1. 1
1.1 OVERVIEW
This project is aimed to identify the criminals in any investigation department. Here the
technique is we already store some images of the criminals in our database along with his
details and that images are segmented into many slices say eyes, hairs, lips, nose, etc. These
images are again stored in another database record so to identify any criminals;
eyewitnesses will see the images or slices that appear on the screen by using it we develop
the face, which may or may not be matched with our images. If any image is matched up to
99% then we predict that he is only the criminal. Thus using this project it provides a very
friendly environment for both operator and eyewitness to easily design any face can identify
criminals very easy.
Face detection can be regarded as a specific case of object-class detection. In object-
class detection, the task is to find the locations and sizes of all objects in an image that
belong to a given class. Examples include upper torsos, pedestrians, and cars. That is, the
detection of faces that are either rotated along the axis from the face to the observer (in-
plane rotation), or rotated along the vertical or left-right axis (out-of-plane rotation), or both.
The newer algorithms take into account variations in the image or video by factors such as
face appearance, lighting, and pose.
2. 2
1.2 OBJECTIVE
This project is intended to identify a person using the images previously taken. The
Identification will be done according the previous images of different persons. Face
detection is gaining the interest of marketers. A webcam can be integrated into a television
and detect any face that walks by. The system then calculates the race, gender, and age
range of the face. Once the information is collected, a series of advertisements can be
played that is specific toward the detected race/gender/age.
Good face recognition algorithms and appropriate preprocessing of the images can
compensate for noise and slight variations in orientation, scale and illumination. Finally,
technologies that require multiple individuals to use the same equipment to capture their
biological characteristics potentially expose the user to the transmission of germs and
impurities from other users. However, face recognition is totally non-intrusive and does not
carry any such health risks.
3. 3
1.3 ADVANTAGES
Very fast and accurate.
No need of any extra manual effort.
No fever of data loss.
Just need a little knowledge to operate the system.
Doesn’t require any extra hardware device.
At last very easy to find the criminals.
1.4 DISADVANTAGES
Need of extra manual effort.
It used to take much time to find any criminals.
Not very much accurate.
Danger of losing the files in some cases.
Need Good Knowledge in drawing.
4. 4
2.1 OVERVIEW
Construction and updating of the criminal record and face. Addition, Clipping.
Comparing the image with the faces that are there in our database.
If any new images are found then it should be entered into our database by add
image module and then it should be segmented into different slices.
You can also have a option to change the password.
Segmentation is performed by comparing.
5. 5
2.2 FEASIBILITY STUDY
Once the problem is clearly understood, the next step is to conduct feasibility study,
which is high-level capsule version of the entered systems and design process. The
objective is to determine whether or not the proposed system is feasible. The three tests of
feasibility have been carried out.
2.2.1 Technical Feasibility
2.2.2 Economical Feasibility
2.2.3 Operational Feasibility
2.2.1 TECHNICAL FEASIBILITY
In Technical Feasibility study, one has to test whether the proposed system can
be developed using existing technology or not. It is planned to implement the proposed
system using java technology. It is evident that the necessary hardware and software
are available for development and implementation of the proposed system. Hence, the
solution is technically feasible.
2.2.2 ECONOMICAL FEASIBILITY
As part of this, the costs and benefits associated with the proposed system
compared and the project is economically feasible only if tangible or intangible
benefits outweigh costs. The system development costs will be significant. So the
proposed system is economically feasible.
2.2.3 OPERATIONAL FEASIBILITY
It is a standard that ensures interoperability without stifling competition and
innovation among users, to the benefit of the public both in terms of cost and service
quality. The proposed system is acceptable to users. So the proposed system is
operationally feasible.
6. 6
2.3 SUMMARY
Face Identification is a technique that is mainly used to identify criminals based on the
clues given by the eyewitnesses. Based on the clues we develop an image by using the
image that we have in our database and then we compare it with the images already we
have. To identify any criminals we must have a record that generally contains name, age,
location, previous crime, gender, photo, etc.
