Progress Report Due: 12/20/15

• Progress:

Tasks Accomplished:

-Identifying our scope (wanting to recognize subway signs through numbers rather than other features such as color).

Questions Answered:

-How we'd recognize the subway signs (through color or through number recognition). We've decided to go with number recognition.

Lessons Learned:

-It is important we narrow down exactly how we will go about completing our project. From there we can find tutorials/source codes/etc. offline that specifically pertain to our project. It is too late in the year to still be experimenting.

Problem:

Difficulties Encountered:

-Finding a code that recognizes numbers while also includes a camera implantation.

Equipments Required: 

-Mac Laptops

-Mr. Lin's iPad

Show Stopper/Open Issues/New Risks: 

-Many source codes we have found so far are for license plate recognition. These could be beneficial although it is important we identify where and how the code could be specified toward subway signs rather than license plates. There may not be a differentiation in code if just the numbers are being detected anyways.

• Plan:

Proposals/Steps to Attack the Problems/Action Items for the Coming Week: 

- Find a source code that recognizes numbers and successfully implement it into our app. Also including a camera feature since the physical recognition of numbers cannot be down without the camera.

Experiments to Conduct, Ideas to Try, Vendors to Contact, Updated Schedule, etc.

-Continue to make sure our app works off of Mr. Lin's iPad as we add new code.

-We are working off of a license plate tutorial's source code right now that seems to be beneficial to our app. During Tuesday's class period we will see if it is compatible with the iPad.

RE: Patent Search Due: 11/30/15

You have come up a very nice list of patents relevant to your research. Your comments about each patents are also very valuable. If you can analyze the patents by grouping them into meaningful categories, and identify the trends of all the patents over time. It will help us get a glance of how technology has been evolved in this field, and it may also help you to identify the possible areas of potential innovations.  

Progress Report Due: 12/6/15

• Progress:

Tasks Accomplished:

-We have found a tutorial that includes source code for an object detection app. The application does this by using MSER (Maximally Stable Extremal Regions) in iOS. The app is very simplistic and only recognizes the Toptal's (the developer company) logo. It does so without having to take a picture or record a video, as we wanted our app to be able to do. (http://www.toptal.com/machine-learning/real-time-object-detection-using-mser-in-ios)

Problems Solved:

-We were worried we'd have trouble creating an object recognition app that didn't require a picture to be taken or video to be recorded. Luckily, we found an application that recognizes objects without having to do so.

Questions Answered:

-How to recognize objects with a camera. How to do so without taking a picture or recording a video.

Lessons Learned:

-It is important we understand what each code and tutorial we follow actually does. We copy and paste so many codes to see how and if they'll benefit our app, without actually knowing what they do. Time can be wasted if we are using codes that may not be beneficial to our app at all. It may be better from now on to learn and wrap our heads around certain codes before adding them into our Xcode Project.

• Problem:

Difficulties Encountered:

-We are in the process of implementing the Toptal source code for object recognition into our app. Although, we are trying to find and figure out where in the code we can change the app so that the camera will be recognizing the objects we tell it to (the app can only identify the Toptal logo right now and we need to change the code so that it can recognize numbers in subway signs).

Missing Information: None.

Equipments Required: 

-Mac Laptops, Mr. Lin's iPad.

Materials Missed: 

-We are not lacking of any materials as of now.

Show Stopper/Open Issues/New Risks: 

-Not being able to adjust the code to fit our needs (recognizing train numbers/letters on subway signs).

Personal Problems: None as of now.

Schedule Conflicts: 

-None as of now. Whenever we cannot meet in person we communicate via Facebook to let one another know of new discoveries outside of classtime.

• Plan:

Proposals/Steps to Attack the Problems/Action Items for the Coming Week: 

-Search the code to see where the Toptal logo is implemented and change the app so it can read numbers and letters.

Action Items for the Coming Week:

-In addition to altering the code, we want to understand what the code actually does. What information does it provide once objects are identified? How does the app transform the object to a readable form?

Experiments to Conduct, Ideas to Try, Vendors to Contact, Updated Schedule, etc.

-Continue to make sure our app works off of Mr. Lin's iPad as we add new code.