Throughout our lives, we've been exposed to countless reports and stories in newspapers and online platforms, underscoring the distressing prevalence of sexual harassment incidents. The reluctance victims often experience when reporting such incidents due to fears of retaliation or social stigma drove the creation of this project. The aim is to leverage innovative technologies to create a safer, more inclusive work environment.
The goal is to build a technological solution for real-time harassment detection while addressing the gaps left by traditional methods. This includes creating a safer work environment, overcoming reporting hesitancy, supporting HR and legal management, reducing stress, and ensuring early detection and prevention of harassment.
The project aims to develop a CNN-based model to detect workplace harassment and a **Safety Monitoring System with Email Alert and Face Recognition** module. This hybrid approach ensures accurate detection of harassment behavior while enhancing workplace safety through real-time face recognition and alert notifications.
This module leverages a CNN-based model to differentiate harassment behaviors from normal workplace activities in videos.
A real-time monitoring solution using facial recognition technology integrated with safety protocols.
Install the following libraries:
Harassment Detection:
yes (harassment images) and no (healthy environment images).Face Recognition:
Harassment Detection:
Safety Monitoring System:
Achieved 98% training accuracy and 97% validation accuracy.
Machine Learning:
Face Recognition:
Deployment:
Optimization:
By combining Harassment Detection with a Safety Monitoring System, this project addresses workplace safety comprehensively. It fosters a secure environment, supports HR processes, and promotes early intervention for safety and harassment concerns.
Throughout our lives, we've been exposed to countless reports and stories in newspapers and online platforms, underscoring the distressing prevalence of sexual harassment incidents. The reluctance victims often experience when reporting such incidents due to fears of retaliation or social stigma drove the creation of this project. The aim is to leverage innovative technologies to create a safer, more inclusive work environment.
The goal is to build a technological solution for real-time harassment detection while addressing the gaps left by traditional methods. This includes creating a safer work environment, overcoming reporting hesitancy, supporting HR and legal management, reducing stress, and ensuring early detection and prevention of harassment.
The project aims to develop a CNN-based model to detect workplace harassment and a **Safety Monitoring System with Email Alert and Face Recognition** module. This hybrid approach ensures accurate detection of harassment behavior while enhancing workplace safety through real-time face recognition and alert notifications.
This module leverages a CNN-based model to differentiate harassment behaviors from normal workplace activities in videos.
A real-time monitoring solution using facial recognition technology integrated with safety protocols.
Install the following libraries:
Harassment Detection:
yes (harassment images) and no (healthy environment images).Face Recognition:
Harassment Detection:
Safety Monitoring System:
Achieved 98% training accuracy and 97% validation accuracy.
Machine Learning:
Face Recognition:
Deployment:
Optimization:
By combining Harassment Detection with a Safety Monitoring System, this project addresses workplace safety comprehensively. It fosters a secure environment, supports HR processes, and promotes early intervention for safety and harassment concerns.
𝐄𝐦𝐚𝐢𝐥 𝐀𝐥𝐞𝐫𝐭 𝐅𝐮𝐧𝐜𝐭𝐢𝐨𝐧
𝐓𝐡𝐢𝐬 𝐟𝐮𝐧𝐜𝐭𝐢𝐨𝐧 𝐬𝐞𝐧𝐝𝐬 𝐚𝐧 𝐞𝐦𝐚𝐢𝐥 𝐚𝐥𝐞𝐫𝐭 𝐰𝐢𝐭𝐡 𝐚𝐧 𝐢𝐦𝐚𝐠𝐞 𝐚𝐭𝐭𝐚𝐜𝐡𝐦𝐞𝐧𝐭 𝐰𝐡𝐞𝐧 𝐡𝐚𝐫𝐚𝐬𝐬𝐦𝐞𝐧𝐭 𝐢𝐬 𝐝𝐞𝐭𝐞𝐜𝐭𝐞𝐝.
def send_alert(frame, incident_details): sender_email = "your_email@example.com" # Replace with your email receiver_email = "receiver_email@example.com" # Replace with the recipient's email password = "your_email_password" # Use app-specific password for security # Save the frame as an image incident_image = "incident.jpg" cv2.imwrite(incident_image, frame) # Set up email msg = MIMEMultipart() msg['From'] = sender_email msg['To'] = receiver_email msg['Subject'] = "Harassment Alert" body = incident_details msg.attach(MIMEBase('application', 'octet-stream')) # Attach the image with open(incident_image, 'rb') as file: part = MIMEBase('application', 'octet-stream') part.set_payload(file.read()) encoders.encode_base64(part) part.add_header('Content-Disposition', f"attachment; filename={incident_image}") msg.attach(part) # Send the email try: server = smtplib.SMTP('smtp.gmail.com', 587) server.starttls() server.login(sender_email, password) server.sendmail(sender_email, receiver_email, msg.as_string()) server.quit() print("Alert sent successfully!") except Exception as e: print(f"Failed to send email: {e}")