Missing Child Recognition System

A dissertation submitted to the Jawaharlal Nehru Technological University, Hyderabad

in partial fulfilment of the requirement for the award of degree of

BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING

Submitted by

K. Chandrika (21B81A05L3)

P. Charmila (21B81A05L4)

A. Sirisha (21B81A05P9)

Under the Guidance of

Mrs. K Deepthi Reddy
Sr. Assistant Professor

Department of Computer Science and Engineering

CVR COLLEGE OF ENGINEERING

(An UGC Autonomous Institution, Affiliated to JNTUH, Accredited by NBA, and
NAAC) Vastunagar, Mangalpalli (V), Ibrahimpatnam (M),
Ranga Reddy (Dist.) - 501510, Telangana State

2024-2025
 CVR COLLEGE OF ENGINEERING
(UGC Autonomous Institution)
Affiliated to JNTU Hyderabad
Vastunagar, Mangalpalli (V), Ibrahimpatnam (M),
Ranga Reddy (Dist.), Hyderabad – 501510, Telangana State

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE

This is to certify that the project work entitled “Missing Child Recognition System” is
being submitted by K. Chandrika (21B81A05L3), P. Charmila (21B81A05L4), A.
Sirisha (20B81A05P9) in partial fulfilment of the requirement for the award of the degree
of Bachelor of Technology in Computer Science and Engineering, during the academic
year 2024-2025.

Project Guide Professor-in-charge projects

Mrs. K Deepthi Reddy Dr.M.Raghava
Sr.Assistant Professor

External Examiner Professor and Head, CSE

Dr. A. Vani Vasthala

ii
 DECLARATION

I hereby declare that this project report titled “Missing Child Recognition System” submitted
to the Department of Computer Science and Engineering, CVR College of Engineering, is a
record of original work done by me under the guidance of Deepthi Reddy. The information
and data given in the report is authentic to the best of my knowledge. This project report is
not submitted to any other university or institution for the award of any degree or diploma or
published at any time before.

K. Chandrika (21B81A05L3)

P. Charmila (21B81A05L4)

A. Sirisha (20B81A05G9)

Date:

Place:

iii
 ACKNOWLEDGEMENT

The satisfaction that accompanies the successful completion of any task would be
incomplete without the mention of the people who made it possible and whose
encouragement and guidance has been a source of inspiration throughout the course of the
project.

We sincerely thank our project guide Mrs.K Deepthi Reddy, Assistant Professor, under
whom we have carried out the project work. Their incisive and objective guidance and
timely encouraged us with constant flow of energy to continue the work.

It is a great pleasure to convey our profound sense of gratitude to Dr. Vani Vathsala,
Professor & Head of Department CSE Department, CVR College of Engineering, for
having been kind enough to arrange necessary facilities for executing the project in the
college.

We thank our Vice- Principal Prof. L. C. Siva Reddy for providing excellent computing
facilities and a disciplined atmosphere for doing our work.

We wish a deep sense of gratitude and heartfelt thanks to our principal Dr. Rama Mohan
Reddy and Management for providing excellent lab facilities and tools. Finally, we thank
all those guidance helpful to us in this regard.

K Chandrika(21B81A05L3)

P Charmila(21B81A05L4)

A Sirisha(21B81A05P9)

iv
 ABSTRACT

In India, a countless number of children are reported missing every year. Among the
missing child cases, a large percentage of children remain untraced. This paper
presents a novel use of deep learning methodology for identifying the reported
missing child from the photos of a multitude of children available, with the help of
face recognition. The public can upload photographs of a suspicious child into a
common portal with landmarks and remarks. The photo will be automatically
compared with the registered photos of the missing child from the repository.
Classification of the input child image is performed and the photo with the best match
will be selected from the database of missing children. For this, the machine learning
model is trained to correctly identify the missing child from the missing child image
database provided, using the facial image uploaded by the public.

v
 TABLE OF CONTENTS
S.No Description Page No.

