Vanita Mane

University of Mumbai, Computer Engineering, Faculty Member

Followers

Following

Public Views

Interests

Uploads

Papers by Vanita Mane

Predicting Mental Health Illness using Machine Learning

2023 3rd Asian Conference on Innovation in Technology (ASIANCON)

SMAP - A Stock Market Analysis and Prediction Web Application

Marathi Character Recognition Using Ant Miner Algorithm

Optical Character Recognition (OCR) is an interesting and challenging field of research in patter... more Optical Character Recognition (OCR) is an interesting and challenging field of research in pattern recognition, artificial intelligence and machine vision and is used in many real life applications. The work done for the recognition of Devanagari handwritten script is negligible in literature despite it is being used by millions people in India and abroad and it has numerous applications. Research on Optical Character Recognition OCR of Devnagari script is very challenging due to the complex structural properties of the script that are not observed in most other scripts. Devnagari is the script for Marathi. The Marathi language contains 49 distinct characters, 12 vowels and 37 consonants. Recognition of Devnagari characters poses great challenge due to the large variety of symbols and their proximity in appearance. Feature extraction and classification are the two very important steps in Optical character recognition. In this paper we have used three sets of feature extraction techn...

Download

Identifying Image Modifications using DCT and JPEG Quantization Technique

2023 IEEE 8th International Conference for Convergence in Technology (I2CT)

Copy-Move and Image Splicing Forgery Detection based on Convolution Neural Network

2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT)

Digital Forensic Framework for Protecting Data Privacy during Investigation

ICST Transactions on Scalable Information Systems

Rapid technological breakthroughs, a surge in the use of digital devices, and the enormous amount... more Rapid technological breakthroughs, a surge in the use of digital devices, and the enormous amount of data that these devices can store continuously put the state of digital forensic investigation to the test. The prevention of privacy breaches during a digital forensic investigation is a significant challenge even though data privacy protection is not a performance metric. This research offered solutions to the problems listed above that centre on the efficiency of the investigative process and the protection of data privacy. However, it’s still an open problem to find a way to shield data privacy without compromising the investigator's talents or the investigation's overall efficiency. This system proposes an efficient digital forensic investigation process which enhances validation, resulting in more transparency in the inquiry process. Additionally, this suggested approach uses machine learning techniques to find the most pertinent sources of evidence while protecting the...

Download

Spam Mail Detection Using Fuzzy Similarity [1]

Spam is an unsolicited bulk mail or junk email. Spam emails not only waste resources such as band... more Spam is an unsolicited bulk mail or junk email. Spam emails not only waste resources such as bandwidth, storage and computation power, but also the time and energy of email receivers who must search for legitimate emails among the spam and take action to dispose the spam. So for overcoming these problems Spam filtering techniques are developed which classify messages among two categories, spam and non-spam. Different decision tree algorithms are studied for spam classification then they are compared analyzed and evaluated on the basis of various measures as Feature preprocessing, Feature Extraction, Measure of best split, Types of Attributes, and Detection rate. Finally fuzzy similarity measure algorithm is proposed which gives higher accuracy and low false positive and low false negative rate.

A Parallel Environment Designing for OWL Thinking

ITM Web of Conferences, 2020

A huge volume of information available today is in the form of images and searching the wanted im... more A huge volume of information available today is in the form of images and searching the wanted images is very difficult and highly time-consuming. The search may take longer periods as the search volume on the internet is very huge and also the relevance of extracted images is still not up to the mark. The technologies like ontology and languages like OWL help us to tag the images that describe the semantic of the images. Hence, it helps in faster searching of the wanted images. Also, another challenge with OWL and Semantic web is the speed in which one can derive the relationships between various objects extracted from the images. The challenge is to extract the semantic from the images more efficiently using a parallel approach. In this paper, we explore the different techniques for generating semantic knowledge using parallel approaches like the T-box approach, merge classification, extract concept for matching ontology. We propose an enhanced method to speed-up the computation b...

