Orientation Correlation

Abstract-We introduce the notion of subspace learning from image gradient orientations for appearance-based object recognition. As image data is typically noisy and noise is substantially different from Gaussian, traditional subspace learning from pixel intensities fails very often to estimate reliably the low-dimensional subspace of a given data population. We show that replacing pixel intensities with gradient orientations and the 2 norm with a cosine-based distance measure offers, to some extend, a remedy to this problem. Within this framework, which we coin IGO (Image Gradient Orientations) subspace learning, we first formulate and study the properties of Principal Component Analysis of image gradient orientations (IGO-PCA). We then show its connection to previously proposed robust PCA techniques both theoretically and experimentally. Finally, we derive a number of other popular subspace learning techniques, namely Linear Discriminant Analysis (LDA), Locally Linear Embedding (LLE) and Laplacian Eigenmaps (LE). Experimental results show that our algorithms outperform significantly popular methods such as Gabor features and Local Binary Patterns and achieve state-of-the-art performance for difficult problems such as illumination-and occlusion-robust face recognition. In addition to this, the proposed IGO-methods require the eigen-decomposition of simple covariance matrices and are as computationally efficient as their corresponding 2 norm intensity-based counterparts. Matlab code for the methods presented in this paper can be found at http://ibug.doc.ic.ac.uk/resources.

show abstract

“…We compute the corresponding set of orientation images {Φ i } and measure image correlation using the cosine kernel [22], [26] …”

Section: Cosine-based Correlation Of Image Gradient Orientationsmentioning

confidence: 99%

Subspace Learning from Image Gradient Orientations

Tzimiropoulos

Zafeiriou

Pantić

2012

IEEE Trans. Pattern Anal. Mach. Intell.

148

150

View full text Add to dashboard Cite

show abstract

“…As proposed in (Fitch et al, 2002), the partial derivatives for the gradient computation are calculated by approximating them with the central differences. Hence, the OC measure between P and I xy is defined as the real part of the correlation between all gradient orientations belonging to P and I xy :…”

Section: The Oc Measurementioning

confidence: 99%

“…The OC measure (Fitch et al, 2002) is based on the correlation of the orientation of the intensity gradient. In particular, for each gradient of the pattern G P (i, j) a complex number representing the orientation of the gradient vector is defined as:…”

Section: The Oc Measurementioning

confidence: 99%

“…Evaluation assessments have also been proposed which compared some of these measures in particular fields such as stereo correspondence (Chambon and Crouzil, 2003), image registration (Zitová and Flusser, 2003) and image motion (Giachetti, 2000). Generally speaking, apart from classical approaches which will be discussed in Section 2, many robust measures for visual correspondence have been proposed in literature (Tombari et al, 2007), (Crouzil et al, 1996), (Scharstein, 1994), (Seitz, 1989), (Aschwanden and Guggenbuhl, 1992), (Martin and Crowley, 1995), (Fitch et al, 2002), (Zabih and Woodfill, 1994), (Bhat and Nayar, 1998), (Kaneko et al, 2003), (Ullah et al, 2001). A taxonomy which includes the majority of these approaches is proposed in (Chambon and Crouzil, 2003).…”

Section: Introductionmentioning

confidence: 99%

“…the approach recently proposed in (Tombari et al, 2007), GC (Gradient Correlation), i.e. the approach initially proposed in (Scharstein, 1994) according to the formulation proposed in (Crouzil et al, 1996) for the pattern matching problem, OC (Orientation Correlation), proposed in (Fitch et al, 2002). Moreover, we will consider the SSD (Sum of Squared Differences) and NCC (Normalized Cross Correlation) measures applied on gradient norms (G-NCC and G-SSD), which showed good robustness against illumination changes in the experimental comparison described in (Martin and Crowley, 1995).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Performance Evaluation of Robust Matching Measures

Tombari¹,

Stefano²,

Mattoccia³

et al. 2008

Proceedings of the Third International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:This paper is aimed at evaluating the performances of different measures which have been proposed in literature for robust matching. In particular, classical matching metrics typically employed for this task are considered together with specific approaches aiming at achieving robustness. The main aspects assessed by the proposed evaluation are robustness with respect to photometric distortions, noise and occluded patterns. Specific datasets have been used for testing, which provide a very challenging framework for what concerns the considered disturbance factors and can also serve as testbed for evaluation of future robust visual correspondence measures.

show abstract

Characterizing interannual variability of glacier dynamics and dynamic discharge (1999–2015) for the ice masses of Ellesmere and Axel Heiberg Islands, Nunavut, Canada

et al. 2016

View full text Add to dashboard Cite

Landsat 7 and RADARSAT‐1/RADARSAT‐2 satellite images are used to produce the most comprehensive record of glacier motion in the Canadian High Arctic to date and to characterize spatial and temporal variability in ice flow over the past ~15 years. This allows us to assess whether dynamically driven glacier change can be attributed to “surging” or “pulsing,” or whether other mechanisms are involved. RADAR velocity mapping allows annual regional dynamic discharge (iceberg calving) to be calculated for 2000 and the period 2011–2015 (yielding a mean regional discharge of 2.21 ± 0.68 Gt a−1), and velocities derived from feature tracking of optical imagery allow for annual dynamic discharge to be calculated for select glaciers from 1999 to 2010. Since ~2011, several of the major tidewater‐terminating glaciers within the region have decelerated and their dynamic discharge has decreased. Trinity and Wykeham Glaciers (Prince of Wales Icefield) represent a notable departure from this pattern as they have generally accelerated over the study period. The resulting increase in dynamic discharge from these glaciers entirely compensates (within error limits) for the decrease in discharge from the other tidewater glaciers across the study region. These two glaciers accounted for ~62% of total regional dynamic discharge in winter 2015 (compared to ~22% in 2000), demonstrating that total ice discharge from the Canadian High Arctic can be sensitive to variations in flow of just a few tidewater glaciers.

show abstract

Orientation Correlation

Cited by 94 publications

References 0 publications

Subspace Learning from Image Gradient Orientations

Subspace Learning from Image Gradient Orientations

Performance Evaluation of Robust Matching Measures

Characterizing interannual variability of glacier dynamics and dynamic discharge (1999–2015) for the ice masses of Ellesmere and Axel Heiberg Islands, Nunavut, Canada

Contact Info

Product

Resources

About