List of Figures vii

Abbreviations viii
1 INTRODUCTION 1
1.1 Motivation 1

1.2 Problem Statement 2

2 LITERATURE REVIEW 3
2.1 Existing Work 3
3 REQUIREMENT ANALYSIS 4
3.1 Software requirements 4
3.2 Hardware requirements 4
3.3 Functional requirements 5
3.4 Non-Functional requirements 6
4 PROPOSED SYSTEM DESIGN 7
4.1 Proposed System architecture 7
4.2 Use case Diagram 11
4.3 Class Diagram 12
4.4 Activity Diagram 13
4.5 Sequence Diagram 14
4.6 Collaboration Diagram 15
4.7 Component Diagram 16
4.8 Deployment Diagram 17
5 IMPLEMENTATION AND TESTING 18
5.1 Modules 18
5.2 Algorithms 19
5.4 Testing 24
6 CONCLUSION & FUTURE SCOPE 40
6.1 Conclusion 40
6.2 Future Scope 41
REFERENCES 42
vi
 LIST OF FIGURES

Figure Title Page

4.1 System Architecture 7

4.2 Use Case Diagram 11

4.3 Class diagram 12

4.4 Activity diagram 13

4.5 Sequence diagram 14

4.6 Collaboration diagram 15

4.7 Component diagram 16

4.8 Deployment diagram 17

5.1 Home Page 24

5.2 Authority Page 26

5.3 Authority Home Page 28

5.4 Add Child Page 30

5.5 Alerts Page 33

5.6 Report Sighting page 35

5.7 Child Found page 37

5.8 Child Not Found page 39

vii
 ABREVIATIONS

HOG Histogram Oriented Gradients

KNN K Nearest Neighbors
NGO Non-Governmental Organization

viii
 CHAPTER 1

INTRODUCTION

An idea for maintaining a virtual space is proposed, such that the recent photographs of
children given by parents at the time of reporting missing cases are saved in a repository. The
public is given the provision to voluntarily take photographs of children in suspected
situations and uploaded them to that portal. Automatic searching of this photo among the
missing child case images will be provided in the application.

This supports the police officials to locate the child anywhere in India.

1.1 MOTIVATION

• Face recognition system has been rapidly growing in various applications such as
airport security, secure door locking system, employee attendance system, etc.

• A huge number of face recognition calculations have been produced a long time
ago.

• Here we propose a methodology for missing child identification that combines

facial feature extraction based on the HOG algorithm and matching based on KNN.

• The proposed system utilizes face recognition for missing child identification.

This is to help authorities and parents in the missing child investigation.

1
1.2 PROBLEM STATEMENT
Children are the greatest asset of each nation. The future of any country depends upon the
right upbringing of its children. India is the second-most populous country in the world and
children represent a significant percentage of the total population. But unfortunately, a large
number of children go missing every year in India due to various reasons including abduction
or kidnapping, run-away children, trafficked children, and lost children. A deeply disturbing
fact about India’s missing children is that while on average 174 children go missing every
day, half of them remain untraced. Children who go missing may be exploited and abused for
various purposes.

As per the National Crime Records Bureau (NCRB) report which was cited by the Ministry
of Home Affairs (MHA) in the Parliament (LS Q no. 3928, 20-032018), more than one lakh
children (1,11,569 in actual numbers) were reported to have gone missing till 2016, and
55,625 of them remained untraced till the end of the year. Many NGOs claim that estimates
of missing children are much higher than reported. The missing from one region may be found
in another region or another state, for various reasons. So even if a child is found, it is difficult
to identify him/her from the reported missing cases. A framework and methodology for
developing an assistive tool for tracing missing child is described in this paper.

2
 CHAPTER 2
LITERATURE SURVEY

Zhongfei Zhang, Srihari, R.K. Rao. A face detection technique and its applications in image
retrieval. Even though this face detection method has relatively high false positives and a low
detection rate (as compared with the dedicated face detection systems in the literature on
image understanding), due to its simple and fast nature, it has been shown that this system
may be well applied in image retrieval in certain focused application domains. Two
application examples are given: one combining face detection with indexed collateral text for
image retrieval regarding human beings, and the other combining face detection with
conventional similarity matching techniques for image retrieval with a similar background.

Ji Tao, Yap-Peng Tan. It is a novel approach to automatic detection and clustering of human
faces presented in videos. In each video shot, continuously appearing human faces are firstly
associated to form face sequences. Instead of matching the face sequences directly, we
partition them into subsequences consisting of similar poses for ease of comparison. Face
subsequences can then be clustered by graph partitioning with the computed affinity matrix.
Prior to that, however, a set of constraints need to be formulated so as to incorporate domain
knowledge into the graph. Moreover, we propose a constraint propagation algorithm to fully
exploit the space-level implications of these constraints.

