Object recognition. Fundamentals and case studies
This book of 350 pages has been written to provide a set of algorithms and paradigms for the purpose of designing automatic object recognition systems. The book is made of three parts covering several aspects of object recognition. The first part of the book starts by providing the reader with a general definition of computer vision, based on the Marr's theory. One can regret that more recent theories of computer vision are not discussed at all. The remaining of this first part is devoted to an overview of acquisitions systems and more particularly to stereo vision (70 pages). A lot of details are not very useful for the reader interested in computer vision. The second part presents methods allowing to recognise 3D objects from object models and databases. In this second part, the authors first study how it is possible to create 3D models from multiple range images. The emphasize is put on the registration stage (58 pages), sometimes required to merge partial models. The second part of the chapter, which is the one directly related to object recognition, provides information for both the representation and matching stage. This chapter is nothing more than a short survey of most common methods. There are a lot of -- often old -- references without any explanation or discussions. The third and last part of the book proposes three case studies on model based object recognition. These case studies are: optical character recognition, recognition of 2D objects and 3D free-form objects. The choice for these cases as well as the proposed solutions are not really satisfactory. Conclusions: Object recognition is a very complex problem. This book only brings a very partial view on this wide subject. On one hand, several chapters are out of the scope of the subject (stereo-vision, 3D registration, etc.). On the other hand, the only chapter really dealing with object recognition is very short (35 pages) and only proposes a survey. A lot of other information coming from psychology, pattern recognition, biological systems or artificial intelligence are missing.
- Rotational projection statistics for 3D local surface description and object recognition
- Integrating graphics and vision for object recognition
- Object detection and recognition in digital images: theory and practice
- scientific article; zbMATH DE number 2134792 (Why is no real title available?)
- Studies of human vision recognition: some improvements
- An introduction to object recognition. Selected algorithms for a wide variety of applications
- scientific article; zbMATH DE number 1094953 (Why is no real title available?)
- Rate-distortion theory applied to automatic object recognition
- Connectionist object recognition: Methods and methodologies
- scientific article; zbMATH DE number 1878346 (Why is no real title available?)
- scientific article; zbMATH DE number 1402210 (Why is no real title available?)
- Concentric ellipse fitting with bias correction and specialized geometric-based clustering approach
- Fitting concentric elliptical shapes under general model
This page was built for publication: Object recognition. Fundamentals and case studies
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2770564)
