # Red channel
mask_image[:, :, 1] = 150  # Green channel
mask_image[:, :, 2] = 200  # Blue channel
mask_image[:, :, 3] = 255  # Alpha channel (fully opaque)

# Set some alpha values to 0 to create transparency variation
mask_image[0:2, 0:1, 3] = 0  # Transparent in one region

# Color as a string that PIL.ImageColor.getcolor can parse
color = '#FF0000'  # Red color

# Intensity as a float between 0 and 1
intensity = 0.5

ARGS = {
    'mask_image': mask_image,
    'color': color,
    'intensity': intensity
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 3, 4) — shape (4, 3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ellipse_angle_of_rotation Ran
ran on a synthesized input
nodefluxio/automatic-masking-master/utils/fit_ellipse.py
code served (permissive licence) · get_code("8757f40657e3bed9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function expects a single parameter 'a' which is indexed like:
# a[0], a[1], a[2], a[3], a[4], a[5]
# This suggests 'a' should be an array-like object with at least 6 elements

# Create a numpy array with 6 elements representing ellipse coefficients
a = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0])

ARGS = {
    'a': a
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ellipse_center Ran
ran on a synthesized input
nodefluxio/automatic-masking-master/utils/fit_ellipse.py
code served (permissive licence) · get_code("d8254c0f147a5940")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function ellipse_center takes a single parameter 'a'
# Looking at the body, it expects 'a' to be array-like with at least 6 elements
# It accesses a[0], a[1], a[2], a[3], a[4], a[5]
# These are used in arithmetic operations

# Create a valid input array with 6 elements
# The coefficients represent the general conic equation: a*x^2 + 2*b*x*y + c*y^2 + 2*d*x + 2*f*y + g = 0
a_input = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0])

ARGS = {
    'a': a_input
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
fitEllipse Ran
ran on a synthesized input
nodefluxio/automatic-masking-master/utils/fit_ellipse.py
code served (permissive licence) · get_code("328f2900ec685445")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (6,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# fitEllipse takes x and y as parameters
# Looking at the function body:
# - x and y are converted to column vectors with x[:, np.newaxis]
# - They are used in arithmetic operations (x*x, x*y, y*y, x, y)
# - np.hstack concatenates them into a design matrix D
# - D.T @ D produces a matrix used for eigenvalue decomposition
# The function expects 1D arrays of coordinates

# Create small sample data for ellipse fitting
# These should be 1D arrays of point coordinates
x = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
y = np.array([2.0, 3.0, 4.0, 5.0, 6.0])

ARGS = {
    "x": x,
    "y": y,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (6,) — shape (6,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_points_on_chin Ran
ran on a synthesized input
nodefluxio/automatic-masking-master/utils/aux_functions.py
code served (permissive licence) · get_code("f2e13aa47113ab54")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Construct a line as a list of two points
line = [[10.0, 20.0], [50.0, 60.0]]

# Construct face_landmark with a 'chin' key containing a list of chin points
face_landmark = {
    'chin': [
        [5.0, 15.0],
        [15.0, 25.0],
        [25.0, 30.0],
        [35.0, 28.0],
        [45.0, 20.0],
        [55.0, 15.0]
    ]
}

ARGS = {
    'line': line,
    'face_landmark': face_landmark,
    'chin_type': 'chin'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
download Not yet run
unverified (harvested, no recorded run)
aqeelanwar/MaskTheFace/utils/fetch_dataset.py
code served (permissive licence) · get_code("b37e60c17b4e8e9e")
How it ran

no invocation recorded.

get_confirm_token Not yet run
unverified (harvested, no recorded run)
nodefluxio/automatic-masking-master/utils/fetch_dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from med-air/FedBN, is pointer only (licence: NONE) · get_code("135b3dc835ffe6ad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from med-air/FedBN, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_line Not yet run
unverified (harvested, no recorded run)
nodefluxio/automatic-masking-master/utils/aux_functions.py
code served (permissive licence) · get_code("3743d0caaf51e752")
How it ran

no invocation recorded.

line_intersection Not yet run
unverified (harvested, no recorded run)
nodefluxio/automatic-masking-master/utils/aux_functions.py
code served (permissive licence) · get_code("7483746051031462")
How it ran

no invocation recorded.

texture_the_mask Not yet run
unverified (harvested, no recorded run)
nodefluxio/automatic-masking-master/utils/create_mask.py
code served (permissive licence) · get_code("b5776a643f464bbe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 11 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_confirm_token 38 other papers
24 dated earlier, 14 later
1409.8230 (2014-09)
RENOIR - A Dataset for Real Low-Light Image Noise Reduction
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1506.03134 (2015-06)
Pointer Networks
and 35 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

With the recent world-wide COVID-19 pandemic, using face masks have become an important part of our lives. People are encouraged to cover their faces when in public area to avoid the spread of infection. The use of these face masks has raised a serious question on the accuracy of the facial recognition system used for tracking school/office attendance and to unlock phones. Many organizations use facial recognition as a means of authentication and have already developed the necessary datasets in-house to be able to deploy such a system. Unfortunately, masked faces make it difficult to be detected and recognized, thereby threatening to make the in-house datasets invalid and making such facial recognition systems inoperable. This paper addresses a methodology to use the current facial datasets by augmenting it with tools that enable masked faces to be recognized with low false-positive rates and high overall accuracy, without requiring the user dataset to be recreated by taking new pictures for authentication. We present an open-source tool, MaskTheFace to mask faces effectively creating a large dataset of masked faces. The dataset generated with this tool is then used towards training an effective facial recognition system with target accuracy for masked faces. We report an increase of 38% in the true positive rate for the Facenet system. We also test the accuracy of re-trained system on a custom real-world dataset MFR2 and report similar accuracy.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2008.11104")
get_code_for_paper("2008.11104")
have("2008.11104")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2008.11104.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2008.11104.svg)](https://syntology.ai/paper/2008.11104)

Connect an agent — have() is free.