2.1 Existing Work

In this system, for face detection, we are using a HOG (Histogram of oriented Gradient) based
face detector which gives more accurate results rather than other methodologies like Haar
Cascade and CNN. In the Face recognition process, we are using HOG which is a standard
technique for face feature extraction. The HOG features are extracted for the test image and
also for the training images and finally for classification we are using KNN algorithms which
effectively recognize the face Labels from the input child image.

3
 CHAPTER 3
REQUIREMENT ANALYSIS

3.1 HARDWARE REQUIREMENTS

• Processer : Any Update Processer

• Ram : Min 4 GB

• Hard Disk : Min 100 GB

3.2 SOFTWARE REQUIREMENTS

• Operating System : Windows family

• Technology : Python 3.11.2 IDE : PyCharm

• Front-End : HTML,CSS,JS

• Back-End : Firebase

• Web Framework : Flask

• Libraries:
Requests, NumPy, Pandas, Matplotlib, TensorFlow, Scikit-learn,
Beautiful Soup

3.3 FUNCTIONAL REQUIREMENTS

1. Features and Capabilities: Functional requirements describe the features and

capabilities that the software system should have. For example, in an ecommerce
application, a functional requirement could be the ability to add products to a shopping
cart.

2. User Interactions: They outline the interactions between users and the system. This
includes details about how users input data, interact with the user interface, and receive
outputs or feedback from the system.

4
3. Data Manipulation: Functional requirements often specify how the system should
handle data. This includes data input, storage, retrieval, and manipulation. For instance,
a functional requirement might specify that user data must be stored securely in a
database.

4. External Interfaces: If the system needs to interact with other systems or external
components, functional requirements describe these interactions. This could involve
integrating with third-party services, APIs, or hardware devices.

5. Performance Requirements: Functional requirements may include performance

criteria such as response times, throughput, or concurrency requirements. For example,
a requirement might state that the system must be able to handle a certain number of
simultaneous user connections.

6. Security Requirements: Functional requirements may specify security features and

measures that the system must implement to protect data and ensure the integrity of
the system.

7. Usability: Requirements related to the usability of the system, including user interface
design, accessibility, and user experience, fall under functional requirements.

8. Error Handling: Functional requirements describe how the system should handle
errors and exceptions. This includes providing appropriate error messages, logging
errors, and ensuring graceful degradation in case of failures.

5
3.4 NON-FUNCTIONAL REQUIREMENTS:

1. Portability: The system shall be developed for both windows and Mac operating systems
platforms.

2. Efficiency: The interface between the system and the user should not take more than 2
seconds.

3. Confidentiality: The system shall not display the login credentials. It should display only
the username of the users.

4. Scalability: The system should be scalable to support the unlimited growth of the dataset
records.

5. Data integrity: The system should not allow empty fields to be entered into the form data
fields.

6. Capacity: The system should be able to store unlimited records of basic user information.

7. Reliability: The website users should be able to access the system 99% of the time
without any failure.

8. Usability: The system navigation is easy for the end user and provides a seamless journey
while accessing the system.

9. Availability: The system should be available for the users to use the system any time, they
need.

6
 CHAPTER 4
PROPOSED SYSTEM DESIGN

4.1 PROPOSED SYSTEM ARCHITECTURE

Fig 4.1 System Architecture

It consists of a national portal for storing details of the missing child along with the photo.
Whenever a child missing is reported, along with the FIR, the concerned officer uploads the
photo of the missing child into the portal. The public can search for any matching child in the
database for the images with them. The system will prompt the most matching cases. Once
the matching is found, the officer can get the details of the child.

7
Preprocessing:

Preprocessing input raw images in the context of face recognition involves acquiring the face
region and standardizing images in a format compatible with the HOG methodology employed.
The photographs of missing children acquired by a digital camera or mobile phone are taken
and categorized into separate cases for creating the database of the face recognition system. The
face region in each image is identified and cropped for getting the input face images.

