MétaCan
Menu
Back to cohort
Record W4399534558 · doi:10.1145/3641032.3641056

Unlocking the Potential of Face Recognition in OpenCV: A Comprehensive Study of Algorithmic Approaches

2023· article· en· W4399534558 on OpenAlexafffund
Shafaq Khan, Tanmay Verma, Y Sharma, Dhairy Bhatt

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicVehicle License Plate Recognition
Canadian institutionsUniversity of Windsor
FundersUniversity of Windsor
KeywordsComputer scienceFacial recognition systemFace (sociological concept)Artificial intelligenceComputer visionFace detectionPattern recognition (psychology)

Abstract

fetched live from OpenAlex

Face recognition technology has become increasingly prevalent in a wide range of industries, including security, monitoring, and biometrics. However, despite this prevalence, achieving accurate and effective face recognition in real-world scenarios remains a challenge. The objective of this research is to examine the algorithmic methods used by OpenCV library for facial recognition and assess their potential to maximize the system's effectiveness. The distinctiveness of this work rests in the comprehensive assessment of both conventional and deep learning-based approaches using OpenCV and Python. Additionally, it involves comparing their performance on a sizable facial dataset, considering factors like speed, accuracy, and precision. The study involves experimentation and testing of three conventional models: Eigenfaces, Fisherfaces, and LBPH. Our findings reveal that these conventional models perform inadequately in situations involving varying lighting conditions, and complex multi-facial contexts while only supporting grayscale images. Thus, we further delved into deep learning models like MTCNN, and pre-trained models like VGG16. While MTCNN exhibited remarkable results with the highest accuracy level, it encountered challenges in scenarios with fluctuating lighting conditions. Whereas as VGG16 yielded comparable outcomes but demanded high-end computational resources. Upon additional experimentation with deep learning models, we found that fine-tuning pre-trained models substantially improved performance on the target dataset, yielding even better results. We concluded that deep learning-based methods can effectively harness OpenCV's facial recognition capabilities, offering an advantage over conventional models. However, it's important to note that the applicability of these models still relies on specific use cases. Our study thoroughly deliberates on the advantages and limitations of each model, enabling the scientific and academic community to make informed decisions, while selecting an appropriate model for distinct use cases. The implications of our study extend to various industries, such as security, surveillance, and biometrics, where precise and effective facial recognition holds paramount importance.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.014
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.013
Threshold uncertainty score0.027

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.014
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.002
Science and technology studies0.0010.001
Scholarly communication0.0020.004
Open science0.0030.003
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0030.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.080
GPT teacher head0.242
Teacher spread0.163 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2023
Admission routes2
Has abstractyes

Explore more

Same topicVehicle License Plate RecognitionFrench-language works237,207