my current "scheme" for creating new passwords is to simply write a long, unique passphrase with the idea that I will only remember it for the short time needed to log in after registration.
If I need to log in sometime in the future, I simply reset the password.
Try and do it cheaply as well. The places you end up staying as a result puts you on an interesting path where you can meet some very interesting folks.
I try and do a 1-3 month long snowboarding trip each year. Buy a season pass, find a room in a hostel and hang out with the other seasonairres. The total cost is only slightly more than a 1-2 week holiday in a hotel. I've meet some awesome, crazy, fun, random and right-down good folks from all around the world.
The imagination gets fired and after some time, I actually really look forward to coming back home and working on something.
(I'm a little worried about posting that on HN since it's unoptimized and will probably crash.)
I'm currently working on skin detection & exclusion during the color detection phase and am looking at using basic machine learning techniques. The key challenge I'm facing is differences in skin tones.
> I'm currently working on skin detection & exclusion during the color detection phase and am looking at using basic machine learning techniques. The key challenge I'm facing is differences in skin tones.
Try looking at the chromatic colour rather than the RGB values. You can get extremely far with just this, most skin colours fall into one of two peaks [0], no machine learning needed.
Once you've got this, edge detection & a few other bits should give you pretty reliable skin blocks. I've used it a few times before. Here's a presentation I did some years ago that I apparently still have on my desktop: http://files.figshare.com/1409002/1.pdf [1]
EDIT - I'm sure there are many good approaches for this, and many fancy ones. This is very simple and was researched/written purely for fun in a couple of weeks.
EDIT 2 - The final slide shows the more interesting part, where you use edge detectors to guide your estimation of what is inside or outside a shape. That plus an adaptive threshold (designed to stop if the number of pixels included jumped rapidly) got some good results, but I've not got the code any more.
awesome stuff :D Thanks for this. Will definitely look into some of that in more detail.
Another tricky part of skin detection is false positives. ie, what if the actual product is that color?
Some things I've noticed and will be taking into account are:
Skin areas tend to clump around the same locations in photos. The product is usually the focus and skin is near the edges.
Product types also tend to share similar photo layouts.
So with that, skin color in those zones score higher.
> awesome stuff :D Thanks for this. Will definitely look into some of that in more detail.
No worries, hope it helps, it was just a quick project back in the day at uni that ended up working a lot better than I expected.
Give me a shout if you want any work done on it (my email address is in my profile).
> Some things I've noticed and will be taking into account are: Skin areas tend to clump around the same locations in photos. The product is usually the focus and skin is near the edges. Product types also tend to share similar photo layouts. So with that, skin color in those zones score higher.
This kind of thing will really help you, small bits of knowledge about the specifics drastically simplify the problem. For example, you can estimate the skin tone by roughly segmenting the image into possible skin/not skin with the approach above, then look at segments which are more likely to be skin because of their positioning you can narrow your accepted parameters and hopefully help distinguish between the two.
Identification of unusual edges/shapes can help too, to classify regions as skin/not skin.
Beyond that, starting to look at estimations of pose to help guess the underlying shape (since you know it's on humans you can make a lot of assumptions).
Also, since you're detecting colours, mistaking very similarly coloured skin as the product wouldn't change your results much :)
Wow, looks awesome so far. At the moment we aren't dealing with skin tones. Mostly it isn't a problem but there are some cases (such as jewellery or swimwear) where we have to use humans
Does anybody but the establishment really prefer such a system though? Setting aside time in my evening itinerary for queueing is not my idea of ideal.
Probably only a matter of time until a side-business of people who are willing to wait in lines for you emerges.
As a customer it can definitely be annoying to experience at times. My tolerance seems to vary depending on the wait times and food expectations.
A perceived upshot is that the restaurant must put an emphasis on quality at reasonable prices, otherwise they won't draw those crowds and I'm definitely not going to wait for a crappy meal.
However, the "no reservation" method itself seems to help draw crowds too. Kind of like the lines outside a night club seem to draw people. Throw in a bit of edgy branding with some cool marketing and it pulls well - having an "image" works.
Queuing is a bit of a cultural thing/expectation over here. Having someone cut in line can be a huge no no.
If someone bought their way into the queue, I could very well see it causing some highly vocal responses.
But I'm sure there are people out there trying it out.
Oh wow, I'm actually trying to make that decision right now too. Thanks for posting this.
I've been building something in my spare time and between freelance gigs. It's at a good working prototype stage. I just want to spend a solid month polishing, plugging in minimally required data, release it and see what happens from there.
At the same time, I've just been offered a new contract which will put my project on the slow track for a good half year but it's money coming in.
Being able to focus on something that I'm interested in is amazing. My creativity flows and I see results occur at a pace that keeps motivated even more.
Yet, I don't know what decision to make - Financially sound status quo or happy pipe-dream.
but... I'm reading everyone's comments with great interest.
I'm slowly building something similar in my spare time. It's a multi-color search engine for street wear (and perhaps other stuff)
http://www.inthatstyle.com/