7. 7
3 PROBLEM DEFINITION
The face recognition problem can be formulated as follows: Given an input face image
and a database of face images of known individuals, how can we verify or determine the
identity of the person in the input image.
Furthermore, the human face is not a unique, rigid object. Indeed, there are numerous
factors that cause the appearance of the face to vary. The sources of variation in the facial
appearance can be categorized into two groups: intrinsic factors and extrinsic ones. Intrinsic
factors are due purely to the physical nature of the face and are independent of the observer.
Determine the identity of a face in an image
The image can be a frame from a video
Processing needs to be fast
Classification problem
Need faces images for training
8. 8
4.1 HARDWARE REQUIREMENTS
Processor : 500 MHz above
Hard disk : 500 MB
RAM : 256 MB
4.2 SOFTWARE REQUIREMENTS
Operating System : Windows XP
Database Server : SQLite
Programming Language : Java 7
Frame Work : Swing
4.3 PERIFERAL
Webcam : 1.3 MP and above
13. 13
5.2 SNAPSHOTS
LOGIN FORM
The inputs to the process are User Id and Password given by the developer to
allow the software available for the user environment. After giving the inputs the code
checks whether the entered ones are valid are not. It displays screen if match occurs
otherwise error message if they are not matched.
Fig.5.2.1:- Login Form
MAIN FORM
This process mainly explains the different screens that are available for the
operator. Here the selection of the screen depends on the operator and he can select
whatever screen he wants.
Fig.5.2.2:- Main Form
14. 14
NEW CRIMINAL FORM
This process clearly illustrates adding the details of the criminal such as name,
alias name, age, gender, location, address, state and city along with his photo.
Fig.5.2.3:- New Criminal Form
CLIP IMAGE FORM
This is used for clipping the image into different slices say eyes, forehead, lips,
hair and nose. The input for this is face which is divided into some slices which are
stored in the database.
Fig.5.2.4:- Clip Image Form
15. 15
CONSTRUCT FACE FORM
Based on the instruction given by the eyewitnesses, the operator brings the clips
of the images from the database and then goes for the construction of the image based on
those clips.
Fig.5.2.5:- Construct Face Form
FIND FACE FORM
In this process we are finding the criminal’s face the image constructed before
and stored in the database.
Fig.5.2.6:- Find Face Form
16. 16
MOST SUITABLE SUSPECT FORM
In this form the image of the most possible suspect is displayed which had been
constructed before this process. It is done on the basis of probability of matching clips to
stored images.
Fig.5.2.7:- Most Suitable Suspect Form
62. 62
5.4 TESTING
The completion of a system is achieved only after it has been thoroughly tested.
Though this gives a feel the project is completed, there cannot be any project without going
though this stage. Though the programmer may have taken many precautions not to commit
any mistakes that crop up during the execution stage. Hence in this stage it is decided
whether the project can under go the real time environment execution without any break
downs, therefore a package can be rejected even at this stage.
The testing phase involves the testing of the developed system using various kinds of
data. An elaborated testing of data is prepared and a system is tested using the test data.
While testing errors are noted and corrections remade, the corrections are also noted for
future use.
5.4.1 SYSTEM TESTING
Testing is a set of activities that can be planned in advance and conducted
systematically. The proposed system is tested in parallel with the software that consists
of its own phases of analysis, implementation, testing and maintenance. Following are
the tests conducted on the system.
5.4.2 UNIT TESTING
During the implementation of the system each module of the system was tested
separately to uncover errors with in its boundaries. User interface was used as a guide
in the process.
63. 63
Table.5.4.2 Unit Testing
Sr.No. Screen Input Output Remarks
1 Login Page User Id
Password
User
validation
User will enter into
Main Screen
2 Main Screen
File
New
Criminal
Details are
entered
Details are
stored in
the
database
New Menu is
selected to enter new
criminal details.