Upload Photo:

It consists of a national portal for storing details of the missing child along with the photo.
Whenever a child missing is reported, along with the FIR, the concerned officer uploads the
photo of the missing child into the portal. The public can upload photos of any suspicious child
at any time into the portal with details like place, time, landmarks, and remarks. The photo
uploaded by the users will be automatically compared with photos of the registered missing
children and if a matching photo with a sufficient score is found, then an alert email will be sent
to the concerned officer. The message will also be visible in the message box of the concerned
officer’s login screen.

Search:

Whenever users upload a photo of a suspected child, the system generates a template vector of
the facial features from the uploaded photo. If matching is found in the repository, the system
displays the most matched photo and pushes a message to the concerned Officer portal or email
the alert message of the matching child. Similarly, the Officer can check for any matching with
the database at any time using the proposed system.

8
UML DIAGRAMS
The System Design Document describes the system requirements, operating environment,
system and subsystem architecture, files and database design, input formats, output layouts,
human-machine interfaces, detailed design, processing logic, and external interfaces.

Global Use Case Diagrams:

Actor: The actor represents the role a user plays with respect to the system. An actor interacts
with but has no control over the use cases.

The actors identified in this system are:

a. System Administrator

b. Customer

c. Customer Care

Identification of use cases:

Use Case: A use case can be described as a specific way of using the system from a user’s

(actor’s) perspective.

Flow of Events
A flow of events is a sequence of transactions (or events) performed by the system. They
typically contain very detailed information, written in terms of what the system should do, not
how the system accomplishes the task. Flow of events are created as separate files or documents
in your favorite text editor and then attached or linked to a use case using the Files tab of a
model element.

9
Relationships in use cases:

Communication:

The communication relationship of an actor in a use case is shown by connecting the actor
symbol to the use case symbol with a solid path. The actor is said to communicate with the use
case.

Uses:
A Uses relationship between the use cases is shown by the generalization arrow from the use
case.

Extends:

The extended relationship is used when we have one use case that is similar to another use case
but does a bit more. In essence it is like a subclass.

SEQUENCE DIAGRAMS

A sequence diagram is a graphical view of a scenario that shows object interaction in a time-
based sequence what happens first, what happens next. Sequence diagrams establish the roles
of objects and help provide essential information to determine class responsibilities and
interfaces.

There are two main differences between sequence and collaboration diagrams: sequence
diagrams show time-based object interaction while collaboration diagrams show how objects
associate with each other.

10
CLASS DIAGRAM:

Identification of analysis classes:

A class is a set of objects that share a common structure and common behavior (the same
attributes, operations, relationships and semantics). A class is an abstraction of real-world items.

4.2 Use Case diagram

In the Unified Modelling Language (UML), a use case diagram is a type of behavioural diagram
defined by and produced from a Use-case analysis. Its objective is to provide a graphical
overview of a system's capabilities in terms of actors, their objectives (represented as use cases),
and any dependencies among those use cases. A use case diagram's primary objective is to
identify which system tasks are carried out for which actor. The system's players can be
represented by their roles.

Fig 4.2: Use Case Diagram

11
4.3 Class diagram:

The class diagram is used to refine the use case diagram and define a detailed design of the
system. The class diagram classifies the actors defined in the use case diagram into a set of
interrelated classes. The relationship or association between the classes can be either an "is-a"
or "has-a" relationship. Each class in the class diagram may be capable of providing certain
functionalities. These functionalities provided by the class are termed "methods" of the class.
Apart from this, each class may have certain "attributes" that uniquely identify the class.

Fig.4.3 Class diagram

12
4.4 Activity diagram:

The process flows in the system are captured in the activity diagram. Similar to a state diagram,
an activity diagram also consists of activities, actions, transitions, initial and final states, and
guard conditions.

Fig.4.4 Activity diagram

13
4.5 Sequence diagram:

A sequence diagram represents the interaction between different objects in the system. The
important aspect of a sequence diagram is that it is timeordered. This means that the exact
sequence of the interactions between the objects is represented step by step. Different objects
in the sequence diagram interact with each other by passing "messages".

Fig.4.5 Sequence diagram

14
4.6 Collaboration diagram:

A collaboration diagram groups together the interactions between different objects. The
interactions are listed as numbered interactions that help to trace the sequence of the
interactions. The collaboration diagram helps to identify all the possible interactions that each
object has with other objects.

