Project Synopsis: Babu Banarasi Das

PROJECT SYNOPSIS
on
Landmark Recognition System Using AI
Towards Partial Fulfilment of The Requirement

For the award of degree of
Bachelor of Computer Applications

from
Babu Banarasi Das University

Lucknow
Academic Session 2019 - 2020

School of Computer Applications
Submitted by: Under Guide:
Atul panday Mr.Zaid kamil

Table of Contents
Sr No. Contents Page No.
1. Title of the project 1
2. Objective and Scope of the project 1
3. Resources Used 2
4. Project Schedule Plan 3
5. Project Teams 4
6. Process Description 4
7. Contribution of the Student in project 5
8. Conclusion 5
Landmark Recognition System Using AI

Introduction:
As smartphones and mobile data become more prevalent in modern society, the possibilities for
them to interact with the physical world also grow exponentially. Technologies such as Oculus Rift
and Google Glass are attempting to bridge the gap between the virtual and the physical, and as
enhancements in computer speed and image processing are made, the concept of Augmented
Reality (AR) becomes more tangible.
However, one difficulty with AR is the sheer complexity of image processing and feature
recognition. A successful AR system must be able to distinguish among a large number of
landmarks and should be able to adapt to the existence of new landmarks. Because of the
adaptability requirement, AR algorithms naturally lend themselves to using machine learning. As
such, the focus of this project is to develop, refine and document a machine learning algorithm
that can distinguish landmarks from images using a database of Known Landmark.
Objective and Scope of the project

Image classification technology has shown remarkable improvement over the past few
years, exemplified in part by the Imagenet classification challenge, where error rates
continue to drop substantially every year. In order to continue advancing the state of the
art in computer vision, many researchers are now putting more focus on fine-grained and
instance-level recognition problems – instead of recognizing general entities such as
buildings, mountains and (of course) cats, many are designing machine learning
algorithms capable of identifying the Eiffel Tower, Mount Fuji or Persian cats. However, a
significant obstacle for research in this area has been the lack of large annotated
datasets.In this project we have implemented landmark recognition using RCNN.
.
2. Resources (Hardware & Software)
1. Hardware Requirements
Client Side
Processor Dual Core or above
RAM 1 GB
Disk space 500 GB
Monitor 15”
Others Keyboard, mouse, Internet Connection
Server Side
Processor Dual Core or above
RAM 4 GB
Disk space 5 GB
Monitor 15”
Others Keyboard, mouse, Internet Connection
2. Software Requirements
Client Side
● Web Browser Google Chrome, Firefox, IE9 or above
Server Side
Web Browser Google Chrome, Firefox, IE9 or above

Operating System Window7 or above / Linux
IDE Jupiter notebook
Database SQLite manager
Runtime environment Anaconda
Front End Framework Flask
3. Project Schedule Plan
The objective of Software Planning is to provide a framework that enables the
manager To make reasonable estimates of resources, cost, and schedule. These estimates
are made Within a limited time frame at the beginning of a software project and
should be Updated regularly as the project progresses. In addition, estimates should
attempt to define Best case and worst-case scenario so that project outcomes can be bounded.
A Gantt chart is a popular type of chart that illustrates a project schedule. Gantt
Chart illustrates the start and finish dates of the terminal elements and summary
Elements of a project. Terminal element and summary comprise the work breakdown
Structure of the project.
Task 4Jan-30Jan 31Jan-9Feb 10Feb-12Mar 13Mar-16Apr 17Apr-22Apr 23Apr-28Apr
Develop project
proposal
27 days
Analysis
10 days
Designing
30 days
Coding
34days
Unit Testing
5 days
Implementation
5 days
Gantt chart
5.PROJECT TEAM
Instructor : Mr. Zaid kamil
Mentor : Mr. Sarfaraz Alam
Project Team Members : Atul Pandey , Manish Kumar
6.Process Description
1. Data Conversion API:
2. Image Reprocessing:
3. Data Set Splitting
4. Image of Mentation
5. VGG16 Mode
6. Transfer Learning
7. Convection and max pooling
8. Image model Evolution
9. Landmark Prediction,
10. View Display
1.Data conversion Api:

