Algorithms for Image Processing and Computer Vision
A cookbook of the hottest new algorithms and cutting-edge techniques in image processing and computer vision
This amazing book/CD package puts the power of all the hottest new image processing techniques and algorithms in your hands. Based on J. R. Parker's exhaustive survey of Internet newsgroups worldwide, Algorithms for Image Processing and Computer Vision answers the most frequently asked questions with practical solutions.
Parker uses dozens of real-life examples taken from fields such as robotics, space exploration, forensic analysis, cartography, and medical diagnostics, to clearly describe the latest techniques for morphing, advanced edge detection, wavelets, texture classification, image restoration, symbol recognition, and genetic algorithms, to name just a few. And, best of all, he implements each method covered in C and provides all the source code on the CD.
For the first time, you're rescued from the hours of mind-numbing mathematical calculations it would ordinarily take to program these state-of-the-art image processing capabilities into software. At last, nonmathematicians get all the shortcuts they need for sophisticated image recognition and processing applications.
On the CD-ROM you'll find:
* Complete code for examples in the book
* A gallery of images illustrating the results of advanced techniques
* A free GNU compiler that lets you run source code on any platform
* A system for restoring damaged or blurred images
* A genetic algorithms package
Why Read This Book
You should read this book if you want a hands‑on, recipe‑style collection of image‑processing and vision algorithms you can apply quickly to real problems. It gives pragmatic descriptions, worked examples from robotics/medical/forensics, and algorithmic recipes (with code on the companion media) that make prototyping and experimenting fast.
Who Will Benefit
Practicing engineers, researchers, and graduate students who implement image‑processing or vision algorithms and need practical, ready‑to‑use techniques rather than deep theoretical derivations.
Level: Intermediate — Prerequisites: Basic linear algebra and probability, familiarity with digital images (sampling, pixels), and comfort programming in C or MATLAB to adapt example code.
Key Takeaways
- Implement classical and advanced edge detectors (e.g., Canny, Marr–Hildreth) and tune them for real images.
- Apply morphological operators and region‑based methods for shape analysis and binary image processing.
- Use multiresolution and wavelet techniques for denoising, compression, and feature extraction.
- Design and implement texture analysis and classification approaches (e.g., Gabor filters, co‑occurrence matrices).
- Build practical segmentation and restoration pipelines for common artifacts and degradations.
- Integrate heuristic and optimization methods (including genetic algorithms) into vision tasks such as matching and recognition.
Topics Covered
- Introduction and practical considerations
- Image enhancement and restoration
- Edge detection and feature extraction
- Segmentation and region processing
- Mathematical morphology and shape operators
- Texture analysis and classification
- Multiresolution methods and wavelets
- Image registration and matching
- Pattern recognition and symbol recognition
- Optimization and evolutionary methods (genetic algorithms)
- Motion analysis and tracking (practical approaches)
- Implementation notes, examples, and code appendices
Languages, Platforms & Tools
How It Compares
More of a hands‑on 'cookbook' than Gonzalez & Woods' Digital Image Processing (which is more theory and pedagogy); less modern and less comprehensive on vision research topics than Szeliski's Computer Vision but more implementation‑oriented.
