The best computer vision books

1 authors have picked their favorite books about computer vision and why they recommend each book.

Soon, you will be able to filter by genre, age group, and more. Sign up here to follow our story as we build a better way to explore books.

Shepherd is reader supported. When you buy through links on our website, we may earn an affiliate commission (learn more).

Multiple View Geometry in Computer Vision

By Richard Hartley, Andrew Zisserman,

Book cover of Multiple View Geometry in Computer Vision

Adding perspective puzzled artists in the fourteenth century; analysing perspective is integral to applied computer vision. You might have seen Hawkeye in action: the principles by which it works are explained superbly within this book. It was the first of its kind to set this analysis in a lucid and compelling format. Richard and Andrew’s text will be on researchers’ bookshelves for many years for its bedrock description of how we analyse three-dimensional scenes.


Who am I?

It’s been fantastic to work in computer vision, especially when it is used to build biometric systems. I and my 80 odd PhD students have pioneered systems that recognise people by the way they walk, by their ears, and many other new things too. To build the systems, we needed computer vision techniques and architectures, both of which work with complex real-world imagery. That’s what computer vision gives you: a capability to ‘see’ using a computer. I think we can still go a lot further: to give blind people sight, to enable better invasive surgery, to autonomise more of our industrial society, and to give us capabilities we never knew we’d have.

I wrote...

Feature Extraction and Image Processing for Computer Vision

By Mark S. Nixon,

Book cover of Feature Extraction and Image Processing for Computer Vision

What is my book about?

Computer Vision now helps society in many ways: we use face recognition on our phones and we can identify plants too (though we sometimes get fined when our number/ license plate goes past a camera too quickly). The advance has been due to faster computers, cheaper memory, better sensors, and better techniques. Back in 1997 I and Alberto found that no book covered feature extraction in-depth, so we rectified that. Our book is pretty much the only one describing computer vision via techniques for finding and describing shapes and structure. Many of these now find use in the systems applied in medicine and in industry – and in current deep learning-based systems. I’ll next be listing some of the great books that have moved this fascinating field forwards.

Computer Vision

By Simon J. D. Prince,

Book cover of Computer Vision: Models, Learning, and Inference

This fine book is about learning the relationships between what is seen in an image, and what is known about the world. It’s a counterpart to our book on feature extraction and it shows you what can be achieved with the features. It’s not for those who shy from maths, as is the case for all of the books here. So that you can build the techniques, Simon’s book also includes a wide variety of algorithms to help you on your way.


Who am I?

It’s been fantastic to work in computer vision, especially when it is used to build biometric systems. I and my 80 odd PhD students have pioneered systems that recognise people by the way they walk, by their ears, and many other new things too. To build the systems, we needed computer vision techniques and architectures, both of which work with complex real-world imagery. That’s what computer vision gives you: a capability to ‘see’ using a computer. I think we can still go a lot further: to give blind people sight, to enable better invasive surgery, to autonomise more of our industrial society, and to give us capabilities we never knew we’d have.

I wrote...

Feature Extraction and Image Processing for Computer Vision

By Mark S. Nixon,

Book cover of Feature Extraction and Image Processing for Computer Vision

What is my book about?

Computer Vision now helps society in many ways: we use face recognition on our phones and we can identify plants too (though we sometimes get fined when our number/ license plate goes past a camera too quickly). The advance has been due to faster computers, cheaper memory, better sensors, and better techniques. Back in 1997 I and Alberto found that no book covered feature extraction in-depth, so we rectified that. Our book is pretty much the only one describing computer vision via techniques for finding and describing shapes and structure. Many of these now find use in the systems applied in medicine and in industry – and in current deep learning-based systems. I’ll next be listing some of the great books that have moved this fascinating field forwards.

Computer Vision

By Richard Szeliski,

Book cover of Computer Vision: Algorithms and Applications

Richard’s authoritative leading textbook excellently describes the whole field of computer vision. It starts with the sensor, moves to image formation followed by feature extraction and grouping, and then by vision analysis. It’s pragmatic too, with excellent descriptions of applications. And there is a ton of support material. This is a mega textbook describing the whole field of computer vision.


Who am I?

