- ํ์ต์ง ์ด๋ฏธ์ง ๋ฐ์ดํฐ์์ ๋ฌธํญ์ ๋ณด๋ฅผ ์ถ์ถํด ๋ฐ์ดํฐ๋ฒ ์ด์ค์ ์ ์ฅ ํ ํด๋น ๋ด์ฉ์ ์ฌ์ฉ์์ ๋ธ๋ผ์ฐ์ ์์ ์ ์ ๊ฐ๋ฅํ๋๋กํ๋ ํ๋ซํผ
- Quizrix is a platform with a user-friendly interface designed to upload and view workbook problems via classifying different components of the question from a problem image and saving them to a database.
- ํ์ต ๋ฌธ์ ์ ์ด๋ฏธ์ง๋ฅผ ์
๋ก๋ ๋ฐฉ์์ผ๋ก ๋ฑ๋กํ๋ค.
The user uploads the image of the problem.
The components of the problem are classified through a deep-learning model. (๋ชจ๋ธ ์์ฑ ํ ์์ )
์ต์ข
๋ณธ gif ์ถ๊ฐ
๋ณธ ํ๋ก์ ํธ๋ ์ฝ๋๋ 'QUIZRIX' ์ฌ์ ์ ์ผ๋ถ ํ๋กํ ํ์ ์ ์์ ์ํด ์งํ๋์์ต๋๋ค.
This project was carried out for building a prototype for "Quizrix" of Codnut.
์นํ์ด์ง์ ๋ฌธ์ ์ด๋ฏธ์ง๋ฅผ ์ฒจ๋ถํ๋ฉด ๋ฌธํญ / ๋ณด๊ธฐ / ์ ์ง๋ก ์ธ๋ถํํ์ฌ ๋ฐ์ดํฐ๋ฒ ์ด์ค์ ์ ์ฅํฉ๋๋ค.
The problem is classified and separated into three components; question, content, and answer, and then they save into the database.
ํ์ฌ ๊ฐ๋ฐ ์ค์ ์์ต๋๋ค.
๋ถ๋ฅ | ๊ธฐ์ |
---|---|
๊ฐ๋ฐํ๊ฒฝ | |
Front-end | |
Back-end | |
DB | |
Deep learning | |
Etc |
-
Clone Repository
git clone https://github.com/2021-Team-E/Mandoo.git
-
package.json
{ ... "proxy": "http://<ip>:<server_port>", ... }
-
config.js
export const USER_SERVER = "http://<ip>:<server_port>";
-
app.py
mongo = MongoClient('mongo_db', 27017)
-
detection.py
#์๋ฒ ํ๊ฒฝ์์์ tesseract.exe ๊ฒฝ๋ก๋ก ์ค์ pytesseract.pytesseract.tesseract_cmd="/usr/bin/tesseract"
-
requirements.txt
Dockerfile์์ ๋ฐ๋ก ์ค์นํ๋ ๋ผ์ด๋ธ๋ฌ๋ฆฌ๋ฅผ ์ฃผ์์ฒ๋ฆฌํฉ๋๋ค.# requirements.txt ... # tesseract-ocr # pytesseract โฆ
-
s3.py <โ Make new file name 's3.py' in ./Backend
AWS_ACCESS_KEY = <AWS ACCESS KEY> AWS_SECRET_KEY = <AWS SECRET KEY> BUCKET_NAME = <AWS S3 bucket name>
docker-compose up โbuild
์ด๋ฆ | ๊ฐ๋ฐ๋ถ์ผ | ๋ด๋น |
---|---|---|
์ต์ค์ฌ | Front-end, Back-end | Web development,API Design, Cloud |
์ด์ฑ๋ฆผ | Front-end | Web development |
๋ฐ์ ์ | Front-end | Web development |
์ดํ์ | Back-end | API Design |
Ryan Lee | Deep learning | Algorithm |
๋ฐ๊ทผ์ฐ | Devops | Cloud, Docker |