Camera-enabled mobile devices(Android) are commonly used as in- teraction platforms for linking the users virtual and physical worlds in numerous research and commercial applications, such as serving an augmented reality interface . On-premise signs (OPSs), a pop- ular form of commercial advertising, are widely used in our living life. The OPSs often exhibit great visual diversity (e.g., appearing in arbitrary size), accompanied with complex environmental conditions (e.g., foreground and back- ground clutter). The language barrier among tourists is one of the major difficulty when traveling. The tourists can rely on mobile phone for traveling purposes. Android provides a translation platform for this base, per- forming 2 times faster than other algorithms. We first proposed an OPS data set, in which images of different businesses are collected from Googles Street View. Further, for addressing the problem of real-world OPS learning and recognition, we developed a probabilistic framework based on the distributional clustering, in which we proposed to exploit the distributional information of each visual feature as a reliable selection criterion for building dis- criminate OPS models. Our approach is simple, linear, and can be executed in a parallel fashion, making it practical and scalable for large-scale multimedia applications.
It gives us great pleasure in presenting the preliminary project report on 'Recognition of Street View Images and languages and converting it into user understandable format'.
I would like to take this opportunity to thank my internal guide Prof. P.S. Gaikwad for giving me all the help and guidance I needed. I am really grateful to them for their kind support. Their valuable suggestions were very helpful.
I am also grateful to Prof. S.N. Zaware, Head of Computer Engineering Department, AISSMS's IOIT, Pune for his indispensable support, suggestions.
In the end our special thanks to Prof. Suresh Limkar for providing various resources such as laboratory with all needed software platforms, continuous Internet connection, for Our Project.To develop an Android-platform based image translation application that is able to recognize the text present on sign board images taken with a mobile phone camera and display the translation result back onto the screen of the mobile phone both online and offline.. User friendly and linear interaction
Alphanumeric and symbol recognisation
World wide language simplification
System Description: To develop an Android-platform based image translation application that is able to recognize the text present on sign board images taken with a mobile phone camera and display the translation result back onto the screen of the mobile phone both online and offline.
Input: Image of any ENGLISH letter clicked from mobile phone camera
Output: HINDI User understandable text
Scanning the captured image , Detecting The Text and Translating it into Hindi
Functions : Detecting Text Image, Grey Scale conversion, Creating Matrix
15*15,Matching The Text and translating it, Functional rela- tions
Mathematical formulation For converting image into Grey scale format: Y =
Success Conditions: An image of an English letter is converted into Hindi user understandable text
The app is able to provide the information of places
Failure Conditions: Non famous places may not be found insufficient database source
IMAGE CHARACTER RECOGNITION USING DEEP CONVOLUTIONAL
NEURAL NETWORK LEARNED FROM DIFFERENT LANGUAGES
Authors: : Jinfeng Bai, Zhineng Chen, Bailan Feng, Bo Xu
Published :978-1-4799-5751-4/14/31.00 2014 IEEE (2014)
Objective: : to use cross knowledge learned from multiple tasks to improve the performance of image character recognition.
Advantages :emphasizes on learning common character traits existed in different languages such as strokes.
Disadvantages : During training, images are continually translated, scaled, stretched and rotated, whereas only the original images are used for validation, hence efficiency increases.
AN EMPIRICAL STUDY ON ENGLISH TO HINDI E-CONTENTS MA-
CHINE TRANSLATION THROUGH MULTI ENGINES
Authors: Sanjay K. Dwivedi, Pankaj K. Goswami
Published :978-1-4799-6896-1/14/31.00 2014 IEEE (2014)
Objective: to present the comparison amongst eight selected machine translation engines based on various comparison criteria.
Advantages : translation engine provides professionally high quality translations. It is based on Translation Memories which will save our time and money in the
Disadvantage: It can translate maximum 200 words only.
ENGLISH-HINDI TRANSLITERATION BY APPLYING FINITE RULES
TO DATA BEFORE TRAINING USING STATISTICAL MACHINE TRANSLATION
Authors: Mitali Halder, Anant Dev Tyagi.
Published :978-1-4799-2845-3/13/31.00 2013 IEEE(2013)
Objective: To develop the concept of high accuracy transliteration system by applying finite rules before training to the data and reducing the effort of machine for
Advantages : The efficiency is increased by 29.1 Accuracyhasbeenincreased.