It’s been fantastic to work in computer vision, especially when it is used to build biometric systems. I and my 80 odd PhD students have pioneered systems that recognise people by the way they walk, by their ears, and many other new things too. To build the systems, we needed computer vision techniques and architectures, both of which work with complex real-world imagery. That’s what computer vision gives you: a capability to ‘see’ using a computer. I think we can still go a lot further: to give blind people sight, to enable better invasive surgery, to autonomise more of our industrial society, and to give us capabilities we never knew we’d have.

I wrote...

Feature Extraction and Image Processing for Computer Vision

By Mark S. Nixon,

Book cover of Feature Extraction and Image Processing for Computer Vision

What is my book about?

Computer Vision now helps society in many ways: we use face recognition on our phones and we can identify plants too (though we sometimes get fined when our number/ license plate goes past a camera too quickly). The advance has been due to faster computers, cheaper memory, better sensors, and better techniques. Back in 1997 I and Alberto found that no book covered feature extraction in-depth, so we rectified that. Our book is pretty much the only one describing computer vision via techniques for finding and describing shapes and structure. Many of these now find use in the systems applied in medicine and in industry – and in current deep learning-based systems. I’ll next be listing some of the great books that have moved this fascinating field forwards.

Advanced Methods and Deep Learning in Computer Vision

By E.R. Davies (editor), Matthew Turk (editor),

Book cover of Advanced Methods and Deep Learning in Computer Vision

The advances of deep learning have been awesome, and fast. It’s been hard for the textbooks to keep up, so it’s good to include one that describes the advances and state of art very well. It seems appropriate that it’s edited by two leading researchers who are Roy – who described computer vision systems implementations in a long series of excellent books – and Matt, whose work on face recognition revolutionised and transformed the progress of face recognition in the 1990s. This book gives you an image of where we are now in computer vision, and where we are going. 


Who am I?

It’s been fantastic to work in computer vision, especially when it is used to build biometric systems. I and my 80 odd PhD students have pioneered systems that recognise people by the way they walk, by their ears, and many other new things too. To build the systems, we needed computer vision techniques and architectures, both of which work with complex real-world imagery. That’s what computer vision gives you: a capability to ‘see’ using a computer. I think we can still go a lot further: to give blind people sight, to enable better invasive surgery, to autonomise more of our industrial society, and to give us capabilities we never knew we’d have.

I wrote...

Feature Extraction and Image Processing for Computer Vision

By Mark S. Nixon,

Book cover of Feature Extraction and Image Processing for Computer Vision

What is my book about?

Computer Vision now helps society in many ways: we use face recognition on our phones and we can identify plants too (though we sometimes get fined when our number/ license plate goes past a camera too quickly). The advance has been due to faster computers, cheaper memory, better sensors, and better techniques. Back in 1997 I and Alberto found that no book covered feature extraction in-depth, so we rectified that. Our book is pretty much the only one describing computer vision via techniques for finding and describing shapes and structure. Many of these now find use in the systems applied in medicine and in industry – and in current deep learning-based systems. I’ll next be listing some of the great books that have moved this fascinating field forwards.

Vision

By David Marr,

Book cover of Vision: A Computational Investigation into the Human Representation and Processing of Visual Information

David Marr shaped the field of computer vision in its early days. His seminal book laid the structure for interpreting images and one which is still largely followed. He popularised notions of the primal sketch and his work on edge detection led to one of the most sophisticated approaches. His work and influence continue to endure despite his early death: we missed and miss him a lot.


Who am I?

It’s been fantastic to work in computer vision, especially when it is used to build biometric systems. I and my 80 odd PhD students have pioneered systems that recognise people by the way they walk, by their ears, and many other new things too. To build the systems, we needed computer vision techniques and architectures, both of which work with complex real-world imagery. That’s what computer vision gives you: a capability to ‘see’ using a computer. I think we can still go a lot further: to give blind people sight, to enable better invasive surgery, to autonomise more of our industrial society, and to give us capabilities we never knew we’d have.

I wrote...

Feature Extraction and Image Processing for Computer Vision

By Mark S. Nixon,

Book cover of Feature Extraction and Image Processing for Computer Vision

What is my book about?

