Outcome

Concept:

The concept of wordcloud is first brought up and implemented by Jonathan Feinberg. A word cloud is a popular visualization of words typically associated with Internet keywords and text data. They are most commonly used to highlight popular or trending terms based on frequency of use and prominence. A word cloud is a beautiful, informative image that communicates much in a single glance. [1]

Outcome:

I created several wordcloud profiles based on Andreas Mueller's code. Further, I created a video profile of a dog based on its story. Keywords are retrieved from the text automatically and the outline of the cloud is filled in as much as possible. A dog's profile with keywords about its story shown on its body can be displayed in real-time and vividly in the video.

Process:

1. Take a picture, write a story about the object (person, animal, etc);

2. Detect the object in the picture and make the background all white;

3. Put the story and the image with pure white background into the generator.

4. Profile Generator will output a static wordcloud profile with the color on different parts computed based on the local area.

5. Further, we can choose whatever colors we like and make the profile more colorful.

6. We can put a series of such wordcloud profiles into a GIF or a video.

Reflection

1. Based on text analysis, we can realize choosing the relevant outline automatically and generate a corresponding profile.

2. We can further optimize a video profile by improving the performance of temporal coherence.

3. Static profile, GIF-based profile or video profile could be used in many contexts. We can use them for bookmarks of E-books. We can use them as profiles of our online social network.

Reference

[1] "Word Cloud Definition." - Peach Belt. Web. 12 Dec. 2015. <http://www.peachbelt.com/information/thePBCis/wordcloud>.

[2] The picture of the woman is a profile of Nina Dobrev.

[3] The picture of the dog is from https://www.youtube.com/watch?v=2PJFfR4szhM