Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
BACHELOR OF TECHNOLOGY
in
COMPUTER SCIENCE AND ENGINEERING
MAY 2019
BONAFIDE CERTIFICATE
This is to certify that the project report entitled, “Image Text Search” is a bonafide record of
Mini Project work done during the academic year 2018-2019 by
DEREK CHRISTY JOSEPH (URK17CS281)
in partial fulfillment of the requirements for the award of the degree of Bachelor of Technology
in Computer Science and Engineering of Karunya Institute of Technology and Sciences.
Coordinator
Head of the Department
ACKNOWLEDGEMENT
First and foremost, I praise and thank the ALMIGTHY GOD whose blessings have
Dr. Paul Dhinakaran, M.B.A, Ph.D, for their love and always remembering us in their
prayers.
I extend my thanks to our Vice Chancellor Dr. P. Mannar Jawahar, Ph.D and our
Registrar Dr. Elijah Blessing, M.E., Ph.D, for giving me this opportunity to do the project.
I would like to thank Dr. Prince Arulraj, M.E., Ph.D., Dean, School of Engineering
and Technology for his direction and invaluable support to complete the same.
I would like to place my heart-felt thanks and gratitude to Dr. J. Immanuel John Raja,
M.E., Ph.D., Head of the Department, Computer Science and Engineering for his
Professor, Department of Computer Science and Engineering for being my guide and to
I also thank all the staff members of the Department for extending their helping hands to
I would also like to thank all my friends and my parents who have prayed and helped me
(i)
ABSTRACT
The phones and tablets storages can quickly get full due to apps, photos, videos and documents.
Many lower-end devices contain a few gigabytes of storage, making this even more of a
problem. Also, searching for photos which contains images like a hard copy of a document, a
quote, notes, etc., can be a daunting task. The purpose of this app is to search and easily delete
images that contain some text content. The app uses an Optical Character Recognition(OCR)
framework created by Google, which is officially known as the Mobile Vision API. The
Mobile Vision API can detect and extract text from images. This API can detect text in any
Latin language (French, German, English, etc.). The app takes a word or a phrase as an input
from the user, the images are scanned for the word, if the word matches it returns the image
file. The results appears in a thumbnail list. The user can then select multiple images and delete
them, or can open an image to view or share it. This app makes deleting images in bulk easy
which results in managing the phone storage problem in an efficient and easy way. Also, now
one can search for a document, quote or screen shots easily in a cluster of images.
(ii)
CONTENTS
Acknowledgment i
Abstract ii
1. Introduction 1
1.1 Introduction
1.2 Objectives
1.3 Motivation
1.4 Overview of the Project
3. Implementation . 3
3.1. Modules Description
3.2. Implementation Details
3.3. Tools used
4. Test results 4
6. References
1. Introduction
1.1 Introduction
We are living in a digital era where we produce about 2.5 quintillion bytes of data daily.
Our smartphone storages are overflowing with apps, pictures, videos, etc. Instant
messaging apps like WhatsApp has around 4.5 billion photos and 1 billion videos shared
in it per day. But most of the photos, gifs and videos shared in these apps are not worth
occupying the phones storage space. Also, if we want to search for some important
screen shot of a document or some quote, it can really be a tedious job.
1.2 Objectives
To create an android application which can search, share and delete images with text
on it.
1.3 Motivation
Searching for images such as a screen shot of a document or a form, or memes in the
phone gallery can be a daunting task. Also, tons of images with text like ‘good morning’
for example, are not worth occupying the phone storage space after once we’ve seen it.
As we all know the phone gets slow and laggy when on low internal storage space. To
get rid of this problem we often need to move or delete some files. Generally the
unnecessary images and videos that gets accumulate in our phone’s gallery through apps
like whatsapp and consume a lot of storage space.
This android application is basically a search engine, which uses Optical Character
Recognition often abbreviated as OCR, to read text from images. When the user enters a
search, all the images stored locally on the phone are scanned. Once the text is detected,
the recognizer then determines the actual text in each block, and segments it into lines
and words. If the search matches it is displayed on the screen. The recognizer can detect
text in Latin based languages (French, German, English, etc.). The resultant images then
can be viewed, shared or can be permanently deleted.
(1)
Robust
2.3 Architecture
(2)
(3)
3. Implementation
3.1 Modules Description
SearchTask
It contains methods :-
Methods
Public void selectAllImages() - selects all the images in the result list
view.
(4)
Android Studio
4. Results
(5)
(6)
This app currently looks up images from WhatsApp only, but it can be
extended to search the whole device.
This app uses a brute force approach for searching images which takes O(n)
time, this makes the searching slow, instead we can use some better
algorithm or methodology to search in lesser time.
6. References
https://developer.android.com/reference/android
https://developers.google.com/vision/android/text-overview
(7)