A Computational Framework for Segmentation and Grouping Review

Average Reviews:

(More customer reviews)This book covers the essential parts of the Tensor Voting framework, describes some of its applications, and compares it with other methodologies. If you want to implement this new approach, however, you're left alone with many details that are not explained, like the construction of the voting fields (especially in the 3D case) and how to choose their parameters. Another thing that annoyed me is that the book is just a fusion of the PhD theses of the two co-authors Mi-Suen Lee and Chi-Keung Tang. Almost all of its text was simply copied from the other documents, thereby introducing several errata and inconsistencies, since some passages are hard to understand without the original accompanying figures. Some of the given equations are erroneous, which can be quite misleading, and many references to other literature are specified with an incorrect number.
Although you won't find a lot of information about the Tensor Voting framework in general and this is the only book covering the topic, I wouldn't recommend buying it. It's not worth its price. You'll be better off getting the original papers -- for free!

Click Here to see more reviews about: A Computational Framework for Segmentation and Grouping

This book represents a summary of the research we have been conducting since the early 1990s, and describes a conceptual framework which addresses some current shortcomings, and proposes a unified approach for a broad class of problems. While the framework is defined, our research continues, and some of the elements presented here will no doubt evolve in the coming years.It is organized in eight chapters. In the Introduction chapter, we present the definition of the problems, and give an overview of the proposed approach and its implementation. In particular, we illustrate the limitations of the 2.5D sketch, and motivate the use of a representation in terms of layers instead.In chapter 2, we review some of the relevant research in the literature. The discussion focuses on general computational approaches for early vision, and individual methods are only cited as references. Chapter 3 is the fundamental chapter, as it presents the elements of our salient feature inference engine, and their interaction. It introduced tensors as a way to represent information, tensor fields as a way to encode both constraints and results, and tensor voting as the communication scheme. Chapter 4 describes the feature extraction steps, given the computations performed by the engine described earlier. In chapter 5, we apply the generic framework to the inference of regions, curves, and junctions in 2-D. The input may take the form of 2-D points, with or without orientation. We illustrate the approach on a number of examples, both basic and advanced. In chapter 6, we apply the framework to the inference of surfaces, curves and junctions in 3-D. Here, the input consists of a set of 3-D points, with or without as associated normal or tangent direction. We show a number of illustrative examples, and also point to some applications of the approach. In chapter 7, we use our framework to tackle 3 early vision problems, shape from shading, stereo matching, and optical flow computation. In chapter 8, we conclude this book with a few remarks, and discuss future research directions.We include 3 appendices, one on Tensor Calculus, one dealing with proofs and details of the Feature Extraction process, and one dealing with the companion software packages.