Viewpoint-Invariant Representation of Generalized Cylinders Using the Symmetry Set

1994 ◽  
Author(s):  
Nic Pillow ◽  
Sven Utcke ◽  
Andrew Zisserman
Keyword(s):  
Invariant Representation ◽  
Symmetry Set ◽  
Generalized Cylinders

Viewpoint-invariant representation of generalized cylinders using the symmetry set

1995 ◽  
Vol 13 (5) ◽  
pp. 355-365 ◽  
Author(s):  
Nic Pillow ◽  
Sven Utcke ◽  
Andrew Zisserman
Keyword(s):  
Invariant Representation ◽  
Symmetry Set ◽  
Generalized Cylinders

scholarly journals 3D Affine: An Embedding of Local Image Features for Viewpoint Invariance Using RGB-D Sensor Data

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 291 ◽  
Author(s):  
Hamdi Sahloul ◽  
Shouhei Shirafuji ◽  
Jun Ota
Keyword(s):  
Low Cost ◽  
Image Features ◽  
Image Feature ◽  
Sensor Data ◽  
Invariant Representation ◽  
Depth Sensors ◽  
Viewpoint Invariance ◽  
Surface Discontinuities ◽  
Local Image ◽  
Local Image Features

Local image features are invariant to in-plane rotations and robust to minor viewpoint changes. However, the current detectors and descriptors for local image features fail to accommodate out-of-plane rotations larger than 25°–30°. Invariance to such viewpoint changes is essential for numerous applications, including wide baseline matching, 6D pose estimation, and object reconstruction. In this study, we present a general embedding that wraps a detector/descriptor pair in order to increase viewpoint invariance by exploiting input depth maps. The proposed embedding locates smooth surfaces within the input RGB-D images and projects them into a viewpoint invariant representation, enabling the detection and description of more viewpoint invariant features. Our embedding can be utilized with different combinations of descriptor/detector pairs, according to the desired application. Using synthetic and real-world objects, we evaluated the viewpoint invariance of various detectors and descriptors, for both standalone and embedded approaches. While standalone local image features fail to accommodate average viewpoint changes beyond 33.3°, our proposed embedding boosted the viewpoint invariance to different levels, depending on the scene geometry. Objects with distinct surface discontinuities were on average invariant up to 52.8°, and the overall average for all evaluated datasets was 45.4°. Similarly, out of a total of 140 combinations involving 20 local image features and various objects with distinct surface discontinuities, only a single standalone local image feature exceeded the goal of 60° viewpoint difference in just two combinations, as compared with 19 different local image features succeeding in 73 combinations when wrapped in the proposed embedding. Furthermore, the proposed approach operates robustly in the presence of input depth noise, even that of low-cost commodity depth sensors, and well beyond.

Emergence of a compositional neural code for written words: Recycling of a convolutional neural network for reading

2021 ◽  
Vol 118 (46) ◽  
pp. e2104779118
Author(s):  
T. Hannagan ◽  
A. Agrawal ◽  
L. Cohen ◽  
S. Dehaene
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Language Processing ◽  
Visual Pathway ◽  
Neural Code ◽  
Letter Recognition ◽  
Invariant Representation ◽  
Spoken Language Processing ◽  
Visual Word Form Area ◽  
Ventral Visual Pathway

The visual word form area (VWFA) is a region of human inferotemporal cortex that emerges at a fixed location in the occipitotemporal cortex during reading acquisition and systematically responds to written words in literate individuals. According to the neuronal recycling hypothesis, this region arises through the repurposing, for letter recognition, of a subpart of the ventral visual pathway initially involved in face and object recognition. Furthermore, according to the biased connectivity hypothesis, its reproducible localization is due to preexisting connections from this subregion to areas involved in spoken-language processing. Here, we evaluate those hypotheses in an explicit computational model. We trained a deep convolutional neural network of the ventral visual pathway, first to categorize pictures and then to recognize written words invariantly for case, font, and size. We show that the model can account for many properties of the VWFA, particularly when a subset of units possesses a biased connectivity to word output units. The network develops a sparse, invariant representation of written words, based on a restricted set of reading-selective units. Their activation mimics several properties of the VWFA, and their lesioning causes a reading-specific deficit. The model predicts that, in literate brains, written words are encoded by a compositional neural code with neurons tuned either to individual letters and their ordinal position relative to word start or word ending or to pairs of letters (bigrams).

scholarly journals Degen Generalized Cylinders and Their Properties

2006 ◽  
pp. 83-94
Author(s):  
Liangliang Cao ◽  
Jianzhuang Liu ◽  
Xiaoou Tang
Keyword(s):  
Generalized Cylinders

scholarly journals Mosaicing of flattened images from straight homogeneous generalized cylinders

1997 ◽  
pp. 122-129 ◽  
Author(s):  
Adrian G. Borş ◽  
William Puech ◽  
Ioannis Pitas ◽  
Jean-Marc Chassery
Keyword(s):  
Generalized Cylinders

Modelling mollusc shells with generalized cylinders

1998 ◽  
Vol 22 (4) ◽  
pp. 505-513 ◽  
Author(s):  
Aadjan van der Helm ◽  
Peter Ebell ◽  
Willem F. Bronsvoort
Keyword(s):  
Generalized Cylinders ◽  
Mollusc Shells
Sign in / Sign up

Export Citation Format

Share Document