Fig.4.6 Collaboration diagram

15
4.7 Component diagram:

The component diagram represents the high-level parts that make up the system. This diagram
depicts, at a high level, what components form part of the system and how they are interrelated.
A component diagram depicts the components culled after the system has undergone the
development or construction phase.

Fig.4.7 Component diagram

16
4.8 Deployment diagram:

The deployment diagram captures the configuration of the runtime elements of the application.
This diagram is by far most useful when a system is built and ready to be deployed.

Fig.4.8 Deployment diagram

17
 CHAPTER 5
IMPLEMENTATION AND TESTING

5.1 MODULES:

Preprocessing:
Preprocessing input raw images in the context of face recognition involves acquiring the face
region and standardizing images in a format compatible with the HOG methodology
employed. The photographs of missing children acquired by a digital camera or mobile phone
are taken and categorized into separate cases for creating the database of the face recognition
system. The face region in each image is identified and cropped for getting the input face
images.

Upload Photo:

It consists of a national portal for storing details of the missing child along with the photo.
Whenever a child missing is reported, along with the FIR, the concerned officer uploads
the photo of the missing child into the portal. The public can upload photos of any suspicious
child at any time into the portal with details like place, time, landmarks, and remarks. The
photo uploaded by the users will be automatically compared with photos of the registered
missing children and if a matching photo with a sufficient score is found, then an alert email
will be sent to the concerned officer.
The message will also be visible in the message box of the concerned officer’s login screen.

Search:

Whenever users upload a photo of a suspected child, the system generates a template vector
of the facial features from the uploaded photo. If matching is found in the repository, the
system displays the most matched photo and pushes a message to the concerned Officer portal
or email the alert message of the matching child. Similarly, the Officer can check for any
matching with the database at any time using the proposed system.

18
5.2 ALGORITHMS:

HOG (Histogram Oriented Gradients):

The most popular way for face and object detection, in general, is using HOG
classifiers. HOG stands for Histogram of Oriented Gradients. The crux of the matter is
in finding appropriate feature descriptors for an image, be it faces or other objects. The
Histogram of Oriented Gradients (HOG) is a function descriptor used primarily for object
recognition in image processing. A function descriptor is a representation of an image or an
image patch that by extracting valuable information from it, simplifies the image.

The theory behind the descriptor histogram of directed gradients is that the distribution
of intensity gradients or edge directions will define the appearance and shape of local objects
within an image. The x and y derivatives of an image (Gradients) are helpful because
due to sudden change in amplitude, the magnitude of gradients is high around edges and
corners and we know that edges and corners pack a lot more object shape details than flat
regions. Therefore, the gradient path histograms are used as properties of this descriptor.

Steps to calculate HOG descriptors for face detection:

1. The picture is divided into 8 to 8 cell blocks, and for each 8 to

8 cell block, a histogram of gradients is measured.

19
 2. A vector of 9 buckets (numbers) corresponding to angles from 0 to

180 degrees is basically a histogram (20-degree increments).

3. The values of these 64 cells (8X8) are binned into these 9 buckets

and cumulatively inserted.

4. This restricts 64 values to 9 values, in principle.

Expected Face Detection Results:

K- Nearest Neighbour (KNN):

K-Nearest Neighbour is one of the simplest Machine Learning algorithms based on the
Supervised Learning technique. K-NN algorithm assumes the similarity between the new

20
case/data and available cases and puts the new case into the category that is most similar to
the available categories. K-NN algorithm stores all the available data and classifies a new data
point based on the similarity. This means when new data appears then it can be easily classified
into a well suite category by using K- NN algorithm. So, the K-NN algorithm can be used for
the Classification problems. Here KNN algorithm at the training phase just stores the dataset
and when it gets new data, then it classifies that data into a category that is much similar to
the new data.

