The Keris and The Komputer

[David]

Egads man! What witchcraft is this! LOL!

[A. G. Maisey]

Dunno David, above my pay grade.

[Ian]

Alan,

Unusual approach to identification of the keris. Any idea who might use such technology in a meaningful way?

Ian

[A. G. Maisey]

Well Ian, since I understand very little about the technology used by this method, any opinion of mine on matters such as this must be regarded as inherently defective, but as I sort of flit around the edges of academia without being a part of academia, I have noted that very often people who know very little about one discipline, but a great deal about some other discipline sometimes produce hypotheses that illustrate their phenomenal depth on knowledge in respect of the known discipline whilst at the same time illustrating their abysmal ignorance in respect of the other.

Having this belief as a base upon which to respond to your question, I would venture that those who might use this wizardry to classify a keris would very likely be those who have virtually no understanding of the keris.

[Lee]

Originally Posted by Ian

Any idea who might use such technology in a meaningful way

I expect this technology could give an airport luggage or postal parcel X-ray inspection device an ability to present a fairly accurate description of the contents to a customs officer without the need of opening...

[ariel]

As far as I could understand, this may be just a training exercise for machine image recognition. Kind of testing a simplified version of facial recognition. Machine reading of CT and MRI scans is under very active development. A very simple version is machine reading of ECGs, and is already widely used.

Kris, with their complexity of forms, are very handy model.

[JeffS]

I work with machine learning for classifying land cover types (forest, grassland etc) on satellite imagery to better under changes over time, like deforestation or development. This particular paper is using edge detection outputs to classify keris types. As such this will broadly allow it to classify broad groups that can be distinguishable with 2-D profile (silhouette) information. As Ariel says, this an interesting academic exercise but certainly can't add to keris understanding which is clearly far more subtle than profile ratios.

[mross]

This is cool stuff, at least to a komputer wienie like me. It seems to be a new take on algorithms to help identify an object. With a database of only 10 comparators it is a little weak. However I thing what we have here is someone has an interest in the Keris and needed to get a paper published. So wallah. Alan I don't think you have anything to worry about in the foreseeable future.

[David]

Originally Posted by JeffS

I work with machine learning for classifying land cover types (forest, grassland etc) on satellite imagery to better under changes over time, like deforestation or development. This particular paper is using edge detection outputs to classify keris types. As such this will broadly allow it to classify broad groups that can be distinguishable with 2-D profile (silhouette) information. As Ariel says, this an interesting academic exercise but certainly can't add to keris understanding which is clearly far more subtle than profile ratios.

I have to point out that you cannot really determine the dhapur of a keris by silhouette edge detection alone. Such a method cannot show, for instance, if the keris has tikel alis, blumbangan, sogokan or other interior keris elements that are essential for proper identification. I am still having problems finding a practical purpose for this methodology.