Aspect Graphs for Visual Recognition of Three-Dimensional Objects

Perception ◽  
1994 ◽  
Vol 23 (5) ◽  
pp. 563-582 ◽  
Author(s):  
Thierry Van Effelterre

Visual representation of three-dimensional (3-D) objects in our environment is a crucial question, for human as well as for machine vision. Some basics are reviewed of a viewer-centred model of 3-D objects, aspect graphs, which represents a 3-D object by all its topologically stable visible image contours (its aspects) and by the transitions between stable image contours (the visual events). This representation takes only geometrical information about discontinuities in depth and in surface orientation into account, and other clues, such as shadows, markings, texture, etc, are disregarded. Mathematical results give some insight into the relationships between the geometry of a 3-D object and the aspect of its image contours, the techniques used to compute an aspect graph effectively, and the state of the art of this type of model in computer vision. Current research is reviewed on viewer-centred representation in cognitive science that seems to indicate that aspect graphs could also have some relevance for human vision.

Author(s):  
Binbin Zhao ◽  
Shihong Liu

AbstractComputer vision recognition refers to the use of cameras and computers to replace the human eyes with computer vision, such as target recognition, tracking, measurement, and in-depth graphics processing, to process images to make them more suitable for human vision. Aiming at the problem of combining basketball shooting technology with visual recognition motion capture technology, this article mainly introduces the research of basketball shooting technology based on computer vision recognition fusion motion capture technology. This paper proposes that this technology first performs preprocessing operations such as background removal and filtering denoising on the acquired shooting video images to obtain the action characteristics of the characters in the video sequence and then uses the support vector machine (SVM) and the Gaussian mixture model to obtain the characteristics of the objects. Part of the data samples are extracted from the sample set for the learning and training of the model. After the training is completed, the other parts are classified and recognized. The simulation test results of the action database and the real shot video show that the support vector machine (SVM) can more quickly and effectively identify the actions that appear in the shot video, and the average recognition accuracy rate reaches 95.9%, which verifies the application and feasibility of this technology in the recognition of shooting actions is conducive to follow up and improve shooting techniques.


2021 ◽  
Vol 3 (4) ◽  
pp. 966-989
Author(s):  
Vanessa Buhrmester ◽  
David Münch ◽  
Michael Arens

Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificially generated datasets, which often do not reflect reality. By basing decision-making algorithms on Deep Neural Networks, prejudice and unfairness may be promoted unknowingly due to a lack of transparency. Hence, several so-called explanators, or explainers, have been developed. Explainers try to give insight into the inner structure of machine learning black boxes by analyzing the connection between the input and output. In this survey, we present the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about the taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.


2021 ◽  
Vol 13 (1) ◽  
pp. 91-98
Author(s):  
Yehia Enab ◽  
Fayez Zaki ◽  
A. Abd El-Fattah ◽  
S. El-Konyaly

Author(s):  
Ning Bi ◽  
Jiahao Chen ◽  
Jun Tan

With the outstanding performance in 2014 at the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14), an effective convolutional neural network (CNN) model named GoogLeNet has drawn the attention of the mainstream machine learning field. In this paper we plan to take an insight into the application of the GoogLeNet in the Handwritten Chinese Character Recognition (HCCR) on the database HCL2000 and CASIA-HWDB with several necessary adjustments and also state-of-the-art improvement methods for this end-to-end approach. Through the experiments we have found that the application of the GoogLeNet for the Handwritten Chinese Character Recognition (HCCR) results into significant high accuracy, to be specific more than 99% for the final version, which is encouraging for us to further research.


2018 ◽  
Vol LXXVIII (5) ◽  
pp. 325-334
Author(s):  
Edyta Gruszczyk-Kolczyńska

In the article, I present the findings of scientific insight into issues that I call tablet children. I provide alarming data on the number of children aged 6 months and a little bit older who are given access to tablets and smartphones by adults. I quote the most important findings included in the theory of representation by Jerome S. Bruner to explain the following: – What makes babies and toddlers use tablets and smartphones in a remarkably efficient way; – Adverse differences in representations created by children based on experiences gathered in the world of real objects and in the virtual world; – Distortions in the outlines of mental representations formed by young children when they watch images on tablet and smartphone screens too frequently. Being given access to these devices is particularly dangerous for young children, who have not yet created the outlines of the representations of three-dimensional objects and three-dimensional qualities of space in their minds. Distortions in the outlines of representations are difficult to fix as subsequent experiences only complement and expand the existing representations. Since the existing representations take part in creating new representations, the new ones are not fully correct either. I also argue the need for serious research that should aim to determine the far-reaching results of tablets and smartphones being available to babies and young children. This will help to come to terms with these devices educationally and also to determine when and for how long they can be made available to children so that they are safe for children's mental development.


Author(s):  
Peter Sterling

The synaptic connections in cat retina that link photoreceptors to ganglion cells have been analyzed quantitatively. Our approach has been to prepare serial, ultrathin sections and photograph en montage at low magnification (˜2000X) in the electron microscope. Six series, 100-300 sections long, have been prepared over the last decade. They derive from different cats but always from the same region of retina, about one degree from the center of the visual axis. The material has been analyzed by reconstructing adjacent neurons in each array and then identifying systematically the synaptic connections between arrays. Most reconstructions were done manually by tracing the outlines of processes in successive sections onto acetate sheets aligned on a cartoonist's jig. The tracings were then digitized, stacked by computer, and printed with the hidden lines removed. The results have provided rather than the usual one-dimensional account of pathways, a three-dimensional account of circuits. From this has emerged insight into the functional architecture.


1985 ◽  
Vol 30 (1) ◽  
pp. 47-47
Author(s):  
Herman Bouma
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document