Forum Replies Created
-
Posts
-
@ Wak:
As Ayelet writes, using the optical shade may solve your problem.But black items reflect little light, and colour in visible light is not the same as colour under IR.
You cannot measure what is not there!
I have got good signals from some dark brown powders like cinnamon and nutmeg and clove, but discrimination between them was not so good.@ Jeanrochmeuni:
Raw spectra download is only possible with a Researcher account, and is the only difference between Developer and Researcher levels.@ Anthony:
I hope Ayelet’s answers have made it clear that there are TWO Apps with greatly different purpose.
a) SCiO Mobile Lab: which we developers will use to create new collections and from them Apps or Applets.
– the cheese collection in there is just for us to play with.
b) SCiO App: which all users will have to scan stuff – depending on the Apps and Applets on it.– it also contains a mini workshop for user created Applets (ID of things but not values).
I have seen a test version of the latter – it certainly Exceeds Expectations, but I have no knowledge of how widely it has been circulated yet.Hi yedaoxiang – the lower limit of detection is stated to be around 1%, so residues which are present in ppm or ppb will not be found.
Agreed! This is a critical feature that all “Recognition Apps” MUST have. As you guys say if the App estimates the wrong pill or the wrong mushroom it could be fatal.
If CP don’t post a reply, I will send a PM asking for re-assurance that this capability will be delivered soon.Roger
I asked this question of Consumer Physics.
Can we get a response saying that the scan does not match any others in the model?
Reply: The feature is under development.
No time scale given.
Hi Rober – It is an excellent question, and not dumb at all.
I was thinking about the same issue with respect to Paul Brady’s currency project.
How can we get a response that shows the latest scan is significantly outside others in the same collection, i.e. an unknown.In case CP don’t spot your question, I will ask them directly by PM, and share the answer. (unless you have already done so?).
Note: When you make your real collection, each sample should come from a different batch of pills so that you do not unfairly tighten the range of scan results. But to test “seen before?” it is exactly right! (please forgive me if you already understood that).
Hi Paul;
I think option 1 where you scan the same note and same location multiple times as a new sample is wrong – it is NOT a new sample, and would unfairly tighten the spread of results. (Multiple scanning within a single sample ID is good).
Making the model simple will help speed of scanning – stick to white paper under the note as standard. (I would test whether a single sheet is enough, the illumination does penetrate somewhat).
You may need to have Condition as an attribute, with New, Used, Grubby as values.
Given the complex patterns on a note, how will you cope with slight inaccuracies in the area illuminated? Will you use a jig? Otherwise that variance may be greater that that of bad notes.
Also – how do you hope to recognise forgeries? Do you have access to some bad notes? or will you try to detect differences from expected scans? i.e. outliers. I would not know how to do that, but maybe CP can offer good advice!
PFB: Good Work – I was looking for an excuse to buy a 3-D printer, THANKS!
What is the OD of your creation?Hi Sean.
AS I understand it SCiO can only work on the reflected NIR of the molecules that are illuminated. So estimation of elements in a complex and varying mix would not work. I cannot imagine how you would set up the reference samples.
Pesticides are likely to be well below the 1% detection threshold. This has been a strong wish from many, but CP have repeatedly said that it is unlikely to work. I do wonder if the samples could be worked up to concentrate the surface chemicals – washed in alcohol for instance, and then the alcohol evaporated to give a “strong” solution. If accurate contamination levels were required, getting known reference samples would be tricky without access to good lab facilities. It is such an important topic that it should be investigated, even if the success likelihood looks low.@ A Scientist: Thanks for the tip … I have partial success.
In SCiO Mobile Lab: I can see the images in the iOS version but NOT with Android!
Also drilling down into the samples works differently between the two Apps. ( I will inform CP)
I wonder what Phone type you have?In Web SCiO lab I still cannot see the images (Using Chrome browser) – I will try with a different browser later.
If you have plenty of spare time, perhaps you can make a couple of screen shots?
Hey Khoa, I think garlic may be a tough target as it can have quite a varied amount of peel and husk, I will listen out with interest on how you do.
I was surprised with green leaves, that the SCiO would shine right through them, and give slightly different results depending on what was below. Two leaves thick is my standard for the moment. Conversely it does not change the scan very much if I have the leaves upside down.I am sure we will learn a lot of DOs and DONTs in the next few months.
@ Randhir:
It works like this:-
Step 1: Create the collection “Milk” with attributes you are interested in. Remember one for unique sample ID.
Step 2: Scan your samples, adding as much info as you can (maybe just Cow Milk, Goat Milk, and unique ID.
Step 3: Make lab analysis of the attributes per unique sample ID
Step 4: Go back into your sample set and add back the lab values against each sample.
Step 5: Create the models for each attribute, and check that they look OK. Take more samples, and clean bad data as appropriate.
Step 6: Test on fresh samples and compare with lab analysis to confirm that it works.It is NOT enough to take the nutritional values from the labels, manufacturing variance is too great.
You could use label data as a very rough first try, but be sure to junk that data later.
