Fusion: Practice and Applications

Journal DOI

https://doi.org/10.54216/FPA

Submit Your Paper

2692-4048ISSN (Online) 2770-0070ISSN (Print)

An efficient extraction of information from Indian Government issued documents Aadhar and Pan Card

Rachna Tewani , Arun K. Dubey , Achin Jain , Eshika Agarwal , Disha Mittal

In today's world, everything is getting digitized, and widespread use of data scanning tools and photography. When we have a lot of image data, it becomes important to accumulate data in a form that is useful for the company/organization. Doing it manually is a tedious task and takes an ample amount of time. Hence to simplify the job, we have developed a FLASK API that takes an image folder as an object and returns an excel sheet of relevant data from the image data. We have used optical character recognition and software like pytesseract to extract data from images. Further in the process, we have used natural language processing, and finally, we have found relevant data using the globe and regex module. This model is helpful in data collection from Registration certificates which helps us store data like chassis number, owner name, car number, etc.,  easily and can be applied to Aadhaar cards and pan cards.

Read More

Doi: https://doi.org/10.54216/FPA.040201

Vol. 4 Issue. 2 PP. 56-61, (2021)

Image Caption Generation and Comprehensive Comparison of Image Encoders

Shitiz Gupta , Shubham Agnihotri , Deepasha Birla , Achin Jain , Thavavel Vaiyapuri , Puneet Singh Lamba

Image caption generation is a stimulating multimodal task. Substantial advancements have been made in thefield of deep learning notably in computer vision and natural language processing. Yet, human-generated captions are still considered better, which makes it a challenging application for interactive machine learning. In this paper, we aim to compare different transfer learning techniques and develop a novel architecture to improve image captioning accuracy. We compute image feature vectors using different state-of-the-art transferlearning models which are fed into an Encoder-Decoder network based on Stacked LSTMs with soft attention,along with embedded text to generate high accuracy captions. We have compared these models on severalbenchmark datasets based on different evaluation metrics like BLEU and METEOR.

Read More

Doi: https://doi.org/10.54216/FPA.040202

Vol. 4 Issue. 2 PP. 42-55, (2021)

An augmented reality application for jewelry shopping

Sarthak Gupta , Monil Pahwa , Prayant Gupta , Surinder Kaur , Angeles Quezada

Developing an augmented reality-based application to place virtual replicas of objects instead of real jewelry in jewelry shops. A virtual object is superimposed on some target that appears to be a real one. The user must wear a marker (different for the corresponding item), and that particular item will be superimposed onto that. By utilizing ICP calculation, the recreation of 3D items is conceivable. The item will be overseen itself, as indicated by the client, continuously by utilizing HAAR. Payment integrations, user authentication, and order functionality have been integrated to make this app as competitive as other e-commerce applications.

Read More

Doi: https://doi.org/10.54216/FPA.040203

Vol. 4 Issue. 2 PP. 62-71, (2021)

Novel Filter of DWT for Image Processing Applications

J. Abed Eleiwy , Nagham Jaafar

In this work, wavelets are used in the analysis of medical images, where the efficiency of mathematics in this field has been proven because the basis of the proposed wavelets in this work is newly constructed mathematical equations, and through the MATLAB program, many programs have been designed to be ready for use in the field of image analysis and study. Physical samples were selected that were compressed using the proposed wavelets, and good results were obtained that prove the efficiency of the method used.

Read More

Doi: https://doi.org/10.54216/FPA.040205

Vol. 4 Issue. 2 PP. 32-41, (2021)

An innovative multi-criteria decision-making framework for assessing India's airport operating efficiency

Surinder Kaur , Javalkar D. Kumar , Gopal Chaudhary

Global air transport operations have risen dramatically, which has led to new airport developments, requiring an in-depth effectiveness study of these investment projects, as is the case here. 6 Indian civil airports' operating efficiency between 2015 and 2018 are examined in this research. These sources were evaluated and assessed using an integrated Shannon's entropy MCDM technique. Using Shannon's entropy approach and the fuzzy WSM method, the weights of decision criteria are determined, and airports are prioritized. As a result, it is capable of dealing with the trepidation and uncertainty that accompany the subjective appraisal of input and outcome components. The findings also show that airports in touristic locations are more efficient than those in less popular places. The more convenient the airport is to the city Centre, the more passengers arrive, and the more money the airport makes. As a result, efficiency ratings are influenced by both of these elements. Airport operators and policymakers will benefit from the study's innovative efficiency analysis approach.

Read More

Doi: https://doi.org/10.54216/FPA.040204

Vol. 4 Issue. 2 PP. 72-85, (2021)