Scribd Logo
Upload

Welcome to Scribd!

  • 531 views

    AI-Based Picture Translation App: 1) Background/ Problem Statement

    Uploaded by

    tejas patil
    This document describes an AI-based picture translation app that uses machine learning and Google Cloud vision and translation APIs. The app allows users to select an image containing text or an object, select a preferred language, and the app will automatically detect and translate the text or recognize and translate the object into the selected language. It provides translation without requiring human translators and is free to use on phones or computers with an internet connection. However, there is a risk of minor translation mistakes due to limitations in AI.

    Copyright:

    © All Rights Reserved
    Download as DOC, PDF, TXT or read online from Scribd

    AI-Based Picture Translation App: 1) Background/ Problem Statement

    Uploaded by

    tejas patil
    531 views7 pages
    This document describes an AI-based picture translation app that uses machine learning and Google Cloud vision and translation APIs. The app allows users to select an image containing text or an object, select a preferred language, and the app will automatically detect and translate the text or recognize and translate the object into the selected language. It provides translation without requiring human translators and is free to use on phones or computers with an internet connection. However, there is a risk of minor translation mistakes due to limitations in AI.

    Original Title

    A189

    Copyright

    © © All Rights Reserved

    Available Formats

    DOC, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document describes an AI-based picture translation app that uses machine learning and Google Cloud vision and translation APIs. The app allows users to select an image containing text or an object, select a preferred language, and the app will automatically detect and translate the text or recognize and translate the object into the selected language. It provides translation without requiring human translators and is free to use on phones or computers with an internet connection. However, there is a risk of minor translation mistakes due to limitations in AI.

    Copyright:

    © All Rights Reserved
    Download as DOC, PDF, TXT or read online from Scribd
    Download as doc, pdf, or txt
    531 views7 pages

    AI-Based Picture Translation App: 1) Background/ Problem Statement

    Uploaded by

    tejas patil
    This document describes an AI-based picture translation app that uses machine learning and Google Cloud vision and translation APIs. The app allows users to select an image containing text or an object, select a preferred language, and the app will automatically detect and translate the text or recognize and translate the object into the selected language. It provides translation without requiring human translators and is free to use on phones or computers with an internet connection. However, there is a risk of minor translation mistakes due to limitations in AI.

    Copyright:

    © All Rights Reserved
    Download as DOC, PDF, TXT or read online from Scribd
    Download as doc, pdf, or txt
    of 7

    AI-Based Picture Translation App

    1) Background/ Problem Statement

    Trying to grasp and understand the universal nuances of multiple


    languages is a whole other game. To date, the only way to translate
    has been for 'human translators' to study many languages and
    attempt to interpret and bridge language boundaries for various
    purposes.
    The complexities of the characters may certainly put even the most
    modern technology to the test. Translation applications may be
    lifesavers when you're travelling and are surrounded by people who
    speak or read a language you don't understand.
    2) Working of the Project

    The system uses Object Detection from Google Cloud vision API to
    recognize the object and it is a part of Machine Learning (ML). Similarly,
    for Text, we are using Text Detection from Google Cloud vision API to
    recognize the Text, and it is also part of ML.

    It translates the text or object into a preferred language. For instance, if


    a user selects a computer image and Marathi as the preferred language,
    Google Translation API will translate the recognized image and display
    the message/output in Marathi.
    Another option is available here; the same user must pick the image on
    which text is accessible, and that text or message will be transformed
    into the specified language. It will be beneficial if you do not
    understand any other language text or message, as you will be able to
    convert it into your understandable language.

    3) Advantages
    It is free of cost.
    Capture an image or get an image from a phone gallery, it will
    automatically detect and translate it into a selected language.
    It will help to understand any object or message in any language.
    It uses a statistical learning approach.

    4) System Description
    The system comprises 2 major modules with their sub-modules as
    follows:
     Object Detect
    Capture or choose any photo of an Object
    By default, Source Language is English
    Choose Language to Translate the Result
    Speak option available

     Text Detect
    - Capture or choose any photo to Translate text in that Photo
    - By default, Source Language is English
    - Choose Language to Translate the Result
    - Speak option is available

    5) Project Life Cycle


    The waterfall model is a classical model used in the system development
    life cycle to create a system with a linear and sequential approach. It is termed a
    waterfall because the model develops systematically from one phase to another
    in a downward fashion. The waterfall approach does not define the process to go
    back to the previous phase to handle changes in requirements. The waterfall
    approach is the earliest approach that was used for software development

    6) System Requirements
    I. Hardware Requirement

    i. Laptop or PC
     Windows 7 or higher
     I3 processor system or higher
     4 GB RAM or higher
     100 GB ROM or higher

    ii. Android Phone (6.0 and above)

    II. Software Requirement

    iii. Laptop or PC
     Android Studio
    7) Limitation/Disadvantages
    - It required net connectivity.
    - Translate words there are often mistakes, particularly with
    grammar, structure, and context.

    8) Application
    Our system uses this AI-powered photo translation system to
    identify the object and text to translate them into the user’s
    desired language.

    9) Reference
    https://www.researchgate.net/publication/
    350555260_Artificial_Intelligence_Based_Language_Translation_Pla
    tform
    https://www.hindustantimes.com/cities/mumbai-news/iit-bombay-
    designs-ai-based-translation-app-to-help-students-from-linguistic-
    minorities-101631632296794.html

    You might also like