Vision

• 

  An example of what Vision does

Inspiration

Our inspiration for this project comes from being visually impaired. For people with glasses or other optical disabilities, recognizing pictures can be a hassle. We made this program so pictures could be easily recognized and saved for later.

What it does

Vision analyzes a given picture and outputs any recognized objects.

How we built it

We used deep learning and OpenCV for the logic behind the code. Vision is written in Python.

Challenges we ran into

Initially, the code was not functioning properly with some images. We tested the code with a multitude of images and we found out that the code did not work well on blurry or low quality images. We optimized our code to work better with a lower quality image to overcome this challenge.

Accomplishments that we're proud of

We are very proud that we were able to learn about the capabilities of machine learning and OpenCV. Before we started this project, we thought machine learning was a very daunting task. Now that we have utilized it in our program, we are more comfortable approaching other unknown topics.

What we learned

We learned how image recognition software works, along with Single Shot Detector and Mobile Net architecture. We combined these elements in Vision.

What's next for Vision

We want to expand Vision to make it easier to use and make it so that more objects can be recognized. One possible addition would be to bring up the nutritional facts of food when a picture of it is taken.

Built With

• mobilenetssd
• opencv
• python
• xcode