Filters








27,622 Hits in 4.1 sec

Pyramid segmentation algorithms revisited

R. Marfil, L. Molina-Tanco, A. Bandera, J.A. Rodríguez, F. Sandoval
2006 Pattern Recognition  
Segmentation algorithms based on regular and irregular pyramids are described, together with the data structures and decimation procedures which encode and manage the information in the pyramid.  ...  The main goal of this work is to compare pyramidal structures proposed to solve segmentation tasks.  ...  Bertolino for their unselfish help. Special thanks are due to Dr. J. M. Jolion for his aid to implement the colour irregular pyramid and provides us the source code of the algorithm proposed in Ref.  ... 
doi:10.1016/j.patcog.2006.02.017 fatcat:f744w7onubh6ppz43r23vz2bkm

Multidirectional motion estimation algorithm for frame rate up-conversion

Songhyun Yu, Jechang Jeong, N. Mastorakis, V. Mladenov, A. Bulucea
2017 MATEC Web of Conferences  
In this paper, we propose a new motion estimation algorithm for motion-compensated frame rate up-conversion.  ...  To reduce computational complexity, it constructs a hierarchical structure using Gaussian image pyramid and unidirectionally estimates motion vectors (MVs) between two original frames at the top level.  ...  Several studies proposed low-complexity FRUC algorithms; [13] used Gaussian pyramid structure and Laplacian pyramid structure in ME step, and [15] used subsampling of the original image for ME.  ... 
doi:10.1051/matecconf/201712505002 fatcat:xmodoei2i5galogaxfg4plhsbq

Mixed-Resolution Patch-Matching [chapter]

Harshit Sureka, P. J. Narayanan
2012 Lecture Notes in Computer Science  
Finding the optimum nearest-neighbors of each patch using a global search of the image is expensive. Optimality is often sacrificed for speed as a result.  ...  We present the Mixed-Resolution Patch-Matching (MRPM) algorithm that uses a pyramid representation to perform fast global search.  ...  The problem of patch-matching is to find K most similar patches in image B, for every patch in image A.  ... 
doi:10.1007/978-3-642-33783-3_14 fatcat:5vphfw3zbjcoznoqkghe57vrzy

An optimized texture-by-numbers synthesis method and its visual applications

Jing Fan, XiaoYing Shi, Zhan Zhou, Ying Tang
2013 Science China Information Sciences  
Besides distance metrics to measure image similarities are specifically designed for different images to better match human visual perception for structural patterns and a user study is conducted to verify  ...  The framework of texture-by-numbers (TBN) synthesizes images of global-varying patterns with intuitive user control.  ...  In particular, feature information is added into the global metric for structural TBN images to do better feature matching.  ... 
doi:10.1007/s11432-013-4834-5 fatcat:fedusysyjnaotgs7z5j7og6g6u

Laplacian Patch-Based Image Synthesis

Joo Ho Lee, Inchang Choi, Min H. Kim
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Recently, the image gradients in each level of the image pyramid are used for enhancing edge structure in addition to coherent patchbased synthesis [11] .  ...  Patch-based image synthesis has been enriched with global optimization on the image pyramid. Successively, the gradient-based synthesis has improved structural coherence and details.  ...  to Sung-Hyun Choi (Samsung) for helpful comments.  ... 
doi:10.1109/cvpr.2016.298 dblp:conf/cvpr/LeeCK16 fatcat:ykfqybf3drenbdavh4z26xmywe

Learning weighted geometric pooling for image classification

Chaoqun Weng, Hongxing Wang, Junsong Yuan
2013 2013 IEEE International Conference on Image Processing  
Local feature extraction, coding, pooling, and image classification are the four typical steps for the state-of-the-art visual recognition systems.  ...  Experiments on 15-scene dataset validate the advantages of our proposed algorithms.  ...  The successes of spatial pyramid matching [5] and receptive field learning [7] have illustrated the effectiveness of using spatial pyramid structure and adaptive receptive field structure for image  ... 
doi:10.1109/icip.2013.6738784 dblp:conf/icip/WengWY13 fatcat:zi4h7dfsfzgsri33qbmqwuqlaa

Pyramid algorithms for perceptual organization

Azriel Rosenfeld
1986 Behavoir research methods, instruments & computers  
This paper describes a set of pyramid-based algorithms that can detect and extract these types of structure; included are algorithms for inferring three-dimensional information from images and for processing  ...  If implemented in parallel on cellular pyramid hardware, these algorithms require processing times on the order of the logarithm of the image diameter.  ...  The rapid detection of global structure in images is an important, but not well-understood, capability of the human visual system.  ... 
doi:10.3758/bf03201434 fatcat:brjet6fjxbbjzew3ernx6qvth4

Wavelet contrast-based image inpainting with sparsity-driven initialization

Philipp Tiefenbacher, Michael Sirch, Mohammadreza Babaee, Gerhard Rigoll
2016 2016 IEEE International Conference on Image Processing (ICIP)  
Image inpainting is the task of removing undesired objects or flaws in images. This work advances an exemplar-based global optimization image inpainting algorithm.  ...  Wavelet contrasts reduce computational complexity in comparison to wavelet histograms while preserving their ability of measuring the density of image texture.  ...  We want to consider the image structure via wavelets in the cost metric while preserving a fast inpainting algorithm.  ... 
doi:10.1109/icip.2016.7533016 dblp:conf/icip/TiefenbacherSBR16 fatcat:slfiae5uvzbg7jfi43zblgniva

