Training model to recognize annotations in text.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rita 892d285569 Update 'README.md' 2 years ago
dataset first attempt 3 years ago
README.md Update 'README.md' 2 years ago
model.h5 first attempt 3 years ago
model.yaml first attempt 3 years ago
predict.py first attempt 3 years ago
requirements.txt first attempt 3 years ago
test.jpg first attempt 3 years ago
test.jpg.predicted.png first attempt 3 years ago
test2.jpg first attempt 3 years ago
test2.jpg.predicted.png first attempt 3 years ago
test3.jpg first attempt 3 years ago
test3.jpg.predicted.png first attempt 3 years ago
test4.jpg first attempt 3 years ago
test4.jpg.predicted.png first attempt 3 years ago
test5.jpg first attempt 3 years ago
test5.jpg.predicted.png first attempt 3 years ago
test6.jpg first attempt 3 years ago
test6.jpg.predicted.png first attempt 3 years ago
test7.jpg first attempt 3 years ago
test7.jpg.predicted.png first attempt 3 years ago
test8.jpg first attempt 3 years ago
test8.jpg.predicted.png first attempt 3 years ago
test9.jpg first attempt 3 years ago
test9.jpg.predicted.png first attempt 3 years ago
test9.png first attempt 3 years ago
test10.jpg first attempt 3 years ago
test10.jpg.predicted.png first attempt 3 years ago
train.py first attempt 3 years ago

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