Download

Usability and Security of Recognition based Graphical Password Scheme

Authentication is the first line of defense against compromising confidentiality and integrity. P... more Authentication is the first line of defense against compromising confidentiality and integrity. People can remember pictures better and for longer periods than alphanumeric passwords. All graphical passwords have two different aspects which are usability and security. Woefully none of these schemes were being able to fulfill both of these aspects at the same time. We analyze the known attack method and categorize them into two kinds Attack by Password Space and Attack by Password Capture. In this paper we summarized the usability and security reported in some user's studies of recognition based graphical password schemes. Finally some suggestion were given

Download

Marathi Character Recognition Using Ant

Image Forgery Detection and Localization using Modified JPEG Ghost

International Journal of Innovative Technology and Exploring Engineering, 2019

Authenticity of an image taken digitally suffers severe threats as a result of increase in variou... more Authenticity of an image taken digitally suffers severe threats as a result of increase in various powerful digital image editing tools. These tools modifies the image contents without leaving footprint of such modifications. We come up with a technique that analyzes digital image forgery detection in JPEG images which goes through multiple compression. Nearly all digital devices uses JPEG as a standard storage format to maintain the storage space. JPEG is a lossy compression standard. By using any image processing tools, when assailant changes any part of a JPEG image and save it, the alter part of the image has different compression artifacts. JPEG ghost algorithm is used to detect disparity in JPEG blocks that rise from improper alignments of JPEG blocks respect to original structure and detect local footprint of JPEG compression. In our work, our proposed technique will modify JPEG ghost detection to detect and localize digital image forgery.

Download

Semantic search over MOOC aggregator using query expansion

2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), 2017

Due to the widespread of internet, online education is gaining popularity. In the field of educat... more Due to the widespread of internet, online education is gaining popularity. In the field of education, Massive Open Online Courses (MOOC) are used in delivering learning content to any person who wants to take the course with no constraint on attendance. The courses by different providers may differ in session timing, price, difficulty level etc. Hence a user has to visit every MOOC provider's site and go through the course details. To make this task user-friendly, a Information aggregator is used which can aggregate online courses from multiple course providers. Before aggregating these courses from different MOOC's, data preprocessing is performed. And to combat the limitations of stemming, we are using lemmatization. In Information Retrieval, one of the important tasks is retrieving relevant information. However an important issue for retrieval effectiveness is the vocabulary mismatch problem. User query is often too short and may not contain relevant terms. These issues are handled by query expansion. User query terms are enriched with additional semantically related terms like synonyms using a dictionary or Wordnet.

Improved Matching Technique in Digital Image Region Duplication

2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2018

Region duplication is the common type of image tampering which copies a part of an image and move... more Region duplication is the common type of image tampering which copies a part of an image and moved in that same image. Many techniques have been proposed to detect such tampering but it is difficult to find the true matched region in an image. Over many existing methods SIFT considered to be efficient one in matching duplicated region under different kinds of transformations, but fails when the image has reflection in it. A method with capability of detecting duplication under reflection is used in this work to make a detection system even more accurate and efficient.

Detection of Contrast Enhancement Forgery in Previously and Post Compressed JPEG Images

2019 IEEE 5th International Conference for Convergence in Technology (I2CT), 2019

Nowadays the digital images become a very powerful source of communication. Digital images are co... more Nowadays the digital images become a very powerful source of communication. Digital images are consider to be proof in many investigation. So it is very important to provide security to these images, But with the advancement in the technology many photo editing tools like adobe photoshop etc. are used to enhance the features of original image which makes forged image. Thus it is important to detect this type of image forgery. Retouching is one of the forgery type in which contrast of images are enhanced or reduced. Our proposed system is about Contrast Enhancement Detection. The Contrast Enhancement Detection is done by Numerical Measures of image Estimation using Zigzag Zonal DCT Band. This algorithm are applicable for Previously and Post Compressed JPEG Images. According to these features SVM classifier gives detection result. Our proposed technique gives better accuracy and also detects contrast enhancement in all types of images.

Multibiometric Database Retrieval Method Based on Index Code

Multibiometrics use of multiple biometric sources for human recognition, mitigates some of the li... more Multibiometrics use of multiple biometric sources for human recognition, mitigates some of the limitations of unimodal biometric systems by increasing recognition accuracy, imparting fault-tolerance, and enhancing security. These databases are used extensively, thereby requirement of efficient technique for searching and retrieving relevant identities from large biometric database. Searching out a biometric information for associate degree identity is usually done by comparing the probe(input) image against every stored identity in the database and generating a ranked list of candidate identities. thorough matching against an large range of identities will increase the latency of the system and should additionally reduce the accuracy of identification. index code is obtained by computing match scores between a biometric input images and fixed set of reference images. Candidate identities are retrieved supported the similarity between the index code of the probe image and people of t...