Lumbar Spine Classification using Pyramidal Histogram of Oriented Gradients

A. Beulah, B. K. Divya Bharathi
2016 Indian Journal of Science and Technology  
After building a model with SVM classification algorithm, classify the MR Images for discs and vertebrae separately. Findings: The accuracy is calculated to verify the performance of this work.  ...  Methods: The classification of the lumbar structure is done using Pyramidal Histogram of Gradients (PHOG). The PHOG technique is applied on the MR Image to select the basic intensity level features.  ...  Here each small grids models a different layer in the pyramidal structure of an image. The initial step is to find the Histogram of Oriented Gradients (HOG). Then find HOG for all the spatial levels.  ... 
doi:10.17485/ijst/2016/v9i32/93186 fatcat:yysfvb2tgjhd7mwwmp52m3oa6e

Efficient Implementation Of Optical Flow Algorithm Based On Directional Filters On A Gpu Using Cuda

Ivar Austvoll, Robert Hegner, Tom Ryen, Guido Schuster
2011 Zenodo  
Publication in the conference proceedings of EUSIPCO, Barcelona, Spain, 2011  ...  Figure 1 shows the structure of the Basic Algorithm. Each frame in the image sequence is decomposed using a set of directional filters to reveal the structure of the image.  ...  For most of the image sequences, the accuracy of the Pyramid Algorithm is better than or comparable to the accuracy of the OpenCV implementation of the Lucas-Kanade Pyramid algorithm.  ... 
doi:10.5281/zenodo.42459 fatcat:3ritrnu4obegreymvuse44tepy

Supporting divide-and-conquer algorithms for image processing

Quentin F. Stout
1987 Journal of Parallel and Distributed Computing  
Divide-and-conquer is an important algorithm strategy, but it is not widely used in image processing.  ...  However, divide-andconquer algorithms use parallel computers in a different manner than, say, local edge detection, so machines optimized for local neighborhood algorithms may be poor for divide-andumquer  ...  For example, to find the average gray level in an image, find the average in each quadrant, and average the averages.  ... 
doi:10.1016/0743-7315(87)90010-4 fatcat:cy2aq4y7rrehfngdfxqdvdeu3q

Segmentation Graph Hierarchies [chapter]

Yll Haxhimusa, Walter Kropatsch
2004 Lecture Notes in Computer Science  
The aim of this paper is to build a minimum weight spanning tree (M ST ) of an image in order to find region borders quickly in a bottom-up 'stimulus-driven' way based on local differences in a specific  ...  Low-level cue image segmentation in a bottom-up way, cannot and should not produce a complete final "good" segmentation.  ...  Thus, the regular image pyramid is an efficient structure for fast grouping and access to image objects in top-down and bottom-up processes [14] , because of the apriori known structure.  ... 
doi:10.1007/978-3-540-27868-9_36 fatcat:bg662gsk7vdrhmcntalq2q6vw4

A hierarchical framework for robust extraction and delineation of geometric features

J.M Jolion
1993 Pattern Recognition  
Pyramid Hierarchical reasoning Line detection and delineation Range image segmentation Gray image multi-thresholding  ...  Several examples in multi-thresholding of gray images, line detection and delineation, and range image segmentation are presented.  ...  Note that this algorithm extracted the same clusters when applied to the global histogram of the image. ~4~ In this experiment, we used a pyramid of base 256 x 256 cells.  ... 
doi:10.1016/0031-3203(93)90136-k fatcat:jvfsx3nfynbqdjtgebfqewfeym

The DTI Challenge: Toward Standardized Evaluation of Diffusion Tensor Imaging Tractography for Neurosurgery

Sonia Pujol, William Wells, Carlo Pierpaoli, Caroline Brun, James Gee, Guang Cheng, Baba Vemuri, Olivier Commowick, Sylvain Prima, Aymeric Stamm, Maged Goubran, Ali Khan (+17 others)
2015 Journal of Neuroimaging  
In addition, the structure of disagreement among methods was similar across hemispheres despite the anatomical distortions caused by pathological tissues.  ...  Although most methods found projections of the pyramidal tract from the medial portion of the motor strip, only a few algorithms could trace the lateral projections from the hand, face, and tongue area  ...  Geller for providing editorial assistance with the manuscript.  ... 
doi:10.1111/jon.12283 pmid:26259925 pmcid:PMC4641305 fatcat:kd4sj6sqtfee3gsz3fk7aljxqe

Hierarchical Region Based Template Matching Technique for Global Motion Reduction of Coronary Cineangiograms

Kulathilake K. A. S. H., Ranathunga L., Constantine G. R., Abdullah N. A.
2015 Journal of clean energy technologies  
The global motion occurring due to the heart beat makes great disturbance to obtain the visual alignment among the vessel structure shown in the CCA frames.  ...  The Coronary Cineangiogram (CCA) is an invasive medical image modality which is used to determine the stenosis in the Coronary Arteries.  ...  Step 3: Apply template matching for the other levels The result image contents are copied in to the upper layer of the pyramid to effectively find the matched position.  ... 
doi:10.7763/ijcte.2015.v7.948 fatcat:3y5tmowiz5hftouw3gi6pnpeva
« Previous Showing results 1 — 15 out of 27,622 results