Filters








987 Hits in 4.1 sec

CURVATURE BASED CORNER DETECTOR FOR DISCRETE, NOISY AND MULTI-SCALE CONTOURS

B. KERAUTRET, J.-O. LACHAUD, B. NAEGEL
2008 International journal of shape modeling  
We finally propose a novel corner detector, which is based on curvature estimation, and we provide a comprehensive set of experiments to compare it with many other classical corner detectors.  ...  Several recent curvature estimators 16,13,15 , which come from the discrete geometry community, can now process damaged data and integrate the amount of noise in their analysis.  ...  Acknowledgments A preliminary version of this work was presented at the International Symposium on Visual Computing, Las Vegas, NV, 2008, Special Track on Discrete and Computational Geometry and their  ... 
doi:10.1142/s0218654308001117 fatcat:dohknmivgbejxjrq4l4syxf62q

An efficient approach for boundary based corner detection by maximizing bending ratio and curvature

Serkan Kiranyaz, Hantao Liu, Miguel Ferreira, Moncef Gabbouj
2007 2007 9th International Symposium on Signal Processing and Its Applications  
The exact corner position within the window is then located accurately using the pixel-based curvature approximation.  ...  This paper introduces a novel corner detection method, which is based on the bending ratio of a moving window along with a local curvature approximation.  ...  Wavelet-based corner detection is a wellknown multi-scale corner detection technique, which can present the "structural" importance of the corners in various scales.  ... 
doi:10.1109/isspa.2007.4555467 dblp:conf/isspa/KiranyazLFG07 fatcat:dnjysbpq3vdxtbcxwz5xfu423e

Contour-Based Corner Detection and Classification by Using Mean Projection Transform

Seyed Kahaki, Md Nordin, Amir Ashtari
2014 Sensors  
The first step is to extract corner candidates using MPT based on the integral properties of the local contours in both the horizontal and vertical directions.  ...  The proposed method presents fewer false-positive (FP) and false-negative (FN) points compared with recent standard corner detection techniques, especially in comparison with curvature scale space (CSS  ...  reviewers for their constructive comments.  ... 
doi:10.3390/s140304126 pmid:24590354 pmcid:PMC4003934 fatcat:ioop4byfgvf3xdfrjk3ecodyje

Corner detection using the point-to-centroid distance technique

Shizheng Zhang, Luwen Huangfu, Zhifeng Zhang, Sheng Huang, Pu Li, Heng Wang
2020 IET Image Processing  
Extensive experimental results demonstrate that the PCD technique is effective and simultaneously efficient for corner detection compared with six other contour-based corner detectors in terms of two commonly  ...  Based on PCD behaviours, the authors propose a novel corner detector.  ...  Curvature scale space (CSS) [18] is the most classical contourbased corner detector and after which many CSS-based corner detectors have been proposed and modelled, such as multi-scale curvature product  ... 
doi:10.1049/iet-ipr.2020.0164 fatcat:x2mgln2lj5dv5k6yjwlxeuppny

Shape description based on bag of salience points

Glauco V. Pedrosa, Agma J. M. Traina, Celia A. Z. Barcelos
2015 Proceedings of the 30th Annual ACM Symposium on Applied Computing - SAC '15  
Each salience point, after extracted from the shape contour, is represented by its curvature value using a multi-scale procedure proposed in this work.  ...  Salient points are very important for image description because they are related to the visually most important parts of the image, leading to a compact and more discriminative representation close to  ...  Acknowledgements This work is supported, in part, by FAPESP, CAPES, SticAMSUD, the RESCUER project, funded by the European Commission (Grant 614154) and by the Brazilian National Council for Scientific  ... 
doi:10.1145/2695664.2695838 dblp:conf/sac/PedrosaTB15 fatcat:ydch3rfhind4jfvrjaf7kzf64a

Multi-Scale and Multi-Orientation Medical Image Analysis [chapter]

Bart M. ter Haar Romeny
2010 Biomedical Image Processing  
The multi-scale image stack (the deep structure) contains a hierarchy of the data and is exploited by edge focusing, retrieval by manipulations of the singularities (top-points) in this space, and multi-scale  ...  Images are discrete, measured data. The optimal aperture for an observation with as little artefacts as possible, is derived from first principles and leads to a Gaussian profile.  ...  [10] is a multi-scale shape analysis, based on a local zero and a high principal curvature, which indicates a cylindric shape.  ... 
doi:10.1007/978-3-642-15816-2_7 fatcat:s7e6i4d24rbs3k7dclgy64jbeq

Robust Image Corner Detection Based on the Chord-to-Point Distance Accumulation Technique

Mohammad Awrangjeb, Guojun Lu
2008 IEEE transactions on multimedia  
Many contour-based image corner detectors are based on the curvature scale-space (CSS). We identify the weaknesses of the CSS-based detectors.  ...  We propose a complete corner detection technique based on the chord-to-point distance accumulation (CPDA) for the discrete curvature estimation.  ...  The contour-based corner detectors [3] , [5] - [11] are mainly based on the curvature scale-space (CSS) (contours can be *corresponding author. open or close).  ... 
doi:10.1109/tmm.2008.2001384 fatcat:yndtghw2xjgbnksyyspiut2tye