Disadvantage: the conjunct word rais eambiguou conditions during transliteration.
HYBRID APPROACH TO ENGLISH-HINDI NAME ENTITY TRANSLITERATION
Authors: Shruti Mathur , Varun Prakash Saxena
Published :978-1-4799-2526-1/14/31.00 2014 IEEE(2014)
Objective: To process English words using a rule based approach which extracts individual phonemes from the words and then we have applied statistical approach which converts the English into its equivalent Hindi phoneme and in turn the corresponding Hindi word.
Advantages : Improve accuracy in translating the name entities
The system attained an accuracy of 83.40
Disadvantage: The system did fairly well with all name entities, except for Organization.
EGMENTATION IN MALAYALAM OCR HANDLING BROKEN
CHARACTERS USING ACTIVE CONTOUR MODEL Praseetha M , Deepa S:978-1-4799-4190-2/14/31.00 2014 IEEE (2014)
To develop a system to avoid the problems occurred because of incorrect segmentation due to presence of broken characte Broken characters can be segmented correctly. If the characters are completely deteriorated they cannot
be recognized by this method.
RELATIVE CLAUSE BASED TEXT SIMPLIFICATION FOR IM-
PROVED ENGLISH TO HINDI TRANSLATION
Sandeep Saini, Umang Sehgal, Vineet Sahula
978-1-4799-8792-4/15/31.00 2015 IEEE (2015)
Objective: In this work, we are focusing on relative clause identification and extraction for text simplification. The generated simple sentences are then fed to the existing translation engines for translation.
ISSUES IN PARSING FOR MACHINE AIDED TRANSLATION FROM ENGLISH TO HINDI
Rekha S. Sugandhi, Ritika Shekhar, Tarun Agarwal, Rajneesh K.
Bedi, Vijay M. Wadhai
978-1-4673-0126-8/11/26.00 c 2011 IEEE (2011)
This paper presents a sub-model of a parser identifies the syntactical elements in English sentences and suggests its Hindi translation taking in to account various grammatical forms of Hindi.
The current language translators perform more of word to word translation without considering sense in case of ambiguous sentences It works on limited vocabulary.
TEXT EXTRACTION FROM DIGITAL ENGLISH COMIC IM-
AGE USING TWO BLOBS EXTRACTION METHOD
978-1-4673-1039-0/12/31.00 2012 IEEE (2012)
To propose a system for English text extraction from blob in comic image using various methods
Provides high quality of text from the printed document. It overcomes the problems like various size,gray scale values,complex backgrounds and different styles of font.
Processing time is more.AUTOMATIC TEXT CATEGORIZATION OF MARATHI DOCU-
MENTS USING CLUSTERING TECHNIQUE'
Mrs. Sushma R. Vispute, Prof. M. A. Potey
978-1-4673-2818-0/13/31.00 2013 IEEE (2013)
To create an intelligent system to retrieve desired documents in Marathi language. The system also focuses on providing the personalized documents in Marathi language to the end user based on their interests identified from the browsing history.
For the Marathi documents overall accuracy of the system is
91.102) automatic categorization of text documents.
This system works for limited dataset.
Software is an android apk file ie. Android Application which will help user to understand english words in hindi keywords. Text in blur images may not be detected accurately. So for accurate recognition and translation of text the image should be sharp.
This application is basically for the Indian user and major fact Detecting and converting English keywords in Hindi Format in android device Saving the data of English keywords may take large space, Here we r taking 15*15 matrix and saving it for detecting keywords. By changing matrix value of hexa-decimal we r replacing it with binary numbers so that the process will be fast and easy to light weight.converting in Hindi keywords is can be used for big projects or in embedded OS applications where the large amount if English data will be present for conversion.The Detected English keywords from the captured image will be translated in
Programming Language : JAVA, SQLite
Android Device cost =Rs. 7000/- Total cost =Rs. 7000/-
Android Device cost =Rs. 7000/- Total cost =Rs. 7000/-
COCOMO MODEL: (cost estimate)
Basic COCOMO equations:
Effort applied (E) =a b(KLOC)bb[person'months]
Developmenttime(D) = cb(ef fortapplied)db[months]
Peoplerequired(P) = ef fortapplied/developmenttime[count]
KLOC = estimatedno.ofdeliveredlinesofcode
Itsrun'timehighlyconstantandperformanceisbasedoncameraquality. Memoryisbasedondatabaseprovision'Volatilityisandroidvirtualenvironmentplat formbased.
softwaretoolsusedare : eclipselunaandmars,SQLiteandAndroidemulator
Shows promising and better translation score than the conventional approaches.
