For the Designing with Web's class, I've chosen the Artficial Intelligence assignment. Here I'm gonna experiment a new application using AI and Machine Learning. The concept is a website that would enable people to discover new mangas and comics based on what they have watched on TV or on the Internet.
It is designed for manga readers or people that like watching it on TV, that want to discover new mangas and comics.
My project, I think, could be useful in different fields :
Manga (漫画 manga) are comics or graphic novels created in Japan or by person using the Japanese language and conforming to a style developed in Japan in the late 19th century.[1] They have a long and complex pre-history in earlier Japanese art..
To have a more efficient website we need then to now what are the different types of mangas:
✿Kodomo:For a young audience under ten, regardless of gender
✿Shonen: For a young male audience aged 8 to 18
✿ Shojo: For a young female audience aged 8 to 18
✿ Seinen: For a young male audience aged 16 and more
✿ Josei: For a young female audience aged 16 and more
✿ Seijin: For an adult audience of 18 and over.
Sources : Vikidia
Considering the nature of our AI, our machine learning process will use unsupervised learning. We have to establish and give a large dataset with classifications to the machine. The dataset will contain many mangas and comics for each genres we defined and the AI will learn from that data.
Here's the summary of our AI's development :
This AI could be publish on the web and trained by users. It could be open and every surfer could upload a comic or a manga and precise its style in order to extend the AI's dataset : the bigger its library gets, the more effective it is.
At the end of the day we could even create a platform that gather several mangas that the users would read or watch on their phones