e-ISSN: 2582-5208

International Research Journal of Modernization in Engineering Technology and Science

Volume:03/Issue:04/April-2021 Impact Factor- 5.354 www.irjmets.com

CRIMINALS AS WELL AS CRIME DETECTION USING MACHINE LEARNING

& OPENCV
Aditya Tripathi *1, Abhishek Yadav*2, Tapan Poojary*3, Jaya Jeswani*4
*1,2,3Student, Information Technology, Xavier Institute of Engineering, Mumbai, Maharashtra, India
*4Professor, Department of Information Technology, Xavier Institute of Engineering, Mumbai,
Maharashtra, India
ABSTRACT
Finding criminals or hunting for people, in a CCTV video footage, after a crime scene or major attack takes place,
is a time-consuming task. Pattern Analytical System and Data Mining techniques are powerful tools that helps
in removing covered up information from a huge dataset to upgrade exactness and productivity of estimating.

Traditional prediction frameworks are hard to manage the enormous information and exactness of crime
detection. As informed to us by cyber cell members, they make multiple members of the department sit with
laptops and computers literally to search through the CCTV footage to find and trace the guilty, as they don't
have the automated system for doing this task with them. This process is both time and labor intensive.

In this research paper we have tried to survey the existing technologies as well as we propose a new system for
criminal Detection & Recognition using Cloud Computing and Machine Learning, which if used by our Crime
Agencies would definitely help them to find criminals from CCTV footage. The proposed system can not only
help find criminals but if used properly on different sites such as railway stations etc, can also help find missing
children and people from the CCTV footage available from the respective site. Existing solutions use traditional
face recognition algorithms which can be troublesome in changing Indian environments especially factors like
light, weather and especially orientation.

Keywords: Machine Learning, Prediction, Data Mining, Analytics, Estimation, Pattern.

I. INTRODUCTION
Circuit Television Cameras (CCTV’s) are widely used to control occurrence of crimes in the surroundings.
Although CCTV’s are deployed at various public and private areas to monitor the surroundings there is no
improvement in the control of crimes. This is because CCTV requires human supervision which can cause
human prone errors like missing of some important crime events by human while monitoring numerous
screens recorded by CCTV’s at same time and Retrieval of images with object-of-interest from a vast pool of
social media images has been a research interest in cybercrime research community for detecting criminal
behavior’s in social media. Due to inherent diversity and therefore the low duplicate property of images on
social media, it brings forth many challenges in image retrieval, especially in identifying distinct features for a
given object-of-interest. The quick and accurate identification of criminal activity is paramount to securing any
residence. With the rapid climb of smart cities, the mixing of crime detection systems seeks to enhance this
security. In the past a robust reliance has been placed on standard video surveillance so as to realize this goal.
This often creates a backlog of video data that has got to be monitored by a supervising official. For large urban
areas, this creates an increasingly large workload for supervising officials which leads to an increase in error
rate Automatic recognition of violence between individuals or crowds in videos in real time is very difficult but
at the same time, if it is implemented in a right direction can provide a high accurate result.
Our Problem revolves around 4 different types of crimes i.e.
1) Crimes happening by the known criminal in real time.
2) Crimes happening by unknown criminal in real time.
3) Crimes like mob lynching which normally happens in crowd
4) Crimes like stealing of vehicles.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2135]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:03/Issue:04/April-2021 Impact Factor- 5.354 www.irjmets.com
II. METHODOLOGY
1. The input for the model will consist of the image and video feeds.

2. Once the dataset is ready with all the known criminal’s data, we can pass it to our system which is a live
CCTV Surveillance. So due to this if any particular moment camera recognizes a criminal and it gets matched
with our dataset…It will give a message and alarm to the guard who will be at that moment monitoring the
surveillance and also one message will go directly to the command center of police with the camera no. and
location of the particular criminal.

3. If a crime is done by a normal person then without having any information about it. Police cannot catch him,
in that with our system since it is capturing face of all the people passing through it…will try to scan that
particular image to all the official websites, Facebook, Instagram etc.

4. Crimes like Mob-Lynching, fights between groups are often seen in India and all the people standing their
they take videos of crime instead of calling the police. So, in this scenario our system with help of machine
learning and artificial intelligence will try to recognize the crime scene as a normal scene or any anomaly or
unwanted happening in the scene. If it detects something uneven the images, videos, and location of that crime
will be directly sent to the nearest police station.

5. Suppose there is a situation wherein someone parks his/her Car or Bike in the parking lot of their society
and in night, a thief robbed the bike and leaving the societies gate, so our system will work as an alarm system
wherein in our database we will have all the entries of cars and bikes number plate in that society with their
owners name and phone number. so, our system using the cameras located on the gate will detect and
recognize the number plate and will send a SMS by saying that your bike/car just leaved the gate.so by this
instead of owner getting understand about the robbery of bike in morning he/she will get and instant message
and can catch the criminal faster.