An Introduction To Augmented Reality With Mobile System

Augmented reality (AR) is a live, direct or indirect, view of a physical, real-world environment ... more Augmented reality (AR) is a live, direct or indirect, view of a physical, real-world environment whose elements are augmented by computer-generated sensory input such as sound, video, graphics or GPS data. It is related to a more general concept called mediated reality, in which a view of reality is modified (possibly even diminished rather than augmented), by a computer. As a result, the technology functions by enhancing one's current perception of reality. By contrast, virtual reality replaces the real world with a simulated one. Augmentation is conventionally in real-time and in semantic context with environmental elements, such as sports scores on TV during a match. With the help of advanced AR technology (e.g. adding computer vision and object recognition) the information about the surrounding real world of the user becomes interactive and digitally manipulable. Artificial information about the environment and its objects can be overlaid on the real world.

Improved Feature Matching Approach for Detecting Copy-Move Forgery and Localization of Digital Images

Advances in Intelligent Systems and Computing, 2020

Nowadays, with the availability of many open-source tools which help to modify digital images, wi... more Nowadays, with the availability of many open-source tools which help to modify digital images, with view to make false publicity. Copy-move forgery (CMF) is most frequent form of forgery technique. The methods available for detecting CMF are mainly classified as keypoint-based methods (KBM) and block-based methods (BBM). KBM found better than BBM in terms of computational complexity and sturdiness against affine transformation, but still, forgery in the flat region cannot be detected by these methods, which is detected by block-based methods. As a result, many researchers proposed a fusion of both. But these methods suffer from a high false-positive rate (FPR). This paper aims to propose a new integrated approach by combining best features of Mirror Invariant Feature Transform (MIFT) and Zernike moment (ZM). Additionally, to reduce FPR a new improved window feature matching technique is proposed which in turn improves detection accuracy.

4G Wireless Networks Challenges and Benefits

Evolution of wireless access technologies is about to reach its fourth generation (4G). 4G system... more Evolution of wireless access technologies is about to reach its fourth generation (4G). 4G systems will be fully IP-based wireless Internet which will provide access to wide range of mobile services. The important and challenging issue in 4G are seamless handoff, Mobility management, Security and Service between different integrated networks. In this paper, several key challenges faced in the global implementation of 4G System and benefits have been

Download

LBG Vector Quantization for Recognition of Handwritten Marathi Barakhadi

Handwritten character recognition has been studied a lot in the past and involves various problem... more Handwritten character recognition has been studied a lot in the past and involves various problems due to many reasons. In this paper, novel method of Handwritten Marathi Barakhadi Character Recognition with Shape and Texture features has been proposed. The Shape features and Texture feature are more unique, so a novel technique based on combination of these is derived and proposed here. For extracting shape features standard gradient operator such as Robert, Prewitt, Sobel, Canny and Laplace are used and vector quantization technique. The gradient mask images of the character images are obtained and then LBG vector quantization algorithm is applied on these gradient images to get the codebooks of various sizes. These obtained codebooks are considered as shape texture feature vectors for handwritten character recognition. In all 45 variations of the character recognition method are proposed using five gradient operators and 9 code book sizes (from 4 to 1024).The database consists of...

Download

Protection of Web Application Against SQL Injection Attack

Web applications are used by many users.web applications are consist of web forms, web server and... more Web applications are used by many users.web applications are consist of web forms, web server and backend. These applications are vulnerable due to attacks and scripts as the number of web application users are increasing. Web application can have sensitive and confidential data which is stored in database.web applications accepts the data from the users. This data is retrieved from the database through the queries.SQL Injection attack is one of the most popular attack used in system hacking or cracking. Using SQL INJECTION ATTACK attacker can gain information or have unauthorized access to the system. When attacker gains control over web application maximum damage is caused. This paper illustrates SQLIA methods and prevention and detection tools.

Download

Vanita Mane

Uploads

Papers by Vanita Mane

Log In