Online Text Categorization System Using Support Vector Machine

Jumani, Awais Khan; Mahar, M. H.; Khoso, Fida Hussain; Memon, Mohsin Ali

doi:10.26692/surj/2018.01.0014

Cited by 8 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, another has classified the text using support vector machine in this system he has classified those which are required [18]. Similar work on the same approach for the classification of text was used in natural language processing [19][20].…”

Section: Problem Identificationmentioning

confidence: 99%

Face Detection and Recognition System for Enhancing Security Measures Using Artificial Intelligence System

Siddiqui¹,

Siddique²,

Ahmedh³

et al. 2020

IJST

View full text Add to dashboard Cite

Background/objectives: The major changes which come across face recognition are to find the age and gender of the person. This study is centered on face detection with voice and biometric technology. Methodology: During this study, it has been worked on the input camera which takes multiple shots of person. After that, the Cascade Classification algorithm has been used inside the application which creates the multiple human templates. So the facial features have been detected. After that, it saved in particular database with their unique ID. Furthermore, the verification process has been started by matching the templates inside the database. Through this process, the student attendance has been marked automatically. Findings: It has been presented that face detection with voice and biometric technology can enhance the security measures. Employee's attendance can be marked by simply detecting face that can increase punctuality. Students can be checked and marked by face detection process. As well, it can also be setup in banks to enhance the security by allowing authorized people only or who have accounts in that bank. Novelty/improvements: For finding the age and gender from a particular image, relevant techniques are discussed, with some new approaches for maintaining security. We discussed complete models with security measures in this research.

show abstract

Section: Problem Identificationmentioning

confidence: 99%

Face Detection and Recognition System for Enhancing Security Measures Using Artificial Intelligence System

Siddiqui¹,

Siddique²,

Ahmedh³

et al. 2020

IJST

View full text Add to dashboard Cite

show abstract

“…So other things there are lots of tools which have helped us in this particular implementation. There are cases of people do not have the skill set, we help them, train them and maybe there are tools help them its embedding part of easy way to implement [31][32]. We have transformed the business goals, challenges, service level agreement (SLA) everything can transform and share their work across their team and everybody works the business goals.…”

Section: Devops Cultural Changementioning

confidence: 99%

Fast Delivery, Continuously Build, Testing and Deployment with DevOps Pipeline Techniques on Cloud

Khan¹

2020

IJST

View full text Add to dashboard Cite

Objectives: To implement the DevOps pipeline on cloud for an organization. That is designed and implemented according to the project requirements. Methods/findings: The results of the study are to automate everything using DevOps pipeline on cloud native with executed Continuous Integration (CI), Continuous Delivery (CD), and Monitoring required for the case project. The best practices of DevOps are for automated test execution, automated deployment on different environments, and monitoring of the application. It also maintains the application source code repository structure.

show abstract

“…The segmented objects contained 15% to 20% connected characters as shown ( Figure 8). The decision whether the extracted object was single character or chunk of connected characters was based on the morphological analysis (23)(24)(25) .…”

Section: Segmentationmentioning

confidence: 99%

Deciphering complex text-based CAPTCHAs with deep learning

Kehar¹

2020

IJST

View full text Add to dashboard Cite

Background: CAPTCHA is a mechanism to distinguish humans from bots. It has become standard means of protection from the misuse of resources on World Wide Web. Different types of CAPTCHAs are implemented but text-based schemes are the most widely used due to its easiness and robustness. A user is asked to type in the text from an image. The image is intentionally distorted to dodge the bots. Recognizing the text is easy for humans but very hard for computers. Method/Findings: In this work, a text-based CAPTCHA scheme with background clutter and partially connected characters is decoded. The main steps consist on preprocessing, segmentation and recognition. Several digital image processing techniques were applied during preprocessing, segmentation steps and convolutional neural network (CNN) was used for recognition process. Since massive data is required for CNN therefore data was generated synthetically. A complex text-based CAPTCHA scheme with varying number of letters: 3, 4 and 5 letters is decoded with the overall precision of 77.5%, 64.2% and 51.9% respectively.

show abstract

Online Text Categorization System Using Support Vector Machine

Cited by 8 publications

References 0 publications

Face Detection and Recognition System for Enhancing Security Measures Using Artificial Intelligence System

Face Detection and Recognition System for Enhancing Security Measures Using Artificial Intelligence System

Fast Delivery, Continuously Build, Testing and Deployment with DevOps Pipeline Techniques on Cloud

Deciphering complex text-based CAPTCHAs with deep learning

Contact Info

Product

Resources

About