The K-NN working can be explained on the basis of the below algorithm:

Step 1 − For implementing any algorithm, we need dataset. So,

during the first step of KNN, we must load the training as well as
test data.
Step 2 − Next, we need to choose the value of K i.e., the nearest
data points. K can be any integer.
Step 3 − For each point in the test data do the following −

● 3.1 − Calculate the distance between the test data point and each
row of training data using a distance metric.
● 3.2 − Now, based on the distance value, sort them in ascending order.
● 3.3 − Next, it will choose the top K rows from the sorted array.
● 3.4 − Now, it will assign a class to the test point based on the most frequent
class of these rows.
Step 4 – End

Example :

The following is an example to understand the concept of K and working of KNN algorithm

Suppose we have a dataset that can be plotted as follows −

21
Now, we need to classify new data point with black dot (at point 60,60) into blue or red class.

We are assuming K = 3 i.e., it would find three nearest data points. It is shown in the next
diagram

We can see in the above diagram the three nearest neighbors of the data point with black dot. Among
those three, two of them lies in red class hence the black dot will also be assigned in red class.

22
Face Recognition with KNN:

In this proposed system, we are using the KNN algorithm for face recognition. However,
the HOG feature will be detected faces from training images and crop that face detected part
and convert into pixel format and store with face Lebel (like the recognized name). So, the
training dataset will be trained with KNN, and when we pass the testing image as input image
then KNN will compare with all datapoints like pixels then which data points are nearly
matched then that the system will return that face Label as output so that we can achieve the
face recognition approach.

Expected Results:

5.3 DATASETS

In this system, we are preparing a customized dataset which is uploaded the missing children’s
images. While uploading the missing children details then automatically the dataset size will
be increased.

23
5.3 TESTING

5.1.1 HOME PAGE

The Home Page serves as a central hub for both logging in and searching for missing
children. Users can upload a suspicious child's photo, which is automatically matched
against the missing child database using deep learning-based face recognition. The system
identifies the best match and provides relevant details. Additionally, users can search and
filter missing children by attributes like Name, Age, Gender, and Location. Social media
sharing options help spread awareness, making the platform efficient in identifying and
recovering missing children.

Fig 5.1 Home Page

24
25
5.1.2 AUTHORITY PAGE

The Login Page plays a crucial role in user authentication and secure access to
the missing child identification system. It allows registered users, including law
enforcement, NGOs, and administrators, to log in using their email and
password. Once authenticated, users can access advanced features such as
managing missing child records, uploading images, and verifying reported
cases. Additionally, if a suspicious child is found, users can search the
database without logging in, ensuring public participation. The login page
enhances security by restricting unauthorized access, ensuring that only verified
individuals can manage sensitive data related to missing children.

Fig 5.2 Authority Page

26
27
 5.1.3 AUTHORITY HOME PAGE

The Authority Home Page helps officials find missing children using facial
recognition or by searching with an ID or Name. It quickly retrieves details like
photo, age, gender, and last known location, making the search process more
efficient and effective.

Fig 5.3 authority home page

28
29
5.1.4 ADD CHILD PAGE

The Add Child page is designed to help users report a suspiciously found child by
providing key details such as photo, gender, height, weight, location found, date
missing, and date found. This information is stored in the system and analyzed using
facial recognition technology to compare with the missing child database. If a match
is detected, the system alerts the authorities or guardians for further action.
Additionally, users can add remarks or specific observations, improving the chances
of correct identification. This feature enhances public participation in the search for
missing children, making the process faster and more efficient.

Fig 5.4 add child page

30
31
32
5.1.5 ALERTS PAGE

The Alerts Page is designed for authorities to monitor and manage sightings of missing
children. It displays alerts based on public reports and allows officials to search and filter
cases using parameters like ID, contact details, location, or whether the child was alone.
Each report includes a photo and unique ID, and clicking on a case provides further
details. This system enables quick verification and action, improving the chances of
identifying and rescuing missing children efficiently.

Fig 5.5 alerts page

33
34
5.1.6 REPORT SIGHTING PAGE

The Report Sighting page allows the public to report a suspected missing child by
submitting key details such as child’s image, contact information, location, and whether
the child was alone or with someone. This information helps authorities verify and cross-
check the report with the missing child database using facial recognition technology. The
system stores the report and enables officials to take immediate action. This page plays a
crucial role in public participation and improving the chances of identifying and rescuing
missing children efficiently.

