Natural Object Recognition presents a totally new approach to the automation of scene understanding. Rather than attempting to construct highly specialized algorithms for recognizing physical objects, as is customary in modern computer vision research, the application and subsequent evaluation of large numbers of relatively straightforward image processing routines is used to recognize natural features such as trees, bushes, and rocks. The use of contextual information is the key to simplifying the problem to the extent that well understood algorithms give reliable results in ground-level, outdoor scenes.

Automatie object recognition is a multidisciplinary research area using con cepts and tools from mathematics, computing, optics, psychology, pattern recognition, artificial intelligence and various other disciplines. The purpose of this research is to provide a set of coherent paradigms and algorithms for the purpose of designing systems that will ultimately emulate the functions performed by the Human Visual System (HVS). Hence, such systems should have the ability to recognise objects in two or three dimensions independently of their positions, orientations or scales in the image. The HVS is employed for tens of thousands of recognition events each day, ranging from navigation (through the recognition of landmarks or signs), right through to communication (through the recognition of characters or people themselves). Hence, the motivations behind the construction of recognition systems, which have the ability to function in the real world, is unquestionable and would serve industrial (e.g. quality control), military (e.g. automatie target recognition) and community needs (e.g. aiding the visually impaired). Scope, Content and Organisation of this Book This book provides a comprehensive, yet readable foundation to the field of object recognition from which research may be initiated or guided. It repre sents the culmination of research topics that I have either covered personally or in conjunction with my PhD students. These areas include image acqui sition, 3-D object reconstruction, object modelling, and the matching of ob jects, all of which are essential in the construction of an object recognition system.

Rapid development of computer hardware has enabled usage of automatic object recognition in an increasing number of applications, ranging from industrial image processing to medical applications, as well as tasks triggered by the widespread use of the internet. Each area of application has its specific requirements, and consequently these cannot all be tackled appropriately by a single, general-purpose algorithm. This easy-to-read text/reference provides a comprehensive introduction to the field of object recognition (OR). The book presents an overview of the diverse applications for OR and highlights important algorithm classes, presenting representative example algorithms for each class. The presentation of each algorithm describes the basic algorithm flow in detail, complete with graphical illustrations. Pseudocode implementations are also included for many of the methods, and definitions are supplied for terms which may be unfamiliar to the novice reader. Supporting a clear and intuitive tutorial style, the usage of mathematics is kept to a minimum. Topics and features: presents example algorithms covering global approaches, transformation-search-based methods, geometrical model driven methods, 3D object recognition schemes, flexible contour fitting algorithms, and descriptor-based methods; explores each method in its entirety, rather than focusing on individual steps in isolation, with a detailed description of the flow of each algorithm, including graphical illustrations; explains the important concepts at length in a simple-to-understand style, with a minimum usage of mathematics; discusses a broad spectrum of applications, including some examples from commercial products; contains appendices discussing topics related to OR and widely used in the algorithms, (but not at the core of the methods described in the chapters). Practitioners of industrial image processing will find this simple introduction and overview to OR a valuable reference, as will graduate students in computer vision courses. Marco Treiber is a software developer at Siemens Electronics Assembly Systems, Munich, Germany, where he is Technical Lead in Image Processing for the Vision System of SiPlace placement machines, used in SMT assembly.

Deep Learning in Object Recognition, Detection, and Segmentation provides a comprehensive introductory overview of a topic that is having major impact on many areas of research in signal processing, computer vision, and machine learning.

Much research as of late has focused on biologically inspired vision models that are based on our understanding of how the visual cortex processes information. One prominent example of such a system is HMAX [17]. HMAX attempts to simulate the biological process for object recognition in cortex based on the model proposed by Hubel & Wiesel [10]. This thesis investigates the ability of an HMAX-like system (GLIMPSE [20]) to perform object-detection in cluttered natural scenes. I evaluate these results using the StreetScenes database from MIT [1, 8]. This thesis addresses three questions: (1) Can the GLIMPSE-based object detection system replicate the results on object-detection reported by Bileschi using HMAX? (2) Which features computed by GLIMPSE lead to the best object-detection performance? (3) What effect does elimination of clutter in the training sets have on the performance of our system? As part of this thesis, I built an object detection and recognition system using GLIMPSE [20] and demonstrate that it approximately replicates the results reported in Bileschi's thesis. In addition, I found that extracting and combining features from GLIMPSE using different layers of the HMAX model gives the best overall invariance to position, scale and translation for recognition tasks, but comes with a much higher computational overhead. Further contributions include the creation of modified training and test sets based on the StreetScenes database, with removed clutter in the training data and extending the annotations for the detection task to cover more objects of interest that were not in the original annotations of the database.

Human object recognition is a classical topic both for philosophy and for the natural sciences. Ultimately, understanding of object recognition will be promoted by the cooperation of behavioral research, neurophysiology, and computation. This original book provides an excellent introduction to the issues that are involved. It contains chapters that address the ways in which humans and machines attend to, recognize, and act toward objects in the visual environment.