Analysis of Noisy Digital Contours with Adaptive Tangential Cover

Phuc Ngo, Isabelle Debled-Rennesson, Bertrand Kerautret, Hayat Nasser
2017 Journal of Mathematical Imaging and Vision  
This study leads to the proposal of several applications of ATC on noisy digital contours: dominant point detection, contour length estimator, tangent/normal estimator, detection of convex and concave  ...  To tackle this issue, we investigate in this paper a discrete structure, named Adaptive Tangential Cover (ATC), which is based on the notion of tangential cover and on a local noise estimator.  ...  Acknowledgment The authors would like to thank the referees for useful comments.  ... 
doi:10.1007/s10851-017-0723-7 fatcat:gnj7lnfqfrgyvok2tnikvsmkjq

Corner detection based on gradient correlation matrices of planar curves

Xiaohong Zhang, Hongxing Wang, Andrew W.B. Smith, Xu Ling, Brian C. Lovell, Dan Yang
2010 Pattern Recognition  
An efficient and novel technique is developed for detecting and localizing corners of planar curves.  ...  Experimental results demonstrate that the GCM detector has a strong corner position response, along with a high detection rate and good localization performance.  ...  Acknowledgments The work described in this paper was partially supported by Science and Technology Key Project of Chongqing (Grant no. 2009AC2057) the National Natural Science Foundation of China (Grant  ... 
doi:10.1016/j.patcog.2009.10.017 fatcat:phkpfm7ga5bjhki54qqgxs74fq

Multi-scale Analysis of Discrete Contours for Unsupervised Noise Detection [chapter]

Bertrand Kerautret, Jacques-Olivier Lachaud
2009 Lecture Notes in Computer Science  
The thickness is tuned by a user and set globally for the contour, which requires both supervision and non-adaptive contour processing.  ...  Based on the asymptotic properties of maximal segments, it also detects curved and flat parts of the contour.  ...  Based on this, discrete tangent and curvature estimators robust to noise have been developed [2, 3] .  ... 
doi:10.1007/978-3-642-10210-3_15 fatcat:p5o2qqoewbgbhg7hf5k4fp54ia

Multi-scale crest line extraction based on half Gaussian Kernels

Baptiste Magnier, Arezki Aberkane, Philippe Borianne, Philippe Montesinos, Christophe Jourdan
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In this paper we propose a new ridge/valley detection method in images based on the difference of rotating Gaussian semi filters adapted in a multi-scale process.  ...  Crest line extraction has always been a challenging task in image processing and its applications. It is possible to detect ridges and valleys in images using second order filters.  ...  (CIRAD) for providing the enabling environment and financial resources that allowed us to achieve this work.  ... 
doi:10.1109/icassp.2014.6854575 dblp:conf/icassp/MagnierABMJ14 fatcat:gflfjlhgdjdb7dnp5gjfpacqdm

Multi-Scale Salience Distance Transforms

Paul L. Rosin, Geoff A. W. West
1993 Procedings of the British Machine Vision Conference 1993  
This paper proposes two things: (1) a multi-scale distance transform to overcome the need to choose edge thresholds and scale and (2) the addition of various saliency factors such as edge strength, length  ...  and curvature to the basic distance transform to improve its effectiveness.  ...  Recently, some work has been carried out in measuring the saliency of every point in an image based on edge length and curvature [6] and orientation and curvature [7] .  ... 
doi:10.5244/c.7.58 dblp:conf/bmvc/RosinW93 fatcat:qvnfrnmrqbbbbfxxu6fzd2gex4

Local Invariant Feature Detectors: A Survey

Tinne Tuytelaars, Krystian Mikolajczyk
2007 Foundations and Trends in Computer Graphics and Vision  
In this survey, we give an overview of invariant interest point detectors, how they evolved over time, how they work, and what their respective strengths and weaknesses are.  ...  We begin with defining the properties of the ideal local feature detector.  ...  Acknowledgments The authors would like to acknowledge support from the Network of Excellence PASCAL and the Flemish Fund for Scientific Research FWO.  ... 
doi:10.1561/0600000017 fatcat:t5e7h3nhtfgozcn2czsuc52r34

OBSTACLE DETECTION USING MONO VISION CAMERA AND LASER SCANNER

Sandip Mahajan .
2013 International Journal of Research in Engineering and Technology  
Only one sensor is capable to take the decision but multi sensor decision is more precise and accurate.  ...  In this proposed system, mono vision camera and laser scanner is used to detect the obstacles for vehicle.  ...  In addition to voting for object position, we cast each of the votes through a set of discrete scales.  ... 
doi:10.15623/ijret.2013.0212117 fatcat:t3fqhw4is5bdpa2lzry4wtweva

A discrete geometry approach for dominant point detection

Thanh Phuong Nguyen, Isabelle Debled-Rennesson
2011 Pattern Recognition  
We propose two fast methods for dominant point detection and polygonal representation of noisy and possibly disconnected curves based on a study of the decomposition of the curve into the sequence of maximal  ...  The second method is deduced from the first one based on a multi-width approach to obtain a non-parametric method that uses no threshold for working with noisy curves.  ...  Acknowledgment We would like to thank anonymous reviewers for their valuable comments to improve this work.  ... 
doi:10.1016/j.patcog.2010.06.022 fatcat:wqzg66unqfe4hm5si7ovoj3fnq
« Previous Showing results 1 — 15 out of 987 results