Revision history [back]

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways the techniques have to be based on some kind of "features".

I've previously tried counting black or white pixels in divisions of the individual symbol images, making vectors out of those numbers and using the basic cosine difference to classify symbols. This method does not allow enough precision 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, but look totally different.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways the techniques have to be based on some kind of "features"."features". Reading the grid is not a problem, classifying the symbols is.

I've previously tried counting black or white pixels in divisions of the individual symbol images, making vectors out of those numbers and using the basic cosine difference to classify symbols. This method does not allow enough precision 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, but look totally different.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways the techniques have to be based on some kind of "features". Reading the grid is not a problem, nor is extracting the symbols, but classifying the symbols is.

I've previously tried counting black or white pixels in divisions of the individual symbol images, making vectors out of those numbers and using the basic cosine difference to classify symbols. This method does not allow enough precision 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, but look totally different.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways the techniques have to be based on some kind of "features". Reading the grid is not a problem, nor is extracting the symbols, but classifying the symbols is.

I've previously tried counting black or white pixels in divisions of the individual symbol images, images (in B&W), making vectors out of those numbers and using the basic cosine difference to classify symbols. This method does not allow enough precision 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, but look totally different.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways the techniques have to be based on some kind of "features". Reading the grid is not a problem, nor is extracting the symbols, but classifying the symbols is.

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 does not allow enough precision 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, areas/divisions, but look totally different.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways the techniques have to be based on some kind of "features". Reading the grid is not a problem, nor is extracting the symbols, but classifying the symbols is.

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 does not allow enough precision 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.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways the techniques have to be based on some kind of "features". Reading the grid is not a problem, nor is extracting the symbols, but classifying the symbols is.

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 does not allow enough precision 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.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways the techniques have to be based on some kind of "features". Reading the grid is not a problem, nor is extracting the symbols, but classifying the symbols is.

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 does not allow enough precision 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.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways the techniques have to be based on some kind of "features". Reading the grid is not a problem, nor is extracting the symbols, but classifying the symbols is.

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.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection of symbols in a grid, without knowing what kind of symbols are expected. In other ways words, the techniques have to be based on some kind of "features". Reading the grid is not a problem, nor is extracting the symbols, but classifying the symbols is.

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.

Specifically I might be looking for explanatory technical explanations / resources for the existing feature detecting algorithms and what kind of features they consider.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection detection/classification of symbols in a grid, without knowing what kind of symbols are expected. In other words, the techniques have to be based on some kind of "features". Reading the grid is not a problem, nor is extracting the symbols, but classifying the symbols is.symbols.

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/YgFbKB46y

Specifically I might be looking for explanatory technical explanations / resources for the existing feature detecting algorithms and what kind of features they consider.

Hi,

I'm looking for pointers into what kind of techniques exist for performing detection/classification of symbols.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/YgFbKB46y

Specifically I might be looking for explanatory technical explanations / resources for the existing feature detecting algorithms and what kind of features they consider.

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/YgFbKB46y

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

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/YgFbKB46y

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.

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/YgFbKB46yhttp://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.

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.