Image processing can be used within a wide field of applications, including adjusting images, extracting image attributes, and creating subsets of images to demonstrate various aspects of a given image. So far, we have utilized various image processing aspects and techniques. Now it is time to begin to incorporate multiple of these acquired techniques into a fully applied task!
Create and filter kernels over an image.
Understand the key differences between different kernels.
Using multiple libraries to develop and use image processing applications.
Complete an image processing task counting objects determined within an image.
Access to a computer and large screen (if you want share with others)
A Google account to access Google Colab
Filter - A mathematical operation that is applied to an image using a kernel to alter an image’s pixel values in a specific fashion.
Kernel - A small (smaller than the input image size) matrix of numbers used to filter an image. The kernels are applied to an image via a mathematical calculation, which is commonly a convolution.
Convolution - The most common way that filters are applied to an image. To filter an image, the filter kernel is slid over an image and calculates the weighted sum of all the pixels under the kernel. This sum correlates to the neighborhood’s pixel value in the output image. Depending on the kernel applied to the image, the resulting output image will display a visible effect from the filtered kernel.
Understanding the variety of techniques that are at your disposal, when preparing data for processing, allows you to easily create more advanced and efficient machine learning models. Models with thoughtfully prepared data can perform a wider array of tasks and complete those tasks more efficiently.
In this activity you will be performing operations that will help strengthen your understanding of image filtering for use in machine learning applications. We will learn about how machine learning models filter images using different math operations of "kernels" and how these kernels are applied to images using convolutions, and how these convolutions and kernels work together to process an image and help you better understand which kernel algorithms to use for the specific task you are trying to accomplish. Understanding how convolution operations on kernels and input images function will allow you to choose the best combination for specific machine learning objectives.
Read through the Simple Image Processing Activity - Activity Guide overview.
Run the Image Filtering - Colab Notebook along with the first portion of the Simple Image Processing Activity - Activity Guide.
Create a new Colab Notebook and work through the second portion of the Simple Image Processing Activity - Activity Guide to create your own image processing code!