Safefaceyolo: Real-time Workplace Safety Enforcement Via Integrated Helmet Detection And Facial Recognition

• Author(s):

  V. Dhamodharan | Dharanitharan S | Adhithya SP | Mohamed Batcha A | Venkatakrishnan S

• Keywords:

  Alert System, Facial Recognition, Grassmann Algorithm, Helmet Detection, Personal Protective Equipment, Safety Monitoring, YOLO Algorithm.

• Abstract:

  Workplace Safety Is A Critical Concern In Industries Such As Construction And Manufacturing, Where Workers Are Exposed To Hazardous Environments. One Of The Major Causes Of Accidents Is The Failure To Wear Personal Protective Equipment (PPE), Particularly Safety Helmets. Traditional Safety Monitoring Systems Rely Heavily On Manual Inspection, Which Is Time-consuming, Costly, And Prone To Human Error, Especially In Large-scale Sites With Multiple Ongoing Activities. To Address These Challenges, This Project Proposes An Automated System That Integrates Computer Vision Techniques For Real-time Helmet Detection And Worker Identification. The System Combines Two Key Functionalities: Helmet Detection And Face Recognition. Helmet Detection Is Performed Using Advanced Object Detection Algorithms To Identify Whether Workers Are Wearing Safety Helmets, While Facial Recognition Is Used To Identify Individuals By Comparing Extracted Facial Features With A Pre-existing Database. The Proposed Approach Improves Efficiency By Eliminating The Limitations Of Manual Monitoring And Enabling Continuous Surveillance. It Also Ensures Better Safety Compliance By Providing Accurate And Real-time Detection Under Varying Environmental Conditions. The System Is Further Evaluated Based On Performance Metrics Such As Accuracy And Recall Rate Across Different Visual Scenarios Found On Construction Sites. Overall, This Integrated Solution Offers A Reliable And Intelligent Approach To Enhance Workplace Safety, Reduce Accidents, And Support Safety Inspectors Through Automated Monitoring And Immediate Detection Of Violations.

---

Other Details

• Paper id:

  IJSARTV12I4104986

• Published in:

  Volume: 12 Issue: 4 April 2026

• Publication Date:

  2026-04-13

Download Article