An API is a set of definitions and protocols for building and integrating ... as well as potentially
monetize your data (the Google Maps API is a popular example). ... without difficult data
conversion transactions or additional integration layers.
2. Image Reprocessing:
Image processing is a method to perform some operations on an image, in order to get

an enhanced image or to extract some useful information from it. It is a type of
signal processing in which input is an image and output may be image or
characteristics/features associated with that image.
3. Data Set Splitting:
Data splitting is the act of partitioning available data into. two portions, usually for cross-
validatory purposes. One. portion of the data is used to develop a predictive model. and
the other to evaluate the model's performance
4. Image of Mentation:
An image (from Latin: imago) is an artifact that depicts visual perception, such as a photograph ... A
scanned image of the definition of image and imagery, from Thomas Blount's ... A volatile image is one
that exists only for a short period of time.
5.VGG16 Mode:
VGG16 is a convolutional neural network model proposed by K. ... Zisserman from the

University of Oxford in the paper “Very Deep Convolutional Networks for Large-Scale
Image Recognition”. The model achieves 92.7% top-5 test accuracy in ImageNet, which is
a dataset of over 14 million images belonging to 1000 classes
6. Transfer Learning:
Transfer learning make use of the knowledge gained while solving one problem and applying it to a
different but related problem. ... When we train the network on a large dataset(for example: ImageNet) ,
we train all the parameters of the neural network and therefore the model is ...
7. Convection and max pooling:
Max pooling is a sample-based discretization process. The objective is to down-sample an input

representation (image, hidden-layer output matrix, etc.), reducing its dimensionality and allowing for
assumptions to be made about features contained in the sub-regions binned.
8. Image model Evolution:

Image Model Evaluation. Model Evaluation is an integral part of image the model development
process. It helps to find the best model that represents our data and how well the chosen model will
work in the future
9. Landmark Prediction:
landmarks as predicted by Active Shape Models to assess facial ... Similar descriptors used by
Vezzetti et al. in 2017 [9] achieved a mean ... Selection of an appropriate dataset for solving
the defined problem:
10. View Display :
Display definition is - to put or spread before the view. How to use display in a sentence. Synonym
Discussion of display.
7. Contribution of the student in the project

● Manish Kumar:
(Data Conversion API, Image Reprocessing, Data Set Splitting, Image of Mentation, VGG16
Model)
● Atul Pandey:
(Transfer Learning, Convection and max pooling, Image model Evolution, Landmark
Prediction, View Display)
8. Conclusion:
Overall, the results are very encouraging, and they demonstrate that
landmarks can be accurately identified from an image using a basic
classification algorithm. An accuracy as high as 90% is attainable using a
relatively small sample size.
Furthermore, the time required to process and analyse an image is
reasonable. These results suggest that this algorithm could be incorporated
into an App to provide real-time feedback as images are taken.
In the future, other feature extraction methods can be looked at that may give
better accuracy but require fewer dimensions. An algorithm will also need to
be developed that can automatically search and obtain data from a database.
The project can ultimately become part of the back-end code for a feature-
recognition smartphone app.

Project Synopsis: Babu Banarasi Das

Uploaded by

Copyright:

Available Formats

Project Synopsis: Babu Banarasi Das

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

Project Synopsis: Babu Banarasi Das

Uploaded by

Copyright:

Available Formats

PROJECT SYNOPSIS

Landmark Recognition System Using AI

Towards Partial Fulfilment of The Requirement

Bachelor of Computer Applications

Babu Banarasi Das University

Academic Session 2019 - 2020

Submitted by: Under Guide:

Atul panday Mr.Zaid kamil

1. Title of the project 1

2. Objective and Scope of the project 1

4. Project Schedule Plan 3

7. Contribution of the Student in project 5

Landmark Recognition System Using AI

Objective and Scope of the project

● Web Browser Google Chrome, Firefox, IE9 or above

Web Browser Google Chrome, Firefox, IE9 or above

Task 4Jan-30Jan 31Jan-9Feb 10Feb-12Mar 13Mar-16Apr 17Apr-22Apr 23Apr-28Apr

Project Team Members : Atul Pandey , Manish Kumar

3. Data Set Splitting

7. Convection and max pooling

8. Image model Evolution

10. View Display

1.Data conversion Api:

Image processing is a method to perform some operations on an image, in order to get

3. Data Set Splitting:

VGG16 is a convolutional neural network model proposed by K. ... Zisserman from the

Max pooling is a sample-based discretization process. The objective is to down-sample an input

8. Image model Evolution:

7. Contribution of the student in the project

You might also like