Can work better on large data sets.
Target complex sentence needs to be ordered properly to convey the message of clause properly.
Purpose and Scope of Document
The actual purpose of SRS is to be clear the requirements of the project and nothing should remain so that the without any interrupt work can be completed. In this SRS it all covers the basic requirements about the of our project like java sdk, jdk, jre , and hardware parts.Overview of responsibilities of Developer
Developer(We) should carried out noting all the things of requirements, developing tools and coding work. Developer should take responsibility of checking that either all the work is completing in time or not, If not then schedule the work accordingly. Developer should keep track on all the work that is to be done and he should do the
testing according to it..
And important thing is to keep the final product idea in mind.When I went to Karnataka, I was not able to read the navigation boards because of no language knowledge. So Idea came to my mind to create one application which will translate the text on any board after providing image of that board.The profiles of all user categories are described here.(Actors and their Description)All use-cases for the software are presented. Description of all main Use cases using use case template is to be provided.Data Description
The image will be captured by Android Camera and it will get stored in cell storage then the actual processing will get start of detecting and translating data.Data objects and Relationships
The captured image should be clear and should not blur, and the Text should be English Keyword.A description of each major software function, along with data flow (structured analysis) or class hierarchy (Analysis Class diagram with class description for object oriented system) is presented.A description of each software function is presented. A processing narrative for function n is presented.(Steps)/ Activity Diagrams.Non Functional Requirements:
Software quality attributes such as availability [ related to Reliability], modifiability [includes portability, reusability, scalability] , performance, security, testability and usability[includes self adaptability and user adaptability]State Diagram:
State Transition Diagram
Fig.?? example shows the state transition diagram of Cloud SDK. The states are represented in ovals and state of system gets changed when certain events occur. The transitions from one state to the other are represented by arrows. The Figure shows important states and events that occur while creating new project.Design Constraints
Any design constraints that will impact the subsystem are noted.Software Interface Description
The software interface(s)to the outside world is(are) described. The requirements for interfaces to other devices/systems/networks/human are stated.
fboxtransition.PNGA description of the program architecture is presented. Subsystem design or Block diagram,Package Diagram,Deployment diagram with description is to be presented.A description of all data structures including internal, global, and temporary data structures, database design (tables), file formats.Data structures that are passed among components the software are described.Global data structure
Data structured that are available to major portions of the architecture are described.Temporary data structure
Files created for interim use are described.Database description
Database(s) / Files created/used as part of the application is(are) described.COMPONENT DESIGN
Class diagrams, Interaction Diagrams, Algorithms. Description of each component description required.To develop the problem under consideration and justify feasibilty using concepts of knowledge canvas and IDEA Matrix.
Refer [?] for IDEA Matrix and Knowledge canvas model. Case studies are given in this book. IDEA Matrix is represented in the following form. Knowledge canvas represents about identification of opportunity for product. Feasibility is represented w.r.t. business perspective.Project problem statement feasibility assessment using NP-Hard, NP-Complete or satisfy ability issues using modern algebra and/or relevant mathematical models.
input x,output y, y=f(x)' SET THEORY OF PROJECT:
CR0 = Capture Image which contains some text.
CR1 = Apply Grayscale to image.
CR2 = Match the pattern of characters in image with the pattern of characters present in database
CR3 = Store recognized characters in string.
T0 =With the help of one to one mapping get the Unicode of characters
T1 = Use Unicode to get equivalent translated text.
T2 = Display the translated text.
Representation of Sets and its operation:-
Set CR = CR0,CR1,CR2,CR3
Set T = T0,T1,T2
Set(CR U T) = CR0,CR1,CR2,CR3,T0,T1,T2
NP HARD COMPLEXITY REASON
In our proposed system the complete flow of the project goes on linearly affecting the output. So all the modules can be easily modify in very less amount of time for the increasing amount of complexity of the project.And in many scenarios of increasing complexity in the proposed system will take exponentially less time to solve these things in the respective modules so that the project produces the desired output. So all these characteristic of proposed model shows the signs of NP hard complexity theory.
...(download the rest of the essay above)