Over the past 40 years, neurobiology and computational neuroscience has proved that deeper understanding of visual processes in humans and non-human primates can lead to important advancements in computational perception theories and systems. One of the main difficulties that arises when designing automatic vision systems is developing a mechanism that can recognize - or simply find - an object when faced with all the possible variations that may occur in a natural scene, with the ease of the primate visual system. The area of the brain in primates that is dedicated at analyzing visual information is the visual cortex. The visual cortex performs a wide variety of complex tasks by means of simple operations. These seemingly simple operations are applied to several layers of neurons organized into a hierarchy, the layers representing increasingly complex, abstract intermediate processing stages. In this Research Topic we propose to bring together current efforts in neurophysiology and computer vision in order 1) To understand how the visual cortex encodes an object from a starting point where neurons respond to lines, bars or edges to the representation of an object at the top of the hierarchy that is invariant to illumination, size, location, viewpoint, rotation and robust to occlusions and clutter; and 2) How the design of automatic vision systems benefit from that knowledge to get closer to human accuracy, efficiency and robustness to variations.

Over the past 40 years, neurobiology and computational neuroscience has proved that deeper understanding of visual processes in humans and non-human primates can lead to important advancements in computational perception theories and systems. One of the main difficulties that arises when designing automatic vision systems is developing a mechanism that can recognize - or simply find - an object when faced with all the possible variations that may occur in a natural scene, with the ease of the primate visual system. The area of the brain in primates that is dedicated at analyzing visual information is the visual cortex. The visual cortex performs a wide variety of complex tasks by means of simple operations. These seemingly simple operations are applied to several layers of neurons organized into a hierarchy, the layers representing increasingly complex, abstract intermediate processing stages. In this Research Topic we propose to bring together current efforts in neurophysiology and computer vision in order 1) To understand how the visual cortex encodes an object from a starting point where neurons respond to lines, bars or edges to the representation of an object at the top of the hierarchy that is invariant to illumination, size, location, viewpoint, rotation and robust to occlusions and clutter; and 2) How the design of automatic vision systems benefit from that knowledge to get closer to human accuracy, efficiency and robustness to variations.

Structured Computer Vision

A unique multidisciplinary perspective on the problem of visual object categorization.

Human performance in visual perception by far exceeds the performance of contemporary computer vision systems. While humans are able to perceive their environment almost instantly and reliably under a wide range of conditions, computer vision systems work well only under controlled conditions in limited domains. This book sets out to reproduce the robustness and speed of human perception by proposing a hierarchical neural network architecture for iterative image interpretation. The proposed architecture can be trained using unsupervised and supervised learning techniques. Applications of the proposed architecture are illustrated using small networks. Furthermore, several larger networks were trained to perform various nontrivial computer vision tasks.

The four-volume set LNCS 8925, 8926, 8927, and 8928 comprises the thoroughly refereed post-workshop proceedings of the Workshops that took place in conjunction with the 13th European Conference on Computer Vision, ECCV 2014, held in Zurich, Switzerland, in September 2014. The 203 workshop papers were carefully reviewed and selected for inclusion in the proceedings. They where presented at workshops with the following themes: where computer vision meets art; computer vision in vehicle technology; spontaneous facial behavior analysis; consumer depth cameras for computer vision; "chalearn" looking at people: pose, recovery, action/interaction, gesture recognition; video event categorization, tagging and retrieval towards big data; computer vision with local binary pattern variants; visual object tracking challenge; computer vision + ontology applies cross-disciplinary technologies; visual perception of affordance and functional visual primitives for scene analysis; graphical models in computer vision; light fields for computer vision; computer vision for road scene understanding and autonomous driving; soft biometrics; transferring and adapting source knowledge in computer vision; surveillance and re-identification; color and photometry in computer vision; assistive computer vision and robotics; computer vision problems in plant phenotyping; and non-rigid shape analysis and deformable image alignment. Additionally, a panel discussion on video segmentation is included.

Computer Vision Systems is a collection of papers presented at the Workshop on Computer Vision Systems held at the University of Massachusetts in Amherst, Massachusetts, on June 1-3, 1977. Contributors discuss the breadth of problems that must be taken into account in the development of general computer vision systems. Topics covered include the application of system engineering techniques to the design of artificial intelligence systems; representation and segmentation of natural scenes; and pragmatic aspects of machine vision. Psychophysical measures of representation and interpretation are also considered. This monograph is divided into four sections: Issues and Research Strategies, Segmentation, Theory and Psychology, and Systems. The first chapter explores the problem of recovering the intrinsic characteristics of scenes from images, along with its implications for machine and human vision. The discussion then turns to special-purpose low-level vision systems that can be flexibly reconfigured as the need arises; design, development, and implementation of large systems from the human engineering point of view; and representation of visual information. The next section examines hierarchical relaxation for waveform parsing; the topology and semantics of intensity arrays; and visual images as spatial representations in active memory. The use of edge cues to recognize real-world objects is also analyzed. This text will be a useful resource for systems designers, computer engineers, and scientists as well as psychologists.