PLAYING WITH COLORS

I've been lately thinking on going to the roots of image processing by studying more about the colors.

What properties can be defined for a color?, how do we represent them?, can we compare two colors?, can we find similar colors?... in fact, what do we mean by similar colors?

Colors are usually compared depending on the context: colors for graphic design, colors for textile applications, colors similar to human perception,...

CREATING A MOSAIC

I haven't been working on image processing tools for a long time as I've been quite busy with many other interesting projects ;)

One of them was migrating the old website to Blogger so it will be faster for me to publish new posts.

After I finished it, I decided that I wanted to go back to the basics of image processing: the COLORS.

I wanted to learn more about them, how to represent them, how to compare, how to find "similar" colors... in fact, what do we mean by similar colors?

GESTURE INTERFACES

Last year, I created a couple of small demos to learn more about interactions with webcam streams.

I'm very interested into gesture detection as I believe it will be the next big change in how we interact with our browsers and applications. Soon it will be no required to touch a mouse or a keyboard to execute basic actions.

The idea was to try to capture the frames on real time and perform some manipulations on them to trace the user's head and hands, with the final objective of creating an interactive menu that doesn't require a physical input (mouse/keyboard).

The demos are far from a final stage as I got busy with other tasks in the office (so my free time was suddenly reduced to 0) but they are still interesting to share ;)

-> GESTURE INTERFACE - OPTION MENU

First trial of a menu tracking the user opened/closed fist

-> GESTURE INTERFACE - HEAD TRACKING

Not being happy with the last demo problems with high/low luminosity environments, I decided to try a new head tracking library which does an amazing job normalizing the frames captured by the webcam.
On this demo we are applying a simple reflection effect on the webcam stream and identifying the user head.

INTERACTIVE COOKING BOOK

For this demo, I focused on filtering images captured through the webcam using SAARs clasifiers to identify gestures. It will try to detect swipe gestures to navigate through the book pages.


The demo code is based on the great work of Brandon Nicholls at https://github.com/iambrandonn/WebcamSwiper

I'm still working to make the detection more accurate by adjusting the thresholds applied during the image processing step.

The demo can be accessed from the old blog page at http://angelraposo.appspot.com/demos/recipe_book/

IMAGE COLOR DETECTION

INITIAL FACTS

For this demo, I'm focusing on processing apparel website images, which are usually taken with a fixed color plain background. This will be very important as the current algorithm won't give very good results when the image has some background elements.

The script will try to obtain the item "main" color from the image. We will define "main" color as the dominant color of the pixels composing the item pictured. I.e: a photo of a red t-shirt with a white background should obtain the red color, even if the amount of white is bigger in the image.