Multi-view face segmentation using fusion of statistical shape and appearance models

2010 ◽  
Vol 114 (3) ◽  
pp. 311-321 ◽  
Author(s):  
Constantine Butakoff ◽  
Alejandro F. Frangi
Keyword(s):  
Face Segmentation ◽  
Statistical Shape ◽  
Appearance Models

Statistical shape and appearance models of bones

Bone ◽  
2014 ◽  
Vol 60 ◽  
pp. 129-140 ◽  
Author(s):  
Nazli Sarkalkan ◽  
Harrie Weinans ◽  
Amir A. Zadpoor
Keyword(s):  
Statistical Shape ◽  
Appearance Models

Automatic Lung Field Segmentation in X-ray Radiographs Using Statistical Shape and Appearance Models

2016 ◽  
Vol 6 (2) ◽  
pp. 338-348 ◽  
Author(s):  
Xuechen Li ◽  
Suhuai Luo ◽  
Qingmao Hu ◽  
Jiaming Li ◽  
Dadong Wang ◽  
...  
Keyword(s):  
Lung Field ◽  
X Ray ◽  
Statistical Shape ◽  
Appearance Models ◽  
Lung Field Segmentation

scholarly journals Estimating the projected frontal surface area of cyclists from images using a variational framework and statistical shape and appearance models

2017 ◽  
Vol 231 (3) ◽  
pp. 169-183
Author(s):  
Ami Drory ◽  
Hongdong Li ◽  
Richard Hartley
Keyword(s):  
Wind Tunnel ◽  
Surface Area ◽  
Aerodynamic Drag ◽  
Image Features ◽  
Dice Similarity Coefficient ◽  
Frontal Surface ◽  
Variational Framework ◽  
Statistical Shape ◽  
Appearance Models ◽  
Pose Variation

We present a computer vision-based approach to estimating the projected frontal surface area (pFSA) of cyclists from unconstrained images. Wind tunnel studies show a reduction in cyclists’ aerodynamic drag through manipulation of the cyclist’s pose. Whilst the mechanism by which reduction is achieved remains unknown, it is widely accepted in the literature that the drag is proportional to the cyclist’s pFSA. This paper describes a repeatable automatic method for pFSA estimation for the study of its relationship with aerodynamic drag in cyclists. The proposed approach is based on finding object boundaries in images. An initialised curve dynamically evolves in the image to minimise an energy function designed to force the curve to gravitate towards image features. To overcome occlusions and pose variation, we use a statistical cyclist shape and appearance models as priors to encourage the evolving curve to arrive at the desired solution. Contour initialisation is achieved using a discriminative object detection method based on offline supervised learning that yields a cyclist classifier. Once an instance of a cyclist is detected in an image and segmented, the pFSA is calculated from the area of the final curve. Applied to two challenging datasets of cyclist images, for cyclist detection our method achieves precision scores of 1.0 and 0.96 and recall scores of 0.68 and 0.83 on the wind tunnel and cyclists-in-natura datasets, respectively. For cyclist segmentation, it achieves 0.88 and 0.92 scores for the mean dice similarity coefficient metric on the two datasets, respectively. We discuss the performance of our method under occlusion, orientation, and pose conditions. Our method successfully estimates pFSA of cyclists and opens new vistas for exploration of the relationship between pFSA and aerodynamic drag.

Statistical Shape and Appearance Models in Osteoporosis

2014 ◽  
Vol 12 (2) ◽  
pp. 163-173 ◽  
Author(s):  
Isaac Castro-Mateos ◽  
Jose M. Pozo ◽  
Timothy F. Cootes ◽  
J. Mark Wilkinson ◽  
Richard Eastell ◽  
...  
Keyword(s):  
Statistical Shape ◽  
Appearance Models

Change of color appearance due to extremely high light level: corresponding colors under 100 and 3000 cd/m2

2019 ◽  
Vol 2019 (1) ◽  
pp. 320-325 ◽  
Author(s):  
Wenyu Bao ◽  
Minchen Wei
Keyword(s):  
Light Level ◽  
Limited Range ◽  
High Light ◽  
Color Preference ◽  
Color Appearance ◽  
Appearance Model ◽  
Color Matching ◽  
Light Levels ◽  
Appearance Models ◽  
Psychophysical Study

Great efforts have been made to develop color appearance models to predict color appearance of stimuli under various viewing conditions. CIECAM02, the most widely used color appearance model, and many other color appearance models were all developed based on corresponding color datasets, including LUTCHI data. Though the effect of adapting light level on color appearance, which is known as "Hunt Effect", is well known, most of the corresponding color datasets were collected within a limited range of light levels (i.e., below 700 cd/m2), which was much lower than that under daylight. A recent study investigating color preference of an artwork under various light levels from 20 to 15000 lx suggested that the existing color appearance models may not accurately characterize the color appearance of stimuli under extremely high light levels, based on the assumption that the same preference judgements were due to the same color appearance. This article reports a psychophysical study, which was designed to directly collect corresponding colors under two light levels— 100 and 3000 cd/m2 (i.e., ≈ 314 and 9420 lx). Human observers completed haploscopic color matching for four color stimuli (i.e., red, green, blue, and yellow) under the two light levels at 2700 or 6500 K. Though the Hunt Effect was supported by the results, CIECAM02 was found to have large errors under the extremely high light levels, especially when the CCT was low.

Sign in / Sign up

Export Citation Format

Share Document