ageitgey/face_recognition

23.3

Adjusted Score

23.3

Raw Score

100%

Time Factor

2026-06-25

Last Push

56.6K

Stars

Python

Language

4.7K

Lines of Code

Files

Pattern Hits

2026-07-14

Scan Date

0.00

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 0MEDIUM 11LOW 67

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 78 distinct pattern matches across 9 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Self-Referential Comments11 hits · 33 pts

Severity	File	Line	Snippet	Context
MEDIUM	docs/conf.py	7	# This file is execfile()d with the current directory set to its	COMMENT
MEDIUM	examples/facerec_from_webcam_faster.py	35	# Initialize some variables	COMMENT
MEDIUM	examples/blur_faces_on_webcam.py	13	# Initialize some variables	COMMENT
MEDIUM	examples/identify_and_draw_boxes_on_faces.py	36	# Create a Pillow ImageDraw Draw instance to draw with	COMMENT
MEDIUM	examples/facerec_from_webcam_multiprocessing.py	143	# Create a thread to capture frames (if uses subprocess, it will crash on Mac)	COMMENT
MEDIUM	examples/facerec_from_video_file.py	14	# Create an output movie file (make sure resolution/frame rate matches input video!)	COMMENT
MEDIUM	examples/facerec_from_video_file.py	30	# Initialize some variables	COMMENT
MEDIUM	examples/find_faces_in_picture.py	8	# This method is fairly accurate, but not as accurate as the CNN model and not GPU accelerated.	COMMENT
MEDIUM	examples/facerec_on_raspberry_pi.py	25	# Initialize some variables	COMMENT
MEDIUM	examples/find_faces_in_picture_cnn.py	8	# This method is more accurate than the default HOG model, but it's slower	COMMENT
MEDIUM	examples/find_facial_features_in_picture.py	12	# Create a PIL imagedraw object so we can draw on the picture	COMMENT

Hyper-Verbose Identifiers24 hits · 26 pts

Severity	File	Line	Snippet	Context
LOW	face_recognition/api.py	124	def _raw_face_locations_batched(images, number_of_times_to_upsample=1, batch_size=128):	CODE
LOW	face_recognition/api.py	146	def convert_cnn_detections_to_css(detections):	CODE
LOW	face_recognition/face_detection_cli.py	29	def process_images_in_process_pool(images_to_check, number_of_cpus, model, upsample):	CODE
LOW	face_recognition/face_recognition_cli.py	71	def process_images_in_process_pool(images_to_check, known_names, known_face_encodings, number_of_cpus, tolerance, show_d	CODE
LOW	tests/test_face_recognition.py	40	def test_cnn_raw_face_locations(self):	CODE
LOW	tests/test_face_recognition.py	81	def test_partial_face_locations(self):	CODE
LOW	tests/test_face_recognition.py	94	def test_raw_face_locations_batched(self):	CODE
LOW	tests/test_face_recognition.py	104	def test_batched_face_locations(self):	CODE
LOW	tests/test_face_recognition.py	139	def test_face_landmarks_small_model(self):	CODE
LOW	tests/test_face_recognition.py	155	def test_face_encodings_large_model(self):	CODE
LOW	tests/test_face_recognition.py	188	def test_face_distance_empty_lists(self):	CODE
LOW	tests/test_face_recognition.py	230	def test_compare_faces_empty_lists(self):	CODE
LOW	tests/test_face_recognition.py	248	def test_command_line_interface_options(self):	CODE
LOW	tests/test_face_recognition.py	255	def test_command_line_interface(self):	CODE
LOW	tests/test_face_recognition.py	266	def test_command_line_interface_big_image(self):	CODE
LOW	tests/test_face_recognition.py	277	def test_command_line_interface_tolerance(self):	CODE
LOW	tests/test_face_recognition.py	288	def test_command_line_interface_show_distance(self):	CODE
LOW⚡	tests/test_face_recognition.py	299	def test_fd_command_line_interface_options(self):	CODE
LOW⚡	tests/test_face_recognition.py	306	def test_fd_command_line_interface(self):	CODE
LOW⚡	tests/test_face_recognition.py	316	def test_fd_command_line_interface_folder(self):	CODE
LOW	tests/test_face_recognition.py	328	def test_fd_command_line_interface_hog_model(self):	CODE
LOW	tests/test_face_recognition.py	337	def test_fd_command_line_interface_cnn_model(self):	CODE
LOW	examples/face_recognition_knn.py	153	def show_prediction_labels_on_image(img_path, predictions):	CODE
LOW	examples/facerec_ipcamera_knn.py	153	def show_prediction_labels_on_image(frame, predictions):	CODE