Algorithm:

Step 1 : Start

Step 2 : Accept the input image or video

Step 3 : Perform an analysis of the captured images by comparing it with trained data.

Step 4 : Objects are classified then localized using object detection algorithm

Step 5 : Combination of classification and localization results in the identification of an object.

Step 6 : Based on identification predictions are made and probability is found.

Step 7 : The prediction having the largest probability will be the output.

Step 8 : The output tells the crime is detected or not.

Step 9 : Alert the respective police authority for the location of the crime .

Step 10 : Look if the crime persists or not.

III. MODELING AND ANALYSIS
We have divided our project in 3 modules and in the end it will be a whole system in which all these
features will be implanted and can be directly used by any of the CCTV Camera.

Module 1: Known Criminals like e.g. Dawood using HAAR Cascade.

Module 2: Live Crime detecting and passing it to the control room(Mob- Lynching):

Module 3: Vehicle Theft

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2136]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:03/Issue:04/April-2021 Impact Factor- 5.354 www.irjmets.com

Figure 1: Overview of the System

IV. RESULTS AND DISCUSSION
Module 1: Known Criminals like e.g. Dawood using HAAR Cascade:

Since we have a lot of images of Dawood and lot of information to…we can train our data with its face, eyes etc.
Once the dataset is ready with all the known criminal’s data, we can pass it to our system which is a live CCTV
Surveillance. So due to this if any particular moment camera recognizes a criminal and it gets matched with our
dataset…It will give a message and alarm to the guard who will be at that moment monitoring the surveillance
and also one message will go directly to the command centre of police with the camera no. and location of the
particular criminal.

Due to this…if police want to catch the criminal it can go directly catch or if police want to track the criminal or
navigates its whole plan…then it can also put an eye on it and try to recognize its plan…or the reason of coming
to that location.

Figure 3:Image of the criminal detected

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2137]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:03/Issue:04/April-2021 Impact Factor- 5.354 www.irjmets.com

Figure 4: Video consisting frame of Criminal detected

Module 2: Live Crime detecting and passing it to the control room(Mob- Lynching):

Crimes like Mob-Lynching, fights between groups are often seen in India and all the people standing their they
take videos of crime instead of calling the police. So, in this scenario our system with help of machine learning
and artificial intelligence will try to recognize the crime scene as a normal scene or any anomaly or unwanted
happening in the scene. If it detects something uneven the images, videos, and location of that crime will be
directly sent to the nearest police station.

All this will be happening at a real time. In today’s scenario…first the crime is happened and after then police
investigates but with our system in between crime police can reach to the location at a fast rate.

Figure 5: Live Crime Detection

Module 3: Vehicle Theft:

Suppose there is a situation wherein someone parks his/her Car or Bike in the parking lot of their society and
in night, a thief robbed the bike and leaving the societies gate, so our system will work as an alarm system
wherein in our database we will have all the entries of cars and bikes number plate in that society with their
owners name and phone number. so, our system using the cameras located on the gate will detect and
recognize the number plate and will send a SMS by saying that your bike/car just leaved the gate.so by this
instead of owner getting understand about the robbery of bike in morning he/she will get and instant message
and can catch the criminal faster.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2138]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:03/Issue:04/April-2021 Impact Factor- 5.354 www.irjmets.com

Figure 6: LPN Detecting Method

Figure 7: License Plate Number detection in Single Car

Figure 8: License Plate Number detection in Multiple Car

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2139]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:03/Issue:04/April-2021 Impact Factor- 5.354 www.irjmets.com

Figure 9: The correct number plate detected and Message Sent

V. CONCLUSION
In this research, we encountered several face recognition algorithms along the way. Some were really accurate
while some were really slow. Our research found that Striking a balance between the Accuracy & Speed is really
difficult. Some of the algorithms we came across through means of this research are HAAR , Eigen Faces, Cam
shift , CNNs, Viola-Jones Algorithm, Gaussian ,Eucledian distance, AdaBoost etc.
The most famous detection algorithm we came across through this research was HAAR. We also came across
and learned about the Microsoft Azure, which bundle of the cloud computing services that are created by
Microsoft which can be used for building, testing, as well as deploying, and managing the applications and
services using a global network of the data centres managed by Microsoft , which has the various Face API
services which is basically cloud based service which provides algorithms for analysing the human faces found
in images and videos. It is fast and accurate and thus our survey and the research helped us choose & use of
Microsoft Azure to take care of our face recognition need.
The above proposed approach will be implemented in the next phase of this project which will help us superior
verify the performance and high accuracy of this approach with very low latency. Accuracy is of paramount
importance for a project of this sensitivity. Also important is the ability to run on any machine regardless of the
how powerful the hardware is . These both lead us to choose the Azure face API. The proposed methodology
when implemented successfully could definitely be of great help to our Criminal agencies in detecting and
finding of criminals, also search for missing people.

