Computer Vision
CNNs, Detection, Segmentation and Vision Transformers
About this guide
A concise exam companion for computer vision. It covers image representation and colour, preprocessing and augmentation, classical features from edges to SIFT-style descriptors, convolution and the frequency domain, convolutional neural networks, classification architectures, transfer learning, object detection, segmentation and vision transformers, with evaluation and benchmarking. Every chapter ends with a worked example carried through step by step, so you can check the reasoning yourself.
Inside the guide
- Representation and colour
- Preprocessing and augmentation
- Classical features from edges to SIFT-style descriptors
- Convolution and the frequency domain
- Convolutional neural networks
- Classification architectures
- Transfer learning
- Object detection
- Segmentation and vision transformers
- With evaluation and benchmarking
Questions students ask
What does Computer Vision cover?
It covers image representation and colour, preprocessing and augmentation, classical features from edges to SIFT-style descriptors, convolution and the frequency domain, convolutional neural networks, classification architectures, transfer learning, object detection, segmentation and vision transformers, with evaluation and benchmarking.
Who is Computer Vision for?
It is written for university students revising computer vision, and for lecturers and librarians choosing a clear, exam-focused reading-list text.
What format does it come in?
Kindle ebook and paperback on Amazon.
Can I read part of it for free?
Full Marks Press offers a free sample chapter at fullmarkspress.com/free, and the full guide is free to read with Kindle Unlimited.