Inspiration
Do you ever spend 2 hours thinking of a caption for your instagram post? Such is the life of Eric Vuong, an avid instagram-er (@foodlovereric), Posting pictures everyday, or sometimes every hour becomes a chore. To help with coming up with captions, CaptionThis was made.
What it does
With the rising popularity of social media platforms and concerns of privacy, it has become difficult to come up with a quote that attracts attention while conforming to social standards. CaptionThis provides a solution by giving a quote caption that best matches your image by using a trained neural network to detect various objects within your picture and provide meaningful quotes.
How we built it
The image is processed and classified and sends back the different categories that best describes the image. These categories are then sent to the DataMuse Api that adds a layer of abstraction to the data and processes the categories into keywords. These keywords are then used to search through a database of quotes.
Challenges we ran into
Understanding the different api used, and connecting them through our backend. Making the UI pretty.
Accomplishments that we're proud of
We're proud to have made a product that we can use in our everyday life.
What we learned
We learned about IBM-Watson,Data-processing and learned Angular.
What's next for CaptionThis
Improve efficiency of the algorithms, and improve accuracy of quote matching.
Log in or sign up for Devpost to join the conversation.