Computer Vision now helps society in many ways: we use face recognition on our phones and we can identify plants too (though we sometimes get fined when our number/ license plate goes past a camera too quickly). The advance has been due to faster computers, cheaper memory, better sensors, and better techniques. Back in 1997 I and Alberto found that no book covered feature extraction in-depth, so we rectified that. Our book is pretty much the only one describing computer vision via techniques for finding and describing shapes and structure. Many of these now find use in the systems applied in medicine and in industry – and in current deep learning-based systems. I’ll next be listing some of the great books that have moved this fascinating field forwards.

Kill Decision

By Daniel Suarez,

Book cover of Kill Decision

When Kill Decision came out, I sent an email to all my Department of Defense colleagues saying: finally, a book that gets swarms, drones, computer vision, and lethal autonomous weapons right! The book shows behavioral robotics can duplicate insect intelligence to create simple, but relentlessly effective, drones. The inexpensive individual drones are limited in intelligence but a greater, more adaptive intelligence emerges from the swarm. It’s on par with a Michael Crichton technothriller with lots of action (plus romance), making it an easy read.  


Who am I?

I have loved science fiction ever since I was a kid and read all my Dad’s ancient issues of Analog Science Fiction and Fact from the 1940s. The first book I can remember reading was The Green Hills of Earth anthology by Robert Heinlein. Fast forward to the 1990s, when, as a new professor of computer science, I began adding sci-fi short stories and movies as extra credit for my AI and robotics courses. Later as a Faculty Fellow for Innovation in High-Impact Learning Experiences at Texas A&M, I created the Robotics Through Science Fiction book series as a companion to my textbook, Introduction to AI Robotics


I wrote...

Robotics Through Science Fiction: Artificial Intelligence Explained Through Six Classic Robot Short Stories

By Robin R. Murphy,

Book cover of Robotics Through Science Fiction: Artificial Intelligence Explained Through Six Classic Robot Short Stories

What is my book about?

Robotics Through Science Fiction explains how robots actually work in a way that anyone, not just a scientist, can relate to. The book is a collection of six famous sci-fi stories, each of which illustrates some important aspects of real-world robotics, such as teleoperation, organization of intelligence,  machine learning, and human-robot interaction. Each story has a prologue that introduces the concept illustrated in the story and what to watch for while reading. After the story, there is a discussion of what was accurate or wrong, and why. It was originally intended as a fun companion to the college-level textbook, Introduction to AI Robotics, but became a standalone book for teaching anyone how robot intelligence is programmed. 

Skyward

By Brandon Sanderson,

Book cover of Skyward

Brandon Sanderson is one of the most prolific writers working today. He’s also my single biggest source of inspiration as an author. He’s written everything from massive, tome-sized fantasy epics for adults to middle grade action-adventure.

With Skyward, a YA space opera set in the far future on an alien planet, Sanderson is having a total blast. You truly cannot turn the pages fast enough. Our heroine, Spensa, wants nothing more than to be a pilot, like her disgraced father (who was branded a coward after inexplicably turning on his flight mates). You see, for Spensa, getting enrolled into flight school and becoming a pilot isn’t just about joining the war against the Krell—it’s about clearing her father’s name and fighting for her family’s legacy.

The book tackles many themes that young readers will resonate with. But, more importantly, the action’s relentless and it’s a quick, satisfying series opener.


Who am I?

I’ve been a creative writer for over a decade, and I always tell people that writers are readers first. As such, I’ve been in love with both young adult and sci-fi books since I was a kid. Fittingly, my debut book is science fiction for young readers. I believe this sub-genre has so much to offer. The really good, memorable books use high-concept ideas or conflict as a vehicle for exploring compelling, relatable themes. I have always believed that’s the best way to approach writing sci-fi. And, with The Memory Index, I took this approach to heart.


I wrote...

The Memory Index

By Julian R. Vaca,

Book cover of The Memory Index

What is my book about?

The Memory Index is a 1980s-set sci-fi mystery. The world is ravaged by Memory Killer—an enigmatic plague that’s created the need for artificial recall. A billion-dollar corporation claims to have created groundbreaking tech that will mark a significant victory in mankind’s battle with memory loss. 500 students are randomly selected to trial the tech at a boarding school. But when Freya (a seventeen-year-old orphan who grapples with inexplicable half-memories) arrives on campus, she and her new friends begin to notice that students are disappearing in the night. What Freya discovers in the woods behind campus will challenge everything she’s ever been told about memory loss.

New book lists related to computer vision

All book lists related to computer vision

Bookshelves related to computer vision