Artificial Intelligence & Image Recognition Assignment
Added on - 16 Sep 2019
Showing pages 1 to 3 of 7 pages
Proposed Project Title:Artificial Intelligence & Image Recognition:Requirements of a High-PerformanceMobile Visual Search System
Brief description of the background to the proposed project:(i.e. description of problem area, nature of challenge)Image recognition(orcomputer vision) is an area of artificial intelligence (AI), or morespecifically machine learning, that looks at acomputer's ability to gain a high-level ofunderstanding from images or video using neural networks.The aim here is to develop an artificially intelligent image recognition app that is able toperceive and process visual information, and to then deliver required relevantinformation accordingly.A number of key issues present themselves when considering mobile visual searcheswhich require access to memory efficient image databases, including the followingpoints:1. The ability to develop a secure database representation that can be searchedquicklyacrossmanyimages by an sql query. This will depend on how the database isset-up and where it is stored (either locally on a device or on a server).2.The important consideration of possible visual distortions between two given images(such as geometric or photometric distortions and/or surrounding clutter) and how thiscould affect the accuracy of returned results.These identified factors present a chance to carry out further research throughinvestigating the best methods/optimisation techniques to use for solving them.This will also enable the effective incorporation of other related technologies suchnavigational image augmentation features for improved functionality.
Brief description of proposed project objectives:(including scope of proposal, planned success criteria)Primary ObjectivesTheproposed project is a real-time landmark recognition Android app that will actas a digital tourist assistant. It willenable a user/tourist to take a picture of alandmark/point of interest, and to then receive relevant information about thatgiven image object (such as it's historical information and/or its opening hoursetc.).The app will also provide user interaction, with the exact geographical location ofthe landmark being displayed via GPS, plus reviewed local areas of interest suchas restaurants or other local attractions.An option to save the given image will also be provided.This will also allow tourists to share their real-time experiences on social networksas well.Extension Objectives:Since this app will be capable of recognising both landmarks and the GPSlocation, an interesting feature that can be added is the capability to incorporateoverlay pointers onto the image (showing directions for a guided tour etc.).This could be implemented using augmented reality technology, a related branch ofAI and image/object recognition. Augmented reality platforms such asVuforiawould enable this through the integration of software development kits (SDKs).Research: Thus far, reading has been carried out about some of the techniquesthat can be used for both storing and recognising images for efficient and securemobile visual search.Augmentation techniques for developing this app further have also beenconsidered and will be continually researched, particularly its involvement (if any)in landmark recognition.