Research

OK, it’s been a while again, but here are the reasons for being silent. 1-bit LBD reconstruction is out! Remember all those posts about LBDs, FREAKs, BRIEFs, and reconstructing images ? The latest version of tis work is out with a major feature: 1-bit quantized LBDs reconstruction. Yes, 1-bit ! To achieve this, we leverage some results from 1-bit Compressed Sensing thanks to my co-author Laurent Jacques. So, the pre-print is on arxiv and on infoscience, and you can get the code from github.

The SNR situation is getting worse, or at the very least more and more intriguing.

LBP model An LBP can be decomposed into two tiers: first, a real description vector, obtained by convolution-then-difference then the quantization (binarization) operation. Mathematically, the real i-th component of the descriptor is computed with the formula: $${\mathcal L}(p)i = \langle{\mathcal G}{x_i, \sigmai} , p \rangle - \langle G{x_i’, \sigmai’} , p\rangle, $$ where ${\mathcal G}{x_i, \sigmai}, {\mathcal G}{x’_i, \sigma’_i}$ are two Gaussians. The variety of the LBP family comes from the choice of these Gaussians : they can have a fixed size but random positions (a la BRIEF), fixed sizes and positions (a la BRISK)1… The choice in FREAK was :

I’m not as much on FREAKs reconstruction and blogging as I wished, because I have one really important target for the next 6 months: submitting my thesis before the end of the year. The dreaded SNR measure We’ve come up with a nice equation in the past few months (hence, this work is completely unpublished) and after managing to implement it I’m now testing it to show that it is actually outstanding.

In a previous post, I have briefly introduced our FREAK descriptor, which belongs to the more general family of the LBPs. In this post, I will state mathematically the problem of the reconstruction of an image patch given its descriptor, i.e. answering the question:

Can you guess which image part created this particular description vector ?

Integrating our lab’s FREAK in your vision workflow is getting easier and easier!

OK, starting to mix posts in English and French since the English version of the blog is still buggy.

Tweet battle Petite taquinade sur Twitter aujourd’hui avec Igor Carron, le rédacteur du blog Nuit Blanche. Igor1 vantait les mérites d’un article intéressant à partir d’un des résultats présentés : une reconstruction d’image à partir d’une image ayant perdu (aléatoirement) 90% de ses pixels. Mais.. attendez… ne serait-ce pas là un problème d’inpainting ? Si fait ! C’était donc l’occasion rêvée pour reparler du code de ce blog récemment arrivé sur Github.

Qui disait que le Pattern Recognition c’était pas du cooking ?

Les choses compliquées sérieuses commencent.