Redundant / Tautological Comments11 hits · 16 pts

Severity	File	Line	Snippet	Context
LOW	examples/web_service_example.py	35	# Check if a valid image file was uploaded	COMMENT
LOW	examples/facerec_from_webcam.py	70	# Display the resulting image	COMMENT
LOW	examples/facerec_from_webcam_faster.py	79	# Display the results	COMMENT
LOW	examples/facerec_from_webcam_faster.py	95	# Display the resulting image	COMMENT
LOW	examples/face_recognition_knn.py	180	# Display the resulting image	COMMENT
LOW	examples/face_recognition_knn.py	201	# Print results on the console	COMMENT
LOW	examples/face_recognition_knn.py	205	# Display results overlaid on an image	COMMENT
LOW	examples/blur_faces_on_webcam.py	26	# Display the results	COMMENT
LOW	examples/blur_faces_on_webcam.py	43	# Display the resulting image	COMMENT
LOW	examples/identify_and_draw_boxes_on_faces.py	69	# Display the resulting image	COMMENT
LOW	examples/facerec_from_webcam_multiprocessing.py	201	# Display the resulting image	COMMENT

Over-Commented Block13 hits · 13 pts

Severity	File	Line	Snippet	Context
LOW	docs/conf.py	1	#!/usr/bin/env python	COMMENT
LOW	docs/conf.py	61	#source_encoding = 'utf-8-sig'	COMMENT
LOW	docs/conf.py	81	#language = None	COMMENT
LOW	docs/conf.py	101	# unit titles (such as .. function::).	COMMENT
LOW	docs/conf.py	121	# The theme to use for HTML and HTML Help pages. See the documentation for	COMMENT
LOW	docs/conf.py	141	# The name of an image file (relative to this directory) to place at the	COMMENT
LOW	docs/conf.py	161	# typographically correct entities.	COMMENT
LOW	docs/conf.py	181	#html_show_sourcelink = True	COMMENT
LOW	docs/conf.py	221	u'Face Recognition Documentation',	COMMENT
LOW	docs/conf.py	281	#texinfo_show_urls = 'footnote'	COMMENT
LOW	examples/web_service_example_Simplified_Chinese.py	1	# 这是一个非常简单的使用Web服务上传图片运行人脸识别的案例，后端服务器会识别这张图片是不是奥巴马，并把识别结果以json键值对输出	COMMENT
LOW	examples/web_service_example.py	1	# This is a _very simple_ example of a web service that recognizes faces in uploaded images.	COMMENT
LOW	examples/find_faces_in_batches.py	1	import face_recognition	COMMENT

Unused Imports10 hits · 10 pts

Severity	File	Line	Context
LOW	face_recognition/__init__.py	7	CODE
LOW	face_recognition/__init__.py	7	CODE
LOW	face_recognition/__init__.py	7	CODE
LOW	face_recognition/__init__.py	7	CODE
LOW	face_recognition/__init__.py	7	CODE
LOW	face_recognition/__init__.py	7	CODE
LOW	face_recognition/__init__.py	7	CODE
LOW	face_recognition/face_detection_cli.py	2	CODE
LOW	face_recognition/face_recognition_cli.py	2	CODE
LOW	examples/blink_detection.py	16	CODE

AI Slop Vocabulary4 hits · 6 pts

Severity	File	Line	Snippet	Context
LOW	examples/facerec_from_webcam.py	51	# If a match was found in known_face_encodings, just use the first one.	COMMENT
LOW	examples/facerec_from_webcam_faster.py	63	# # If a match was found in known_face_encodings, just use the first one.	COMMENT
LOW	examples/identify_and_draw_boxes_on_faces.py	46	# If a match was found in known_face_encodings, just use the first one.	COMMENT
LOW	examples/facerec_from_webcam_multiprocessing.py	94	# If a match was found in known_face_encodings, just use the first one.	COMMENT

Deep Nesting3 hits · 3 pts

Severity	File	Line	Context
LOW	examples/face_recognition_knn.py	46	CODE
LOW	examples/facerec_ipcamera_knn.py	51	CODE
LOW	examples/blink_detection.py	21	CODE

Slop Phrases1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	examples/facerec_on_raspberry_pi.py	14	# If this fails, make sure you have a camera connected to the RPi and that you	COMMENT

Excessive Try-Catch Wrapping1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	face_recognition/api.py	10	except Exception:	CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings