Page 22 -

Preface xx

TABLE 1: Dependencies between chapters: It will be difficult to read a chapter if you
don’t have a good grasp of the material in the chapters it “requires.” If you have not read
the chapters labeled “helpful,” you might need to look up one or two things.
Part Chapter Requires Helpful
I 1: Geometric Camera Models
2: Light and Shading
3: Color 2
II 4: Linear Filters
5: Local Image Features 4
6: Texture 5, 4 2
III 7: Stereopsis 1 22
8: Structure from Motion 1, 7 22
IV 9: Segmentation by Clustering 2, 3, 4, 5, 6, 22
10: Grouping and Model Fitting 9
11: Tracking 2, 5, 22
V 12: Registration 1 14
13: Smooth Surfaces and Their Outlines 1
14: Range Data 12
15: Learning to Classify 22
16: Classifying Images 15, 5
17: Detecting Objects in Images 16, 15, 5
18: Topics in Object Recognition 17, 16, 15, 5
VI 19: Image-Based Modeling and Rendering 1, 2, 7, 8
20: Looking at People 17, 16, 15, 11, 5
21: Image Search and Retrieval 17, 16, 15, 11, 5
VII 22: Optimization Techniques

Generally, we have tried to reduce the interdependence between chapters, so
that readers interested in particular topics can avoid wading through the whole
book. It is not possible to make each chapter entirely self-contained, however, and
Table 1 indicates the dependencies between chapters.

We have tried to make the index comprehensive, so that if you encounter a new
term, you are likely to find it in the book by looking it up in the index. Computer
vision is now fortunate in having a rich range of intellectual resources. Software
and datasets are widely shared, and we have given pointers to useful datasets and
software in relevant chapters; you can also look in the index, under “software” and
under “datasets,” or under the general topic.
We have tried to make the bibliography comprehensive, without being over-
whelming. However, we have not been able to give complete bibliographic references
for any topic, because the literature is so large.

What Is Not in this Book
The computer vision literature is vast, and it was not easy to produce a book about
computer vision that could be lifted by ordinary mortals. To do so, we had to cut
material, ignore topics, and so on.