Training model to recognize annotations in text.
選択できるのは25トピックまでです。 トピックは、先頭が英数字で、英数字とダッシュ('-')を使用した35文字以内のものにしてください。
rita 892d285569 Update 'README.md' 2年前
dataset first attempt 3年前
README.md Update 'README.md' 2年前
model.h5 first attempt 3年前
model.yaml first attempt 3年前
predict.py first attempt 3年前
requirements.txt first attempt 3年前
test.jpg first attempt 3年前
test.jpg.predicted.png first attempt 3年前
test2.jpg first attempt 3年前
test2.jpg.predicted.png first attempt 3年前
test3.jpg first attempt 3年前
test3.jpg.predicted.png first attempt 3年前
test4.jpg first attempt 3年前
test4.jpg.predicted.png first attempt 3年前
test5.jpg first attempt 3年前
test5.jpg.predicted.png first attempt 3年前
test6.jpg first attempt 3年前
test6.jpg.predicted.png first attempt 3年前
test7.jpg first attempt 3年前
test7.jpg.predicted.png first attempt 3年前
test8.jpg first attempt 3年前
test8.jpg.predicted.png first attempt 3年前
test9.jpg first attempt 3年前
test9.jpg.predicted.png first attempt 3年前
test9.png first attempt 3年前
test10.jpg first attempt 3年前
test10.jpg.predicted.png first attempt 3年前
train.py first attempt 3年前

README.md

Image Classifier for Annotations

At the time of the research for The Library is Open, a point of interest for everyone was annotations.

The Library is Open was a research project focused on knowledge production and its systems. The work questioned the shadows and biases cast by knowledge taxonomy; examined digital proprietary tools as impediments to the free access and circulation of knowledge; and developed annotation tools to foster collective interpretation towards existent knowledge.

As a research group, we were reading and annotating texts together and debating the possibilities of sharing these notes. One particular discussion was about what could/should be considered an annotation: folding corners of pages, linking to other contents, highlighting, scribbling, drawing. I was curious if we could train a computer to see all of these traces, so I started prototyping some examples.

Aim: make the computer recognise “clean” pages of books or “annotated” pages of books.

Each set (test and training) had 50 examples of “clean” pages and “annotated” pages, it makes sense to add more in the future. The results were not very accurate. Pages with hand-written text gave better results while highlighting and computer notes were often misinterpreted. It’s useful to try to see what the computer is looking for, understand if the script is breaking the image in parts, and try other scripts.

Annotated image