Computer vision and the machine learning workflow
Computer vision applications with machine learning have a common basic structure. This structure is divided into different steps:
- Pre-process
- Segmentation
- Feature extraction
- Classification result
- Post-process
These are common in almost all computer vision applications, while others are omitted. In the following diagram, you can see the different steps that are involved:
Almost all computer vision applications start with a Pre-process applied to the input image, which consists of the removal of light and noise, filtering, blurring, and so on. After applying all pre-processing required to the input image, the second step is Segmentation. In this step, we have to extract the regions of interest in the image and isolate each one as a unique object of interest. For example, in a face detection system, we have to separate the faces from the rest of the parts in the scene. After detecting the objects inside the image, we continue to the next step. Here...
