Text Reader
Text Reader
Text Reader
Input Text Reader
Input Text Reader
Png to Text
Png to Text
About
About
Project Name: Text Reader
Project Name: Text Reader
Achievements:
Achievements:
1) Ignite CS 2022 1st Place （Grade 7-8）
1) Ignite CS 2022 1st Place （Grade 7-8）
2) Inclusive Coding Festival 2022 Best AI-based Solution
2) Inclusive Coding Festival 2022 Best AI-based Solution
3) Provisional Patent: I have successfully filed the provisional patent for the AI algorithm I developed - Jiaheng Su, "An Application to Improve the Reading Experience of Users using Artificial Intelligence", US Provisional Patent, 63/382,799, 2022/11/15
3) Provisional Patent: I have successfully filed the provisional patent for the AI algorithm I developed - Jiaheng Su, "An Application to Improve the Reading Experience of Users using Artificial Intelligence", US Provisional Patent, 63/382,799, 2022/11/15
Description:
Description:
In Summer 2022, I did my first research internship in college. I joined Dr. Sun's research lab at Cal Poly Pomona. During the internship, I worked on a research project related with AI. Since I like listening to audio books, I thought of building an application for those who also enjoy audio books but the audio is not available. I first used the code to access the image files of the computer, which supports txt, png, or jpg formats. In the txt file, my program uses Mac say command to make the sound and for-each loop to read out each words. If the input is a png/jpg file, the code inside will upload that file to the Microsoft machine learning AI engine which can automatically extract the text inside a png/jpg file into an txt file. After it is converted, the AI will send the txt file back, and the code inside will repeat the process above to read out the whole article.
In Summer 2022, I did my first research internship in college. I joined Dr. Sun's research lab at Cal Poly Pomona. During the internship, I worked on a research project related with AI. Since I like listening to audio books, I thought of building an application for those who also enjoy audio books but the audio is not available. I first used the code to access the image files of the computer, which supports txt, png, or jpg formats. In the txt file, my program uses Mac say command to make the sound and for-each loop to read out each words. If the input is a png/jpg file, the code inside will upload that file to the Microsoft machine learning AI engine which can automatically extract the text inside a png/jpg file into an txt file. After it is converted, the AI will send the txt file back, and the code inside will repeat the process above to read out the whole article.