Hands-on Morphological Image Processing (SPIE Tutorial Texts in Optical Engineering Vol. TT59) [Paperback]

Edward R. Dougherty (Author), Roberto A. Lotufo (Author)

Book Description

ISBN-10: 081944720X | ISBN-13: 978-0819447203 | Publication Date: July 24, 2003

Morphological image processing, now a standard part of the imaging scientist's toolbox, can be applied to a wide range of industrial applications. Concentrating on applications, this book shows how to analyze a problem and then develop successful algorithms based on the analysis. The book is hands-on in a very real sense: readers can download a demonstration toolbox of techniques and images from the Web so they can process the images according to examples in the text.

Contents

- Preface
- List of Symbols
- Binary Erosion and Dilation
- Binary Opening and Closing
- Morphological Processing of Binary Images
- Hit-or-Miss Transform
- Gray-Scale Morphology
- Morphological Processing of Gray-Scale Images
- Morphological Segmentation Watershed
- Granulometries
- Automatic Design of Morphological Operators
- Index

Product Details

• Paperback: 272 pages
• Publisher: SPIE Publications (July 24, 2003)
• Language: English
• ISBN-10: 081944720X
• ISBN-13: 978-0819447203
• Product Dimensions: 10 x 7.1 x 0.7 inches
• Shipping Weight: 1.4 pounds (View shipping rates and policies)
• Average Customer Review: 4.6 out of 5 stars  See all reviews (5 customer reviews)
• Amazon Best Sellers Rank: #119,415 in Books (See Top 100 in Books)
  • #28 in Books > Professional & Technical > Professional Science > Physics > Optics

More About the Author

Discover books, learn about writers, read author blogs, and more.

Customer Reviews

Most Helpful Customer Reviews

3 of 3 people found the following review helpful:

5.0 out of 5 stars If I could only have one - this would be it, December 24, 2005

By 

J. Sokolowski (Houston, TX USA) - See all my reviews
(REAL NAME)   

This review is from: Hands-on Morphological Image Processing (SPIE Tutorial Texts in Optical Engineering Vol. TT59) (Paperback)

I've read a number of texts on Morphological Image Processing and they have all been quite excellent and very helpful for my work. However, for me, if I could only have one text, this would be it. The reason is the intuitive approach used to explain the nature of the various morphological image transforms for both binary and grey scale imaging combined with a thorough mathmatical foundation. The two combined enabled me to understand what these transforms are all about and how to apply them to my real world problems. By reading and studying the various definitions of the morphological operators, I was able to find at least one perspective for each operator that made sense to me, and, therefore, opened the door to increased understanding and appreciation for the other perspectives. Combine this with the practical Phython-based morphological processing toolkit that supports this book and I think I've found a nearly perfect exposition of this subject. I'd highly recommend this text as the first approach to the subject, to be followed and supplemented downstream by others as needed.

4 of 5 people found the following review helpful:

5.0 out of 5 stars A powerful learning tool for mathematical morphology, April 30, 2004

By 

Michel Kocher (Geneva, Switzerland) - See all my reviews

This review is from: Hands-on Morphological Image Processing (SPIE Tutorial Texts in Optical Engineering Vol. TT59) (Paperback)

The morphological approach to signal and image processing is interesting because it combines the riguor of mathematics with the intuition of the morphological description of the data.

The first books describing the subjects, written by J. Serra were diffcult to read because they were written in a very formal language.

Recently, Pierre Soille wrote a very precise and still understandable book entitled "Morphological Image Analysis" which describes the state of the art methods used in mathematical Morphology. This book illustrates the theoretical algorithms with many industrial applications.

The book "Hands-on Morphological Image Processing" adds another brick to the mathematical morphology wall by providing the first, to my knowledge, powerful learning tool in the field. I recommend this book for two reasons :

First, it precisely describes the basic morphological image processing methods such as erosion, dilation, opening, closing and Hit or Miss transform. The advanced concepts of generalized dynamics, connected filtering as well as segmentation by watershed and hierarchcical segmentation are also covered. It is interseting to note that all these concepts can be applied to 1D, 2D or nD data such as signal image and volume, like MRI scans. The concepts of bounded operators and infinite domain
are also covered. A good intuition is provided about the class of connected filters for binary and numeric images, based on reconstruction algorithms. Finally, I particularly appreciated the section devoted to binary and numeric granulometry. This section leads to the interseting and complex field of tecture segmentation.

Second it offers for free to the student a complete toolbox where all the described methods are implemented. This toolbox, called pymorph, is written in Python and can be downloaded from http://sourceforge.net/projects/pymorph. Furthermore, this book is illustarted by many pedagogical figures that describe the application of the concepts to practical cases. The documentation, in html format is complete and easy to use. The data as well as the algorithms are available in
http://www.dca.fee.unicamp.br/~lotufo/handson.

To conclude, I consider this book and the python project which goes with it as a very valuable pedagogical tool for anybody interested in the field of Mathematical Morphology. I think that that the possibility of computing the figures enclosed in the book by issuing some python or matlab commands help the student to notably increase the depth of his knowledge.

Dr. Michel Kocher
Professor of Image Processing
Geneva Technical University

1 of 1 people found the following review helpful:

4.0 out of 5 stars Expository and practical, May 2, 2006

By 

Andrew Diamond "psoriasis" (San Diego, CA United States) - See all my reviews
(REAL NAME)   

This review is from: Hands-on Morphological Image Processing (SPIE Tutorial Texts in Optical Engineering Vol. TT59) (Paperback)

Great combination of theoretic underpinnings, pithy practical insights, and worked examples with pictures. I can't think of a better introduction to this material (this is the kind of subject that can easily be presented in such a way as to be simultaneously mathematically rigorous and expository and yet not impart any practical feel for the material)
The accompanying downloadable Matlab toolbox is excellent but the library functions don't include source code (for the functions) and it expires in just 30 days unless you buy it (and it's not cheap if you're not a student). Matlab source code is a great way to learn and verify what you've learned. Perhaps 90 days would've been better. The toolbox is more comprehensive and its watershed algorithm seems to be better than what's in the morphological component of Matlab's Image Processing Toolbox.
I would like to see more on the gray scale morphological techniques for some of the latter topics and some more on pattern recognition/machine vision topics but I guess that isn't central to the topic. There does appear to be a few errors/typos but nothing significant.