VI. REFERENCES
[1] S.Shirsat, A.Naik, D.Tamse, J.Yadav, P. Shetgaonkar, S.Aswale, “Proposed System for Criminal Detection
and Recognition on CCTV Data Using Cloud and Machine Learning”, 2019 International Conference on
Vision Towards Emerging Trends in Communication and Networking (ViTECoN), ISBN: 978-1-5386-
9353-7, DOI: 10.1109/ViTECoN.2019.8899441.
[2] AMR. Abdali, RFA. Tuma, “Robust Real-Time Violence Detection in Video Using CNN And LSTM”, 2019
2nd Scientific Conference of Computer Sciences (SCCS), University of Technology - Iraq, ISBN: 978-1-
7281-0761-5, DOI: 10.1109/SCCS.2019.8852616
[3] S. Ali, SA. Alvi, Atiq Ur Rehman, “The Usual Suspects: Machine Learning Based Predictive Policing for
Criminal Identification”, 2019 13th International Conference on Open Source Systems and
Technologies (ICOSST), ISBN:978-1-7281-4613-3, DOI:10.1109/ICOSST48232.2019.9043925.
[4] J.Li, X.Jiang, T.Sun, K.Xu, “Efficient Violence Detection Using 3D Convolutional Neural Networks”, 2019
16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), ISBN:
978-1-7281-0990-9,DOI: 10.1109/AVSS.2019.8909883
[5] M.Ramzan, A. Abid, H. Khan, S. Awan, A. Ismail, M. Ahmed, M. Ilyas, A. Mahmood, “A Review on state-of-
the-art Violence Detection Techniques”, DOI 10.1109/ACCESS.2019.2932114, IEEE Access.
[6] L.Elluri, V.Mandalapu, N.Roy, “Developing Machine Learning based Predictive Models for Smart
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[2140]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:03/Issue:04/April-2021 Impact Factor- 5.354 www.irjmets.com
Policing”, 2019 IEEE International Conference on Smart Computing (SMARTCOMP), ISBN: 978-1-7281-
1689-1, DOI: 10.1109/SMARTCOMP.2019.00053.
[7] M.Soliman, M.Kamal, M.Nashed, Y.Mostafa, B.Chawky, D.Khattab, “Violence Recognition from Videos
using Deep Learning Techniques”, 2019 IEEE Ninth International Conference on Intelligent Computing
and Information Systems (ICICIS), ISBN: 978-1-7281-3995-1, DOI:
10.1109/ICICIS46948.2019.9014714.
[8] S. Chackravarthy, S. Schmitt, Li. Yang,” Intelligent Crime Anomaly Detection in Smart Cities using Deep
Learning”, 2018 IEEE 4th International Conference on Collaboration and Internet Computing, ISBN:
978-1-5386-9502-9, DOI: 10.1109/CIC.2018.00060.
[9] A. Mumtaz, Ab. Sargano, Z.Habib, “Violence Detection in Surveillance Videos with Deep Network using
Transfer Learning”, 2018 2nd European Conference on Electrical Engineering and Computer Science
(EECS), ISBN: 978-1-7281-1929-8, DOI: 10.1109/EECS.2018.00109.
[10] U. Navalgund, Priyadarshini. K, “Crime Intention Detection System Using Deep Learning”, 2018
International Conference on Circuits and Systems in Digital Enterprise Technology (ICCSDET), ISBN:
978-1-5386-0576-9, DOI: 10.1109/ICCSDET.2018.8821168.
[11] K. Rasanayagam, K.S.D.D.C, W.A.D.D, S.N.T, Dr. P. Samarashinge, S.E.R. Siriwardana, “CIS: An Automated
Criminal Identification System”, 2018 IEEE International Conference on Information and Automation
for Sustainability (ICIAfS), ISBN: 978-1-5386-9418-3, DOI: 10.1109/ICIAFS.2018.8913367.
[12] X. Chen, X. Yang, M. Wang,Ji. Zou, “Convolution Neural Network for Automatic Facial Expression
Recognition”, 2017 International Conference on Applied System Innovation (ICASI), ISBN: 978-1-5090-
4897-7, DOI: 10.1109/ICASI.2017.7988558.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2141]