Recognition by symmetry derivatives and the generalized structure tensor

Bigün, Josef; Bigun, Tomas; Nilsson, Kenneth

doi:10.1109/tpami.2004.126

Cited by 120 publications

(91 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Symmetry features enable the description of symmetric patterns such as lines, circles, parabolas, and so on ( Figure 1). Symmetry features are extracted via symmetry filters, Equation 1, which output how much of a certain symmetry exist in a local image neighborhood [12,13]. …”

Section: Eye Localizationmentioning

confidence: 99%

Eye detection by complex filtering for periocular recognition

Alonso‐Fernandez

Bigün

2014

2nd International Workshop on Biometrics and Forensics

View full text Add to dashboard Cite

We present a novel system to localize the eye position based on symmetry filters. By using a 2D separable filter tuned to detect circular symmetries, detection is done with a few 1D convolutions. The detected eye center is used as input to our periocular algorithm based on retinotopic sampling grids and Gabor analysis of the local power spectrum. This setup is evaluated with two databases of iris data, one acquired with a close-up NIR camera, and another in visible light with a webcam. The periocular system shows high resilience to inaccuracies in the position of the detected eye center. The density of the sampling grid can also be reduced without sacrificing too much accuracy, allowing additional computational savings. We also evaluate an iris texture matcher based on 1D Log-Gabor wavelets. Despite the poorer performance of the iris matcher with the webcam database, its fusion with the periocular system results in improved performance.

show abstract

Section: Eye Localizationmentioning

confidence: 99%

Eye detection by complex filtering for periocular recognition

Alonso‐Fernandez

Bigün

2014

2nd International Workshop on Biometrics and Forensics

View full text Add to dashboard Cite

show abstract

“…Instead, normal orientations are required to compute structure. Following the approach in [2], such orientations can be extracted from tensors R computed as:…”

Section: Tensor-valued Imagesmentioning

confidence: 99%

“…A related approach based on quadrature filters has been proposed in [19,12]. Furthermore, extensions using higher-order derivatives [9,21], and extensions for curved structures [2] have also been proposed. Despite its popularity, the structure tensor also has important shortcomings, such as detection of features in flat regions, loss of small features, detection of false corners, and misplacement of corners.…”

Section: Introductionmentioning

confidence: 99%

Adaptation of Tensor Voting to Image Structure Estimation

Moreno

Pizarro

Burgeth

et al. 2012

Mathematics and Visualization

View full text Add to dashboard Cite

Tensor voting is a well-known robust technique for extracting perceptual information from clouds of points. This chapter proposes a general methodology to adapt tensor voting to different types of images in the specific context of image structure estimation. This methodology is based on the structural relationships between tensor voting and the so-called structure tensor, which is the most popu- lar technique for image structure estimation. The problematic Gaussian convolution used by the structure tensor is replaced by tensor voting. Afterwards, the results are appropriately rescaled. This methodology is adapted to gray-valued, color, vectorand tensor-valued images. Results show that tensor voting can estimate image structure more appropriately than the structure tensor and also more robustly.

show abstract

“…Bigun et al [5] use a structure tensor to represent and detect more intricate patterns than straight lines and edges to produce and filter dense orientation fields for feature extraction, matching, and pattern recognition.…”

Section: Related Workmentioning

confidence: 99%

High Frequency Assessment from Multiresolution Analysis

Castro

Perez

Mota

et al. 2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We propose a method for the assessment and visualization of high frequency regions of a multiresolution image. We combine both orientation tensor and multiresolution analysis to give a scalar descriptor of high frequency regions. High values of this scalar space indicate regions having coincident detail vectors in multiple scales of a wavelet decomposition. This is useful for finding edges, textures, collinear structures and salient regions for computer vision methods. The image is decomposed into several scales using the Discrete Wavelet Transform (DWT). The resulting detail spaces form vectors indicating intensity variations which are combined using orientation tensors. A high frequency scalar descriptor is then obtained from the resulting tensor for each original image pixel. Our results show that this descriptor indicates areas having relevant intensity variation in multiple scales.

show abstract

Recognition by symmetry derivatives and the generalized structure tensor

Cited by 120 publications

References 34 publications

Eye detection by complex filtering for periocular recognition

Eye detection by complex filtering for periocular recognition

Adaptation of Tensor Voting to Image Structure Estimation

High Frequency Assessment from Multiresolution Analysis

Contact Info

Product

Resources

About