Automatic Image Cyberbullying Detection From Social Netwoks: 1 .Problem Statement

AUTOMATIC IMAGE CYBERBULLYING DETECTION FROM
SOCIAL NETWOKS
1 .PROBLEM STATEMENT
In the Internet, cell phones or other devices are used to send or post text,
images, videos and audios that are intended to hurt or embarrass another person. This form of
bullying is severely and negatively affecting many adolescents involved. Victims are
experiencing lower self-esteem, increased suicidal ideation, and a variety of emotional responses,
including cyber bullying back, being scared, frustrated, angry, and depressed. One of the most
damaging effects clear in today’s society is that a victim begins to avoid friends and daily
activities. Cyber-bullying campaigns are sometimes so damaging that victims have committed
suicide.
2 .ABSTRACTION
In the present era, online social networks are the most popular and rapid
information propagation applications on the Internet. People of all ages spend most of their time
on social networking sites. Huge volumes of data are being created and shared through social
networks around the world. These interests have given rise to illegitimate users who engage in
fraudulent activities against social network users. Cyberbullying has grown as an important
societal challenge nowadays. The Cyberbullying affects person in terms of psychological and
emotional means of a person. So there is a need to devise a method to detect and prevent
cyberbullying in social networks. The proposed work is going to detect cyberbully image from
the social networks. The cyberbully image will be detected using the content based image
retrieval techniques and the output will be classified such Threatening,Trolling,Abusing,Insulting
and Irritating of images using support vector machine classifier.
3.TECHNICAL SPECIFICATIONS
Software Requirements: MATLAB
Hardware Requirements:64bit,windows 10,4GB RAM
4.LIST OF MODULES
The modules used to detect the cyberbully image are,
I. Data preprocessing
Social network dataset consist of most noisy and unwanted data, to improve the
accuracy of the input data the preprocessing has been applied. Filtering is a method used in pre-
processing for improving an image. The image is filtered using linear and non-linear filtering
techniques. A non-linear technique is the one which is good for removing the impulse-like noise
with the help of Lucy Richardson algorithm.
II. Image detection
Nowadays the cyberbullying using images is vast and causes large effects to the
society. They seems to be spreading in the social networks very rapidly. Such as even the anti
social elements able to create more case to the world by spreading communalism through
images. In Figure 1 shows the cyberbully image will be detected using the Content Based Image
Retrieval Techniques(CBIR).The visual contents of images, such as color, texture, shape and
region are extensively explored for indexing and representation of the image contents. It used to
find similar image in the image database when a query image is given. A user gives input to the
system in the form of specified query image and system return set of relevant images.
Figure.1 Content Based Image Retrieval Techniques(CBIR) system

Components of CBIR system
The CBIR system consists of the following components:
1) Input image: It is the image to be create from the image dataset.
2) Image dataset: It contains of n digit of images based on the user select.
3) Feature extraction: It splits visual material from the image and protects them as structures
vectors in a features dataset.
4) Image matching: Feature paths of numerous images are linked with the feature vectors of
input image which helps in calculating the similarity.
5) Cyberbully images: Similar images having closet or same features as that of the input image
are retrieved.
III. Classification of cyberbully images

Cyberbullying image can be classified into Threatening, Trolling, Abusing, Insulting and
Irritating. The above categories are explained given below:
I. Threatening: It involves sending offensive and malicious images/command to an

individual or a group.
II. Trolling: Trolling is the use of bad language on social networking sites. The main aim
is to make them angry enough to act in the same way .
III. Abusing: It is a sustained, constant and intentional form of comprising
abusive messages.
IV. Insulting : Offended that person intentionally through rude word/expression .
5.ARCHITECTURE DIAGRAM
Conclusion
Thus the proposed system will detect the cyberbully image from social networks using
CBIR.The cyberbully image will be classified such as Threatening, Trolling, Abusing,
Insulting and Irritating of images using support vector machine classifier.
REFERENCES
1. S.Nithyadhevi ,R. Venkatesan , B. Mahendran , M.Mohamed Nijasudeen . “Novel Text
Extraction from Video Image Using Multispectral Fusion ” International Journal of
Computer Trends and Technology (IJCTT) – Volume 33, Number 1 - March 2016
2. Ms. R.A.Kolhe,Prof. A. S. Deshpande. “A Survey On: Object Recognition for Image
Retrieval Systems” International Journal of Advanced Research in Computer Engineering
& Technology (IJARCET) Volume 5, Issue 4, April 2016, ISSN: 2278 – 1323
3. Suman Khokhar , Satya Verma. “Content Based Image Retrieval with Multi-Feature
Classification by Back-propagation Neural Network” International Journal of Computer
Applications Technology and Research Volume 6–Issue 7, 278-284, 2017, ISSN:-2319–
8656.
4. Sanket Rege , Rajendra Memane,Mihir Phatak, Parag Agarwal. “2d geometric shape and
color recognition using digital image processing” International Journal of Advanced
Research in Electrical, Electronics and Instrumentation Engineering Vol. 2, Issue 6, June
2013 ,ISSN: 2320 – 3765 .
5. Ruchi Kapadia, Hinal Somani. “hybrid approach for effective feature extraction technique
in content based image retrieval: a survey” IJARIIE-ISSN(O)-2395-4396 ,Vol-2 Issue-6,
2016.
6. . Hewa Majeed Zangana . “ A New Algorithm for Shape Detection” IOSR Journal of
Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661,p-ISSN: 2278-8727, Volume 19,
Issue 3, Ver. I (May.-June. 2017), PP 71-76
7. Noorul Amin Khan . “Content-Based Image Retrieval Using Texture Color Shape and
Region” International Journal of Advanced Computer Science and Applications, Vol. 7,
No. 1, 2016.
8. Geetanjali Adlinge, Shashikala Kashid, Tejasvini Shinde, Virendrakumar Dhotre. “Text
Extraction from image using MSER approach” International Research Journal of
Engineering and Technology (IRJET) ISSN: 2395 -0056 ,Volume: 03 ,Issue: 05 ,May-
2016 .

Automatic Image Cyberbullying Detection From Social Netwoks: 1 .Problem Statement

Uploaded by

Copyright:

Available Formats

Automatic Image Cyberbullying Detection From Social Netwoks: 1 .Problem Statement

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Automatic Image Cyberbullying Detection From Social Netwoks: 1 .Problem Statement

Uploaded by

Copyright:

Available Formats

AUTOMATIC IMAGE CYBERBULLYING DETECTION FROM

Hardware Requirements:64bit,windows 10,4GB RAM

II. Image detection

Figure.1 Content Based Image Retrieval Techniques(CBIR) system

The CBIR system consists of the following components:

1) Input image: It is the image to be create from the image dataset.

2) Image dataset: It contains of n digit of images based on the user select.

III. Classification of cyberbully images

I. Threatening: It involves sending offensive and malicious images/command to an

You might also like