8
$\begingroup$

I'm searching a good (and compact) book or online tutorial about multivariate pattern analysis in images with machine learning techniques. I took a machine learning course based on the Bishop text book "Pattern Recognition and Machine Learning" from 2006 but I found it difficult and is currently out of date.

Ideally the book would be oriented to practical applications and related to multivariate pattern analysis in images (image processing). The mathematical foundations and proofs are not important. Most important is that it present a variety of different algorithms and techniques are presented (e.g. SVM etc.) in an easy way with some explanations and perhaps implementation details.

Can someone suggest a good book?

What about the the book "Pattern Classification" from R. Duda, P. Hart, and D. Stork?

$\endgroup$
1
  • $\begingroup$ What do you mean when you write that PRML is "out of date"? It's hard to know what to make of this because the question specifically names SVMs, as a topic you want to know about, but SVMs are also covered in PRML (chapter 7). What makes it out of date? What are the more recent concepts that you want to know about that aren't covered? $\endgroup$
    – Sycorax
    Apr 12 at 20:15

2 Answers 2

5
$\begingroup$

The book by Prince, recommended by @seanv507 is indeed an excellent book on the topic (+1). And while it is not really compact, it has very logical structure and even a generous refresher chapter on probability as well as great focus on machine learning within computer vision context.

However, I'd like to recommend another excellent book on the topic (also freely downloadable), which, while having more focus on computer vision per se, IMHO contains enough machine learning material to qualify for an answer. The book that I'm talking about is "Computer Vision: Algorithms and Applications" by Richard Szeliski (Microsoft Research). One of the advantages of this book versus the one by Price is... narrower margins, which allow for larger font size and, thus, better readability. Also, the book by Szeliski is very practical. Since both books share significant content, but have somewhat different focus, in my opinion, they very well complement each other. All this, among other advantages, makes it very easy for me to highly recommend Szeliski's book.

$\endgroup$
4
  • 1
    $\begingroup$ Thank you, I will have a look at the book, but of course I cannot read a lot of books. I think I will read one book from the beginning to the end and from other books only some chapters for new techniques. So I have to decide on one book. $\endgroup$
    – machinery
    Apr 12, 2015 at 20:01
  • $\begingroup$ @user1684118: You're welcome and good luck! $\endgroup$ Apr 12, 2015 at 23:31
  • 1
    $\begingroup$ (+1) Even though this answer is from 2015, it's still valuable today. The second edition of Szeliski's book was published in 2022, and includes expanded sections on machine learning, neural networks/deep learning, as well as new sections on new technologies such as SLAM and VIO. $\endgroup$
    – Sycorax
    Apr 13 at 16:16
  • $\begingroup$ @Sycorax Thank you for your kind words and for the update on the book. $\endgroup$ Apr 13 at 20:55
5
$\begingroup$

I would recommend Computer Vision: Models, Learning, and Inference by Simon Prince the pdf is available (free) to students at the above link. It is exactly aiming at combining ML and image processing

$\endgroup$
1
  • $\begingroup$ Thank you very much. In detail, I have to do multivariate pattern analysis of images. Is this book also ok with this? $\endgroup$
    – machinery
    Apr 12, 2015 at 19:59

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.