Training model to recognize annotations in text.
Du kannst nicht mehr als 25 Themen auswählen Themen müssen mit entweder einem Buchstaben oder einer Ziffer beginnen. Sie können Bindestriche („-“) enthalten und bis zu 35 Zeichen lang sein.
rita 892d285569 Update 'README.md' vor 2 Jahren
dataset first attempt vor 3 Jahren
README.md Update 'README.md' vor 2 Jahren
model.h5 first attempt vor 3 Jahren
model.yaml first attempt vor 3 Jahren
predict.py first attempt vor 3 Jahren
requirements.txt first attempt vor 3 Jahren
test.jpg first attempt vor 3 Jahren
test.jpg.predicted.png first attempt vor 3 Jahren
test2.jpg first attempt vor 3 Jahren
test2.jpg.predicted.png first attempt vor 3 Jahren
test3.jpg first attempt vor 3 Jahren
test3.jpg.predicted.png first attempt vor 3 Jahren
test4.jpg first attempt vor 3 Jahren
test4.jpg.predicted.png first attempt vor 3 Jahren
test5.jpg first attempt vor 3 Jahren
test5.jpg.predicted.png first attempt vor 3 Jahren
test6.jpg first attempt vor 3 Jahren
test6.jpg.predicted.png first attempt vor 3 Jahren
test7.jpg first attempt vor 3 Jahren
test7.jpg.predicted.png first attempt vor 3 Jahren
test8.jpg first attempt vor 3 Jahren
test8.jpg.predicted.png first attempt vor 3 Jahren
test9.jpg first attempt vor 3 Jahren
test9.jpg.predicted.png first attempt vor 3 Jahren
test9.png first attempt vor 3 Jahren
test10.jpg first attempt vor 3 Jahren
test10.jpg.predicted.png first attempt vor 3 Jahren
train.py first attempt vor 3 Jahren

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