16,760 Hits in 6.2 sec

Fast Scale-Space Feature Representations by Generalized Integral Images

Konstantinos G. Derpanis, Erich T. H. Leung, Mikhail Sizintsev
2007 2007 IEEE International Conference on Image Processing  
In this paper, we place the integral image-based approach for multi-scale feature construction, popularized by Viola and Jones, into a common framework of understanding.  ...  The integral image within this framework represents space variant image filtering with the zero-order B-spline.  ...  Spline generated scale-spaces represent an alternative for fast realizations of multi-scale decompositions of images [4, 5] .  ... 
doi:10.1109/icip.2007.4380069 dblp:conf/icip/DerpanisLS07 fatcat:6fu7w5xw2vhodbvugdidpgvida

Image matching Under Varying Illumination Using Uniform Symmetric-Local Binary Pattern

2016 Revista Técnica de la Facultad de Ingeniería Universidad del Zulia  
Firstly, the local maxima is detected with recursive DOG scale space as candidate interesting points.  ...  The experimental results show that the proposed algorithm has the excellent features of scale invariance, rotation invariance, affine invariance and illumination invariance in the process of image matching  ...  Acknowledgements This work is supported by the Specialized Research Fund for the Doctoral Program of Higher Education (20130018110001).  ... 
doi:10.21311/ fatcat:ueplqn7p35ccpl7aiqupwbnsfi

Dynamic Texture Recognition Using Time-Causal Spatio-Temporal Scale-Space Filters [chapter]

Ylva Jansson, Tony Lindeberg
2017 Lecture Notes in Computer Science  
For this purpose, we present a new family of video descriptors based on regional statistics of spatiotemporal scale-space filter responses and evaluate this approach on the problem of dynamic texture recognition  ...  These results support the descriptive power of time-causal spatio-temporal scale-space filters as primitives for video analysis.  ...  The theoretical properties of scale-space filters enable the design of methods invariant or robust to natural image transformations [2] [3] [4] .  ... 
doi:10.1007/978-3-319-58771-4_2 fatcat:62qrktimibcalb4brb7ugqu77i

Page 6850 of Mathematical Reviews Vol. , Issue 2003i [page]

2003 Mathematical Reviews  
The aim of the article is to show the intimate relation between the dimension-trace function and several elements of shift-invariant space theory.  ...  (RS-SYKTM; Syktyvkar) The Butterworth wavelet transform and its implementation using recursive filters. (Russian. Russian summary) Zh. Vychisl. Mat. Mat.  ... 

Velocity adaptation of spatio-temporal receptive fields for direct recognition of activities: an experimental study

Ivan Laptev, Tony Lindeberg
2004 Image and Vision Computing  
Based on a framework of recursive spatio-temporal scale-space, we first outline how a straightforward mechanism for local velocity adaptation can be expressed.  ...  The basic idea consists of adapting the shapes of the filter kernels to the local direction of motion, so as to allow the computation of image descriptors that are invariant to the relative motion in the  ...  Acknowledgements The support from the Swedish Research Council for Engineering Sciences (TFR), the Swedish Research Council (VR), as well as the Royal Swedish Academy of Sciences (KVA) and the Knut and  ... 
doi:10.1016/j.imavis.2003.07.002 fatcat:2m4yf2ysnbcxfjdggb4gv33z44

Time-Causal and Time-Recursive Spatio-Temporal Receptive Fields

Tony Lindeberg
2015 Journal of Mathematical Imaging and Vision  
We present an improved model and theory for time-causal and time-recursive spatio-temporal receptive fields, based on a combination of Gaussian receptive fields over the spatial domain and first-order  ...  Compared to previous spatio-temporal scale-space formulations in terms of non-enhancement of local extrema or scale invariance, these receptive fields are based on different scale-space axiomatics over  ...  If extending the rotationally symmetric Gaussian scale-space concept to an anisotropic affine Gaussian scale-space and/or if we make use of non-separable velocity-adapted receptive fields over space-time  ... 
doi:10.1007/s10851-015-0613-9 fatcat:g5jvzhrxyzbediu6q3iadtmfwm

Dynamic Texture Recognition Using Time-Causal and Time-Recursive Spatio-Temporal Receptive Fields

Ylva Jansson, Tony Lindeberg
2018 Journal of Mathematical Imaging and Vision  
This work presents a first evaluation of using spatio-temporal receptive fields from a recently proposed time-causal spatio-temporal scale-space framework as primitives for video analysis.  ...  Further, our qualitative and quantitative investigation into parameter choices and the use of different sets of receptive fields highlights the robustness and flexibility of our approach.  ...  with state of the art (Sect. 7.4).  ... 
doi:10.1007/s10851-018-0826-9 fatcat:pjqqkkwgifha7pvpqcxat6b5ky