Fig 5.6 Report

35
36
5.1.7 CHILD FOUND PAGE

The Found Child page displays the name and photo of a child who has been
successfully identified using the face recognition system. If a match is found in
the database, the page confirms that the authorities have been notified for further
action. This page helps in quick identification and verification by showcasing
the found child’s details clearly. If no match is found, an appropriate message is
displayed. With a simple and responsive design, this page ensures that important
information is easily accessible, aiding in the efficient recovery of missing
children.

Fig 5.7 Child Found page

37
38
5.1.8 CHILD NOT FOUND PAGE

The Child Not Found page informs users that no matching record has been found
in the database for the searched child. It displays a clear message indicating that
the child is not yet identified and provides a visually appealing layout for better
user experience. The page ensures smooth navigation by offering a "Go Back"
button, allowing users to return and try again. This feature helps in efficiently
managing searches while keeping the process user-friendly and informative.

Fig 5.8 Child Not Found page

39
 6.CONCLUSION

6.1 Conclusion

A missing child identification system is proposed, which combines the powerful HOG-based
approach for feature extraction and KNN machine classifier for the classification of different
child categories. Face recognition has been a rapidly growing and intriguing region
progressively applications. A huge number of face recognition calculations have been produced
a long time ago. In this paper, for face detection, we are using a HOG (Histogram of oriented
Gradient) based face detector which gives more accurate results rather than other machine
learning algorithms like Haar Cascade and CNN. In the Face recognition process, we are using
HOG which is a standard technique for face feature extraction. The HOG features are extracted
for the test image and also for the training images and finally for classification we are using
KNN algorithms which effectively recognize the face Labels from the input image.

40
6.2 Future scope

The future scope of the missing child identification project using face recognition technology
is vast and holds significant potential for advancements. One of the key areas of improvement
is enhancing the accuracy of the AI model by incorporating advanced deep learning techniques
such as transformers and generative adversarial networks (GANs), which can improve facial
recognition, especially in cases of aging or facial changes. Additionally, integrating edge
computing can enable real-time recognition on mobile devices, reducing the dependency on
cloud processing and enhancing the system’s responsiveness. Security can be further
strengthened by leveraging blockchain technology to ensure data integrity and prevent
unauthorized modifications to missing child records.
Furthermore, collaboration with law enforcement agencies through direct API integrations can
facilitate quicker actions in locating missing children. Expanding the system for cross-border
collaboration will allow seamless sharing of missing child data across different countries,
increasing the chances of successful identification. Crowdsourced verification, where verified
volunteers can assist in validating matches and providing additional evidence, can enhance the
reliability of the system. Another innovative approach is the use of augmented reality (AR) to
predict and visualize how a missing child’s appearance may have changed over time.
In addition to facial recognition, incorporating multi-modal biometric identification, such as
voice recognition and gait analysis, can further improve the accuracy of matches. Automated
alerts and notifications can also be implemented to instantly inform law enforcement, parents,
and the public when a potential match is found. Finally, scalability remains a crucial aspect, as
the system needs to be optimized to handle large datasets efficiently while ensuring seamless
performance. By implementing these advancements, the project can significantly enhance its
effectiveness in reuniting missing children with their families

41
 REFERENCES
[1] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning", Nature,521(7553):436–
444, 2015.

[2] O. Deniz, G. Bueno, J. Salido, and F. D. la Torre, "Face recognition using histograms of
oriented gradients", Pattern Recognition Letters, 32(12):1598– 1603,2011.

[3] C. Geng and X. Jiang, "Face recognition using sift features", IEEE International Conference
on Image Processing(ICIP), 2009.

[4] Rohit Satle, Vishnuprasad Poojary, John Abraham, Shilpa

Wakode, "Missing child identification using face recognition system", International Journal of
Advanced Engineering and Innovative Technology (IJAEIT), Volume 3 Issue 1 July – August
2016

[5] Simonyan, Karen and Andrew Zisserman, "Very deep convolutional networks for large-scale
image recognition", International Conference on Learning Representations ( ICLR), April
2015.

[6] O. M. Parkhi, A. Vedaldi, and A. Zisserman, "Deep Face

Recognition," in British Machine Vision Conference, vol. 1, no. 3, pp. 1-12, 2015.

[7] A. Vedaldi, and K. Lenc, "MatConvNet: Convolutional Neural Networks for MATLAB",
ACM International Conference on Multimedia, Brisbane, October 2015.

42