Neural Networks and Image Processing to Shoot Caterpillars w/ Lasers

I am somewhat of an amateur farmer and I have a precious cherry tomato plant growing in a pot. Lately, to my chagrin, I have discovered that my precious plant has been the victim of a scheme perpetrated by the evil Manduca Quinquemaculata - also known as the Tomato Hornworm (http://insects.tamu.edu/images/insects/common/images/cd-43-c-txt/cimg308.html).

While smashing the last worm I saw, I thought to myself, if I were to use a webcam connected to my computer with a program running, would it be possible to use some kind of an application to monitor my precious plant? These pests are supremely camouflaged and very difficult for my naive eyes to detect.

I've seen research using artificial neural networks (ANNs) for all sorts of things such as recognizing people's faces, etc., and so maybe it would be possible to locate the pest with an ANN.

I have several questions though that I would like some suggestions though.

1) Is there a ranking of the different ANNs in terms of how good they are at classifying? Are multilayer perceptrons known to be better than Hopfields? Or is this a question to which the answer is unknown?

2) Why do there exist several different activation functions that can be used in ANNs? Sigmoids, hyperbolic tangents, step functions, etc. How would one know which function to choose?

3) If I had an image of a plant w/ a worm on one of the branches, I think that I could train a neural network to look for branches that are thin, get fat for a short period, and then get thin again. I have a problem though with branches crossing all over the place. Is there a preprocessing step that could be applied on an image to distinguish between foreground and background el开发者_Python百科ements? I would want to isolate individual branches to run through the network one at a time. Is there some kind of nice transformation algorithm?

Any good pointers on pattern recognition and image processing such as books or articles would be much appreciated too.

Sincerely, mj

Tomato Hornworms were harmed during the writing of this email.

---

A good rule of thumb for machine learning is: better features beat better algorithms. I.e if you feed the raw image pixels directly into your classifier, the results will be poor, no matter what learning algorithm you use. If you preprocess the image and extract features that are highly correlated with "caterpillar presence", then most algorithms will do a decent job.

So don't focus on the network topology, start with the computer vision task.

---

Do these little suckers move around regularly? If so, and if the plant is quite static (meaning no wind or other forces that make it move), then a simple filter to find movement could be sufficient. That would bypass the need of any learning algorithm, which are often quite difficult to train and implement.