Kalman filtering for self-similar processes

Birsen Yazıcı, Meltem Izzetogˇlu, Banu Onaral, Nihat Bilgutay
2006 Signal Processing  
We referred to this class of processes as scale stationary processes.  ...  We will introduce Kalman filtering techniques and Ricatti Equations for smoothing and prediction of self-similar processes.  ...  As an alternative, the proposed Kalman filter can be used for the estimation and prediction of the transmitted l/f signal from the observation data in a recursive fashion where no extra steps of wavelet  ... 
doi:10.1016/j.sigpro.2005.06.009 fatcat:rduk34xzxbcjrhf6gr47qdo73m

Page 871 of Mathematical Reviews Vol. , Issue 80B [page]

1980 Mathematical Reviews  
Author’s summary: “The extended Kalman filter is an approxi- mate filter for nonlinear systems, based on first-order linearization.  ...  The present paper utilizes the Hilbert resolution space structure to derive an abstract Wiener-Hopf filter.  ... 

Modeling and estimation of multiresolution stochastic processes

M. Basseville, A. Benveniste, K.C. Chou, S.A. Golden, R. Nikoukhah, A.S. Willsky
1992 IEEE Transactions on Information Theory  
: one class of algorithms has a multigrid relaxation structure; a second uses the scale-to-scale whitening property of wavelet transforms for our models; and a third leads to a new class of Riccati equations  ...  The second, weaker notion of stationarity leads directly to a class of state space models on homogenous trees.  ...  of multiresolution measurements using multiscale, scale-recursive generalizations of Kalman filtering and smoothing.  ... 
doi:10.1109/18.119735 fatcat:wcdqwezcqfcwfmq7lsfltfviym

Log-polar wavelet energy signatures for rotation and scale invariant texture classification

Chi-Man Pun, Moon-Chuen Lee
2003 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper proposes an effective scheme for rotation and scale invariant texture classification using log-polar wavelet signatures.  ...  and scale invariant features.  ...  CONCLUSION We address the problem of rotation and scale invariance in image analysis and classification and propose an effective wavelet energy feature for rotation and scale invariant texture classification  ... 
doi:10.1109/tpami.2003.1195993 fatcat:bk4res6ywfarpg2cg7cww7nise

Efficient and reliable schemes for nonlinear diffusion filtering

J. Weickert, B.M.T.H. Romeny, M.A. Viergever
1998 IEEE Transactions on Image Processing  
Dr. ter Haar Romeny is author of a number of papers and book chapters.  ...  He is editor of a recent book on nonlinear diffusion theory in computer vision, and has initiated a number of international collaborations on these subjects. He is on the editorial board of the  ...  Maas for careful proofreading and helpful hints.  ... 
doi:10.1109/83.661190 pmid:18276260 fatcat:skgsoty2zvcfvmnrv3pols3enq

The Active Segmentation Platform for Microscopic Image Classification and Segmentation

Sumit K. Vohra, Dimiter Prodanov
2021 Brain Sciences  
In summary, differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical invariant objects.  ...  Image segmentation still represents an active area of research since no universal solution can be identified. Traditional image segmentation algorithms are problem-specific and limited in scope.  ...  by INCF and the Belgian Neuroinformatics Node in the scope of the ImageJ working group (accessed on 9 December 2021).  ... 
doi:10.3390/brainsci11121645 pmid:34942947 pmcid:PMC8699732 fatcat:ohdjbtweubh3rdiapb2zl26ixe

Morphological scale-space in image processing

Joseph H. Bosworth, Scott T. Acton
2003 Digital signal processing (Print)  
Finally, it is desired that a scale-space must be generated by an Euclidean invariant filtering procedure.  ...  This recursive scale generation is referred to as alternating sequential filtering. Examples of scale-spaces generated in this manner are shown in Figs. 12 and 13.  ... 
doi:10.1016/s1051-2004(02)00033-7 fatcat:zyjjgsmqnjc7xci6u2fodo5yne

Self-Similarity: Part I—Splines and Operators

Michael Unser, Thierry Blu
2007 IEEE Transactions on Signal Processing  
We specify the corresponding L-splines, which yield an extended class of fractional splines.  ...  CONCLUSION Starting from first principles-in particular, the notion of selfsimilarity-we pursued the task of specifying an extended class of scale-invariant L-splines together with some efficient signal  ...  Blu is the recipient of the 2003 best paper award (SP Theory and Methods) from the IEEE Signal Processing Society.  ... 
doi:10.1109/tsp.2006.890843 fatcat:pqcksq7vkja2ngppipfpgfofpe
« Previous Showing results 1 — 15 out of 16,760 results