Good feature engineering involves two components. The first is an understanding the properties of the task you’re trying to solve and how they might interact with the strengths and limitations of the classifier you’re using. The second is experimental work where you will be testing your expectations and find out what actually works and what … Read more
The easiest solution would be to normalize all of your images, both for training and testing, to have the same resolution. Also the character in each image should be about the same size. It is also a good idea to use greyscale images, so each pixel would give you just one number. Then you could … Read more
Hidden Markov Models are a great place to look, as well as Artificial Neural Networks. Edit: You could take a look at NeuronDotNet, it’s open source and you could poke around the code. Edit 2: You can also take a look at ITK, it’s also open source and implements a lot of these types of … Read more
Here’s a very basic, visual explanation of how a Hough Transform works for detecting lines in an image:
I have been there, and I faced this problem. The ANN was made for fixed feature vector length, and so are many other classifiers such as KNN, SVM, Bayesian, etc. i.e. the input layer should be well defined and not varied, this is a design problem. However, some researchers opt for adding zeros to fill … Read more
Here is a sample result from a small project I did to partition ecg data. My approach was a “switching autoregressive HMM” (google this if you haven’t heard of it) where each datapoint is predicted from the previous datapoint using a Bayesian regression model. I created 81 hidden states: a junk state to capture data … Read more
The first thing that I would do is see what is already out there. Indeed, this specific problem has already been heavily researched. Here is a brief overview of some really simple methods: link. I must respond to another answer, as well. I do research in signal processing and music information retrieval. On the surface, … Read more