Note: I am experimenting with exporting Jupyter notebooks into a WordPress ready format. This notebook refers specifically to to the Nature Conservancy Kaggle, for classifying fish species, based only on photographs.
I’ve been messing around with a few things during my time off for the Holidays:
- This one, for the Nature Conservatory, specifically
- For using Convolution Neural Networks, without the headaches
- Jupyter Notebooks
- For presenting data analysis results in Python
- Also experimenting with whether I can port these to WordPress easily
So here’s a quick combination of these things, in the form of a simple guide to using Keras on the Nature Conservatory image recognition Kaggle.
Hopefully it serves as an easy introduction to get up and running with neural networks for this competition.
Example code to start experimenting with the Harris Corner Detection Algorithm on your own, in Matlab. And some of the results I obtained in my own testing.
Among the classic algorithms in Computer Vision is Harris Corner Detection. (For the original paper, from 1988, see here.) The problem it solves: Given any image file, can you find which areas correspond to a corner with a high degree of certainty?
The answer is yes. And the algorithm is elegant. Essentially the steps are:
- Convert your image to a Matrix, storing the pixel values by intensity (converting to B/W makes this easier)
- Find the horizontal and vertical gradients of the image (essentially the derivative of pixel intensities). This will let us know where there are horizontal and vertical edges.
- Scan the image getting groups of pixels for however wide an area you are concerned with, and perform a calculation to determine where the horizontal and vertical edges intersect. (This requires some relatively complex linear algebra, but I’m not focusing on the theory here, just the implementation.)
Recently, I was trying to implement my own version of the Harris Detector in Matlab, and ended up banging my head against the wall for a few hours while figuring out some of the subtler details the hard way.
Here’s the code I came up with, and some examples of the outputs. Grab the code from both gists below, and you can start experimenting on your own.
Displaying Your Results
Here’s what you can expect to see. I’m coloring the corners RED, using circles that grow larger the more likely the area is to hold a corner. So, larger circles –> more obvious corners. (Also note that I’m downsizing my output images slightly, just to make computation faster. )
That’s it. With this code, you can start experimenting with Harris Detectors in about 30 seconds. And hopefully the way I’ve written it is transparent enough to make it obvious what’s going on behind the scenes. Most of the implementations out there are somewhat opaque and hard to understand at a conceptual level. But I’m hoping that my contribution will make this all a little more straightforward to those just gettings started. Enjoy. -t