Practical Computer Vision with SimpleCV

Chapter 4. Pixels and Images

The previous chapters have provided a broad overview of working with the SimpleCV framework, including how to capture images and display them. Now it is time to start diving into the full breadth of the framework, beginning with a deeper look at images, color, drawing, and an introduction to feature detection. This chapter will drill down to the level of working with individual pixels, and then move up to the higher level of basic image manipulation. Not surprisingly, images are the central object of any vision system. They contain all of the raw material that is then later segmented, extracted, processed, and analyzed. In order to understand how to extract information from images, it is first important to understand the components of a computerized image. In particular, this chapter emphasizes:

• Working with pixels, which are the basic building blocks of images

• Scaling and cropping images to get them to a manageable size

• Rotating and warping images to fit them into their final destination

• Morphing images to accentuate features and reduce noise

Pixels

Pixels are the basic building blocks of a digital image. A pixel is what we call the color or light values that occupy a specific place in an image. Think of an image as a big grid, with each square in the grid containing one color or pixel. This grid is sometimes called a bitmap. An image with a resolution of 1024×768 is a grid with 1,024 columns and 768 rows, which therefore contains 1,024 × 768 = 786,432 pixels. ...