Hacker News Reader

Comment by Omnipresent | Hacker News Reader

To overcome these shortcomings, we used a modern machine learning-based algorithm. The algorithm is trained on images where humans annotate the most significant edges and object boundaries.

Does anyone know which "modern machine-learning algorithm" they are referring to here? Is there something like this available in OpenCV?

View on HN

We can reasonably assume it's nothing more complicated than what you can do using a combination of machine learning libraries and OpenCV (however if they have instead some new technique, I hope to find a paper from them in a few months :) ).

EDIT: Adding more details.

If you are looking for similar ideas, you should read papers in the area of object-class segmentation / classification[0][1][2], and generic supervised learning.

[0] https://arxiv.org/abs/1510.03727

[1] https://www.microsoft.com/en-us/research/publication/object-...

[2] https://www.ais.uni-bonn.de/papers/DAGM_NC2_2011_Schulz.pdf

Yup, there aren't any ML built into OpenCV but perhaps they use a ML library on top of OpenCV.

OpenCV doesn't have any ML algorithms builtin that I know of, but the article is pretty vague there eh? Either way, document-scanning from a phone camera is no picnic.

I tried a little while ago. Memory is kind of hazy, but depending on how well you do the image transformation (automatically[ish] skew to rectangle, etc), image quality might get poor. Then you have to do the actual OCR. Now the only complete OSS solution is Tesseract and it's not a state-of-the-art one. There's also ocrpy, but it's more of a toolkit and it's model needs to be trained (one single-line text when I last checked). So yeah, it's fairly hard to do.

https://github.com/opencv/opencv/blob/master/modules/ml/src/

Obviously it is a convolutional neural net. Here you can find source code for one of the latest work:

https://github.com/s9xie/hed

Not so obvious. In fact, I believe they are using Random Forest.

Good point

Hi, they are using Random Forest to get the edges :)

Reply on news.ycombinator.com