3 Main Screen
File
Show
Details
Display option
is clicked.
Criminal
Details are
displayed
Display details menu
is selected to get
details from database.
4 Main Screen
File
Exit
Exit Option is
Clicked.
Screen
will be
exited
Screen will be shut
down
5 Main Screen
Edit
Clip Image
Criminal Image
is clipped into
different parts
The clips
are stored
in database
Clip image menu is
selected to clip image
and store them in
database
6 Main Screen
Edit
Update
Details
Changes in the
details of the
criminals are
entered
Details of
the
criminal
are updated
Update details menu
is selected to update
the details of the
criminals
7 Main Screen
Identificatio
n
Construct
Face
Different clips
of criminals are
selected and
arranged in
order
Face of
the
criminal is
constructed
Construct face menu
is to construct the
criminal face from
various clips stored in
the database.
64. 64
8 Main Screen
Identificatio
n
Find Face
Show all
suspects is
checked
All
suspects
detail along
with photo
are
displayed
Show more suspect
menu is selected to
get the details of all
suspects and more
possible suspect
involved in crime.
9 Main Screen
Help
About
About Face
Identification is
checked
The
version and
the
overview
of the
system is
displayed
About face
identification system
menu is selected to
get the details of
above system.
65. 65
6.1 FUTURE WORK
All current face recognition algorithms fail under the vastly varying conditions under
which humans need to and are able to identify other people. Next generation person
recognition systems will need to recognize people in real-time and in much less constrained
situations. Technology used in smart environments has to be unobtrusive and allow users to
act freely. Wearable systems in particular require their sensing technology to be small, low
powered and easily integral with the user's clothing. Considering all the requirements,
identification systems that use face recognition and speaker identification seem to us to have
the most potential for wide-spread application. Audio and video based recognition systems
have the critical advantage that they use the modalities humans use for recognition. Finally,
researchers are beginning to demonstrate that unobtrusive audio-and-video based person
identification systems can achieve high recognition rates without requiring the user to be in
highly controlled environments.
6.2 CONCLUSION
The purpose of face Identification system is to identify criminals. In past years this
process is carried out by humans. This process gives the exact image of the criminal but it is
very difficult to identify the criminal details and also it requires much amount of human
burden.
The main aim of our project is to overcome the drawbacks of human based system by
using the machine based face Identification process. In this process we store the details of
criminal into the database along with his photo or image. Then we make the image
into different clips containing hair, forehead, eyes, nose, lips and chin and store these clips
into the database. When any crime occurs we compare the details given by the eyewitness
with the clips already stored in the database and we will identify the criminal. This project
can be extended to adjust the gaps between the clips after construction of the image to be a
perfect photograph using Image processing Techniques.
66. 66
7 REFERENCES
IEEE/REPUTED JOURNAL PAPERS
[1]Yang M.H., Kriegman D.J., and Ahuja N., “Detecting Faces in Images: A Survey”,
IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.24, No.1, January
2002.
[2] Rowley H. A., Baluja S. , Kanade T., “Neural Network- Based Face Detection”,
IEEE Trans. On Pattern Analysis and Machine Intelligence, vol.20, No. 1, Page(s). 39-
51, 1998.
[3] S. Arya and D.M. Mount. Algorithms for fast vector quantization. In J. A. Storer and
M. Cohn, editors, Proceedings of DCC 93: Data Compression Conference, pages 381–
390. IEEE Press, 1993.
BOOKS
[4] Herbert Schildt,”The Complete Reference Java2”, Tata McGraw-Hill, Chapter No.1,
publishing Company Limited, Page. No.3-9.
[5] Roger S. Pressman,”Software Engineering”, A Practitioner’s Approach”, Tata
McGraw-Hill Publishing Company Limited, Page. No.6-13.
WEBSITES
[6] http://www.java.sun.com/products/java.index.php
[7] http://www.facedetec tion.org/ facedetec tion
[8] http://www.faceidentification.com.php