mviljamaa's profile - activity

I'd like to know this as well.

What's the shape/contour descriptor, you mean the contours returned by e.g. findContours? It's probably what I'm looking for, because the contours are obviously different. I just couldn't think how to do comparisons with them. Any links?

@GilLevi I don't know if it matters what kind of symbols there would be, because, as stated, the symbols could be anything, but there's a limited set of them and they would need to be classified in some way. It's maybe a strange problem, but real. What I'm trying to understand is what kind of feature detectors are out there that are more special than counting pixels in the divisions and using the cosine difference, so I could understand what they do / are useful for and could use them for identifying/separating symbols. An example five symbol set can be found in: http://temp-share.com/show/HKd9f201A , particularly e.g. symbols 2 and 3 get mixed or there's not enough separation in the numeric values when just counting the pixels. Let me know if I'm not being specific enough.

http://stackoverflow.com/questions/10526124/basic-build-issue-regarding-libs-pkg-config-and-opencv

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection/classification of symbols. Specifically I'm reading individual symbols out of grids.

I've previously tried counting black or white pixels in divisions of the individual symbol images (in B&W), making vectors out of those numbers and using the basic cosine difference to classify symbols. This method isn't as precise as needed though, because it's blind for differences in symbols that may have close to the same amount of pixels in close to the same areas/divisions, but look totally different.

An example symbol set: http://temp-share.com/show/HKd9f201A

Specifically I might be looking for explanatory technical explanations / resources for the existing feature detecting algorithms and what kind of features they consider in order to classify e.g. the example symbols.

I'm looking for known techniques or concepts regarding extracting tiles from a grid of tiles, where the grid and tile sizes, nor the number of tiles, are not pre-determined and the tiles are not necessarily exactly the same size.

For my specific problem involving a grid of tiles where the task is to crop every tile, what I've looked at involves simple calculation of height, width and centroid of one tile (a corner tile) by using floodfill and using these quantities for identifying, where the other tiles must approximately lie and what size of area I need to crop. I also know the grid size by finding the largest contour after using findCountours. However, when using OpenCV and real, non-B&W images as well as some image processing (Gaussian blur, adaptive thresholding...) I notice that the tile sizes can vary slightly and become not well-defined and when traversing a large grid the initial calculation may become inaccurate for the tiles that are read later. I have some ideas for how to approximate/recalibrate this, but I wonder if there are any "standard" techniques for recalibrating or finding the exact tile area (= basically the black area or a few pixels larger than that to all directions) for every tile in the described situation (e.g. something involving floodfilling, although that would need an assumption that the tiles have the same fill color, which is not true, because the tiles may have symbols, or the Hough transform, which I am aware of).

Here's an example grid (a small one):