1 / 21

Understanding Computer Vision: Image Formats, Filtering Techniques, and Convolution Basics

This guide introduces the fundamentals of computer vision, focusing on image formats, reading and writing images, and various image environments. It explores black and white images as 2D matrices with pixel intensities and color images as 3D matrices represented in RGB. The document covers linear filtering techniques, including modifying pixels based on their neighborhood and using convolution for image processing. Learn the importance of linear methods in integrating information over constant regions, scaling, and detecting changes through Fourier analysis and convolution kernels.

danica
Télécharger la présentation

Understanding Computer Vision: Image Formats, Filtering Techniques, and Convolution Basics

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Computer Vision • Introduction to Image formats, reading and writing images, and image environments • Image filtering

  2. Images • Black and white image is a 2D matrix. • Intensities represented as pixels. • Color images are 3D matrix, RBG.

  3. Linear Filtering • About modifying pixels based on neighborhood. Local methods simplest. • Linear means linear combination of neighbors. Linear methods simplest. • Useful to: • Integrate information over constant regions. • Scale. • Detect changes. • Fourier analysis.

  4. (from Freeman, MIT)

  5. (Freeman)

  6. Convolution • Convolution kernel g, represented as matrix. • it’s associative • Result is:

More Related