Human trafficking

ABSTRACT:-

The government defines human trafficking as “modern slavery”. Human trafficking includes both sex trafficking and forced labour. In our research, we specifically focus  on both types of human trafficking. Trafficking victims are coerced or tricked into trading for money. Human trafficking is the fastest growing organized crime, according to the FBI. and the third largest criminal enterprise in the world.The International Labor Organization estimates that there were 4 million victims of human trafficking  in 2017 alone. Machine learning is increasingly giving us insight into previously obscure problems by finding helpful signals in large amounts of noisy data. We are passionate about using these tools to create a positive social impact. The main conception of our design is to experiment with the use of deep neural networks to quickly detect and respond to ongoing crimes, with an effective crime detection and prosecution system of  people  to reduce the crime rate.Surveillance can take colorful forms, such as detecting a malicious effort related to a specific reality, a specific person in  CCTV video) or tracking people’s movements in general. Also, manual hunting can be very difficult. This is done using facial recognition plus video processing.The current system in this area aims to search for a reality in a video by rooting its face and comparing (or running) it to a database of human faces of interest. No system will stop the task if it doesn’t have a predefined database to compare. Our intelligent AI will do this in an intelligent way, first  generating human facial datasets from CCTV video and using them in a facial recognition model that we will use. To accomplish this task, deep learning libraries like OpenFace are used along with  image processing tools like openCV.On the other hand, if the victim’s face and the perpetrator’s face  match  our existing record, we  send an alert  to all police departments with the victim’s face information and exact location. This makes it the easiest way to catch the criminal. The idea behind the project is the ability to sort through a massive amount of data to find patterns  useful for law enforcement. This type of data analysis was technologically impossible a few decades ago, but the hope is that recent developments in deep  learning neural networks  are up to the task.The project uses computer vision and other techniques to detect potentially criminal anomalies in real-time surveillance videos with facial recognition and gait analysis technology, helping us  use advanced intelligence concepts to find and track people.

EXISTING SYSTEM:-

Given the level of human interaction and burden of proof required in human trafficking investigations, black box approaches are not ideal. Law enforcement officers require justification behind their actions. In addition, they do not have the resources to read through the millions of ads that are posted everyday. An ideal methodology would not only identify features used to classify human trafficking but be able to do so with minimal supervision. We develop a pipeline that can do exactly that. After pre-processing, we use unsupervised NLP features on a bag of words representation of each ad to train interpretable models

PROPOSED SYSTEM:-

The main conception of our design is to experiment using deep neural networks to briskly descry and respond to ongoing crimes with an effective crime discovery and people tracking system to reduce the crime rate. Monitoring can take colorful forms, e.g. detecting vicious exertion, relating a specific reality, a specific person in a CCTV video) or tracking people’s movements in general. Also, manual chasing can be authentically difficult. This is done using facial recognition plus video processing. The current system in this area aims to search for an reality on video by rooting its face and comparing( or running) it to a database of human faces of interest., no system will break the task if it doesn’t have a predefined database to compare against. Our smart AI will do this intelligently, first by generating human face datasets from CCTV video and using them in a face recognition model that we will use. To negotiate this task, deep learning libraries like OpenFace are used along with some image processing tools like openCV. In other side if victim and criminal face gets match with our existing dataset then we will send alert message to all police stations with victim face information and exact location. This thing makes easiest way to catch the criminal. The idea behind the project is to being able to sort through a massive volume of data to find patterns that are useful for law enforcement. This kind of data analysis was technologically impossible a few decades ago, but the hope is that recent developments in deep learning neural networks are up to the task. The project uses computer vision and other techniques to spot potentially criminal anomalies on real-time surveillance video with facial recognition and gait analysis technology help us to use advanced intelligence concepts to find and track individuals.

MODULES:-

• Police administrator Register/Login: Administrator have to register themself to be part of this surveillance system.
  
  
• Victim and criminal Face Registration: By using face recognition API collecting face landmark and encoding face data to store and all the metadata stored in block chain.

• View Victim and criminal: View all Victim and criminal data to the police administrator who register.

• Start recognition: By using face recognition API we detect the person is victim or criminal capture in surveillance camera and retrieve all information from the block chain and send on the police station mail.

APPLICATION:-

• Quick notifications about criminal location.
• Better approach to find missing and suspicious people.
• Better scan to run facial recognition to search for potential criminals or missing people.
• Reduced human effort.
• Tracking criminals at faster rate.
• Footage is available at all times.
• Provides efficient surveillance.

HARDWARE AND SOFTWARE REQUIREMENTS:-

HARDWARE:-

• Processor: Intel Core i3 or more.
• RAM: 4GB or more.
• Hard disk: 250 GB or more.
• Web camera

SOFTWARE:-

• Operating System : Windows 10, 7, 8.
• python
• anaconda
• Spyder, Jupyter notebook, Flask.
• mysql