Machine Learning Projects for Mobile Applications

Finding features from an image

Let's take a look at an image of the letter X. When we feed a new image into the system, the CNN doesn't know whether the feature will match or not. Consequently, it will try to match the feature pattern everywhere across the image. This is how we build a filter:

The math logic we apply here is called convolution. To calculate the match of a feature to the portion of the image, multiply each pixel value of the feature by the value of the corresponding pixel in the image. To come to one final value, add together all of the values and divide them by the total number of pixels:

 

For example, if both pixels are ...