CS6825: Computer Vision word cloud
Main
Goals
Data Input
Research
Getting Started
Proposal

Implementation
Requirements AND Data Output

Deliverables
Other

Project 3: Mobile Imaging Research

                            DUE DATES , Evaluation Guidelines 

You are to write a GUI Java application that run on the Android platform and can run under an Android Emmulator in the Eclipse Java IDE that features some Computer Vision Application. Your Application MUST BE APPROVED by the instructor and should be of significant complication to be interesting and have some barrier of entrance (meaning would take at the least a computer vision scientist to implement it). You are going to propose a Mobile Imaging Application that in some way will assist a blind or low-vision (not completely blind) person

 

PART of choosing this option will involve self learning of Android Programming ---you have my CS4521 website to help you out. We have done this project as an official project and everyone loved it. I have even done Android programming successfully in my CS3340 OOP class ---so it is something if you like the idea that can be fit into the course. To accommodate the fact that there is some new learning here --- to SOME EXTENT (YOU MUST REQUEST AND GET APPROVAL) the use of other FREEWARE (you can NOT STEAL) code that you use...be careful about licensing if you intend to turn into the android marketplace --- you will want to own your own code!!!!

 

 

IMPORTANT REQUIREMENT:
You must use Google Cloud Vision to implement your recognition layer (which means you will make an Asynchronous call passing your data to Google Cloud Vision service --you must register)
IF this does not fit in your proposal you are to use the Google Cloud Machine Learning API or Google TensorFlow API (and also read here and here) instead for some part of your project which again requires Asynchronous calling..


EXTRA CREDIT - you will get 30 extra points if you use Google TensorFlow and train your own model (do not use someone elses model) ...
see this video for mobile and backend tensor flow

 

 

© Lynne Grewe