Results 1 -
7 of
7
Detecting symmetry and symmetric constellations of features
- In ECCV
, 2006
"... Abstract. A novel and efficient method is presented for grouping feature points on the basis of their underlying symmetry and characterising the symmetries present in an image. We show how symmetric pairs of features can be efficiently detected, how the symmetry bonding each pair is extracted and ev ..."
Abstract
-
Cited by 76 (3 self)
- Add to MetaCart
(Show Context)
Abstract. A novel and efficient method is presented for grouping feature points on the basis of their underlying symmetry and characterising the symmetries present in an image. We show how symmetric pairs of features can be efficiently detected, how the symmetry bonding each pair is extracted and evaluated, and how these can be grouped into symmetric constellations that specify the dominant symmetries present in the image. Symmetries over all orientations and radii are considered simultaneously, and the method is able to detect local or global symmetries, locate symmetric figures in complex backgrounds, detect bilateral or rotational symmetry, and detect multiple incidences of symmetry. 1
Human Face Verification by Robust 3D Surface Alignment
, 2006
"... Traditional 2D face recognition systems are not tolerant to changes in pose, lighting and expression. This dissertation explores the use of 3D data to improve face recognition by accounting for these variations. A two step, fully automatic, 3D surface alignment algorithm is developed to correlate th ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
Traditional 2D face recognition systems are not tolerant to changes in pose, lighting and expression. This dissertation explores the use of 3D data to improve face recognition by accounting for these variations. A two step, fully automatic, 3D surface alignment algorithm is developed to correlate the surfaces of two 3D face scans. In the first step, key anchor points such as the tip of the nose are used to coarsely align two face scans. In the second step, the Iterative Closest Point (ICP) algorithm is used to finely align the scans. The quality of the face alignment is studied in depth using a Surface Alignment Measure (SAM). The SAM is the root mean squared error over all the control points used in the ICP algorithm, after trimming to account for noise in the data. This alignment algorithm is fast (<2 seconds on a 3.2GHz P4) and robust to noise in the data (<10 % spike noise). Extensive experiments were conducted to show that the alignment algorithm can tolerate up to 15 ◦ of variation in pose due to roll and pitch, and 30 ◦ of variation in yaw. It is shown that this level of pose tolerance easily covers the normal pose variation of a database of over 275 cooperative
European starlings are capable of discriminating subtle size asymmetries in paired stimuli
- Journal of the Experimental Analysis of Behavior
, 2007
"... Small deviations from bilateral symmetry (fluctuating asymmetries) are cues to fitness differences in some animals. Therefore, researchers have considered whether animals use these small asymmetries as visual cues to determine appropriate behavioral responses (e.g., mate preferences). However, there ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
(Show Context)
Small deviations from bilateral symmetry (fluctuating asymmetries) are cues to fitness differences in some animals. Therefore, researchers have considered whether animals use these small asymmetries as visual cues to determine appropriate behavioral responses (e.g., mate preferences). However, there have been few systematic studies of animals ’ abilities to visually discriminate such minor asymmetries. If the asymmetries cannot be discriminated, fluctuating asymmetry can not be a visual cue. Here, we report an investigation of European starlings ’ (Sturnus vulgaris) abilities to discriminate small size asymmetries. We trained starlings, through operant conditioning in a free-flight aviary, to discriminate achromatic, symmetric paired stimuli from size-matched asymmetric stimuli. By starting the learning process with a large asymmetry and progressing through sequential trials of decreasing asymmetry, we elucidated a behavioral limit to asymmetry discrimination. We found that starlings are capable of discriminating a 10 % size asymmetry. There was weaker evidence for discrimination of 5 % asymmetry but no evidence for signal discrimination at 2.5 % size asymmetry. This level of asymmetry discrimination suggests that many size asymmetry cues in nature can be discriminated by birds. At each level of asymmetry discrimination, we also tested whether starlings could generalize their learned symmetry preference to unreinforced novel images. Consistent with previous findings, we found that starlings could generalize their symmetry preferences.
SPATIAL DATBASE FEASIBILITY FOR FACIAL CHARACTERIZATION USING FUZZY LOGIC QUERIES
"... ..."
(Show Context)
GPU-based Multi-Resolution Image Analysis for Synthesis of Tileable Textures
"... Abstract. We propose a GPU-based algorithm for texture analysis and synthesis of nearly-regular patterns, in our case scanned textiles or similar manufactured surfaces. The method takes advantage of the highly parallel execution on the GPU to generate correlation maps from captured template images. ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract. We propose a GPU-based algorithm for texture analysis and synthesis of nearly-regular patterns, in our case scanned textiles or similar manufactured surfaces. The method takes advantage of the highly parallel execution on the GPU to generate correlation maps from captured template images. In an analysis step a lattice encoding the periodicity of the texture is computed. This lattice is used to synthesize the smallest texture tile describing the underlying pattern. Compared to other approaches, our method analyzes and synthesizes a valid lattice model without any user interaction. It is robust against small distortions and fast compared to other, more general approaches. 1 Introduction and Related Work Many manufactured surfaces contain regular patterns, which could efficiently be used as repetitive textures in a computer graphics. Capturing these patterns by camera or similar means leads in most cases- due to perspective or lens distortion, or due to the geometry of the underlying surface- to images which do not tile correctly. Converting
Article Similar Symmetries: The Role of Wallpaper Groups in Perceptual Texture Similarity
, 2011
"... symmetry ..."
Available online at www.s
"... er et C. avi nd sexual selection; signalling; Sturnus vulgaris; visual perception debated and there is no clear resolution as to whether these on the generality of the visual communication properties ANIMAL BEHAVIOUR, 2 doi:10.1016/j.anbehaing lack of experimental investigations of the visual role o ..."
Abstract
- Add to MetaCart
(Show Context)
er et C. avi nd sexual selection; signalling; Sturnus vulgaris; visual perception debated and there is no clear resolution as to whether these on the generality of the visual communication properties ANIMAL BEHAVIOUR, 2 doi:10.1016/j.anbehaing lack of experimental investigations of the visual role of FA inmediating behavioural interactions. To date, there are Johnson 2007) and positional (Swaddle & Pruett-Jones 2001) and numerical asymmetries (Swaddle & Ruff 2004). If the European starling is a representative passer-ine and its asymmetry-detection abilities generally indi-cate those of other avian species, we can use our results to interpret the relevance of FA to visual communication
