489 Hits in 9.9 sec

Illumination invariant face recognition based on the new phase features

Dan Zhang, Jianjia Pan, Yuan Yan Tang, Chunzhi Wang
2010 2010 IEEE International Conference on Systems, Man and Cybernetics  
Hilbert transform is adopted on the IMFs to get the analytical local features. Recently, bidimensional version has been studied for advanced image processing.  ...  It contains two key parts: Empirical Mode Decomposition (EMD) and Hilbert transform.  ...  Therefore, the quantity named Phase Congruency (PC) is exploited as a frequencybased approach for feature detection.  ... 
doi:10.1109/icsmc.2010.5641808 dblp:conf/smc/ZhangPTW10 fatcat:54gziviwbvhzhiy6sy6k7quc5e

Histogram of oriented phase (HOP): a new descriptor based on phase congruency

Hussin K. Ragb, Vijayan K. Asari, Sos S. Agaian, Sabah A. Jassim
2016 Mobile Multimedia/Image Processing, Security, and Applications 2016  
In this paper we present a low level image descriptor called Histogram of Oriented Phase based on phase congruency concept and the Principal Component Analysis (PCA).  ...  The proposed features can be formed by extracting the phase congruency information for each pixel in the image with respect to its neighborhood.  ...  Using ( ) and Hilbert Transform ( ), The local energy function ( ) can be defined as given in Eq. 2 [19] , [25] , [26] . ( ) = ( ) + ( ) (2) Phase congruency can be computed by convolving the two dimensional  ... 
doi:10.1117/12.2225159 fatcat:ym7yrxqcgbh3lp4quic6fke2xe

The Monogenic Scale Space on a Rectangular Domain and its Features

Michael Felsberg, Remco Duits, Luc Florack
2005 International Journal of Computer Vision  
The features of the monogenic scale space, including local amplitude, local phase, local orientation, local frequency, and phase congruency, are much easier to interpret in terms of image features evolving  ...  Previous implementations of the monogenic scale space are Fourier transform based, and therefore suffer from the implicit periodicity in case of finite domains.  ...  In general, the monogenic scale space can be used for any kind of phase based image processing method, i.e., all methods which are somehow based on the Hilbert transform or quadrature filters (e.g.  ... 
doi:10.1007/s11263-005-1843-x fatcat:ukn3avknofflrnqanikjjnenhu

Optimized multimodal biometric system based fusion technique for human identification

Muthana H. Hamd, Rabab A. Rasool
2020 Bulletin of Electrical Engineering and Informatics  
First, the computations cost is greatly reduced by eliminating the feature extraction phase and considering only the detected face features from the phase congruency.  ...  A 2-D multi-scale phase congruency (2D-MSPC) software for detecting and evaluation of image features could appropriately tune many parameters for optimal image features detection, these parameters are  ...  Unlike gradient-based feature detectors, which can only detect the first or second derivative features (also called step features), phase congruency correctly detects all kind of phase angle related features  ... 
doi:10.11591/eei.v9i6.2632 fatcat:z7lhpuwtefg3zbzt4jp7yaznyi

Monogenic signal theory based feature similarity index for image quality assessment

Xue-Gang Luo, Hua-Jun Wang, Sen Wang
2015 AEU - International Journal of Electronics and Communications  
This paper proposes a novel feature similarity (RMFSIM) index for full reference IQA based on monogenic signal theory.  ...  Recent phase congruency, which is a dimensionless, normalized feature of a local structure, is used as the structure similarity feature.  ...  Monogenic phase congruency Phase congruency is a method for feature detection that is different from the method based on gradient in spatial domain, which can only detect step features, phase congruency  ... 
doi:10.1016/j.aeue.2014.07.015 fatcat:lyjxr7ylpjgqvhc6birsrwhjzq

Histogram of Oriented Phase and Gradient (HOPG) Descriptor for Improved Pedestrian Detection

Hussin K Ragb, Vijayan K Asari
2016 IS&T International Symposium on Electronic Imaging Science and Technology  
The experimental results show that the human detection system based on the proposed features has less error rates and better detection performance over a set of state of the art feature extraction methodologies  ...  This paper presents a new pedestrian detection descriptor named The proposed descriptor extracts the image information using both the gradient and phase congruency concepts.  ...  Assume ( ) is the same as the input signal ( ) filtered from a component and ( ) is 90˚ phase shift of ( ) (Hilbert Transform).  ... 
doi:10.2352/issn.2470-1173.2016.3.vstia-511 fatcat:dw23tvodojcx5kjkquqoi6bonu

An analysis of local energy and phase congruency models in visual feature detection

Y. K. Aw, Robyn Owens, John Ross
1998 The Journal of the Australian Mathematical Society Series B Applied Mathematics  
The local energy model provides an alternative approach, detecting a variety of feature types in a single pass by analysing order in the phase components of the Fourier transform of the image.  ...  A variety of approaches have been developed for the detection of features such as edges, lines, and corners in images.  ...  The local energy function is defined as the norm of an energy vector whose two bases are the image itself and its Hilbert transform.  ... 
doi:10.1017/s0334270000012406 fatcat:w37qysi6njd4hmeukz3zaazqoa

Towards better performance: phase congruency based face recognition

Muthana H. Hamd, Rabab A. Rasool
2020 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
In this paper, two novel techniques are introduced for developing a low-cost human identification system based on face recognition.  ...  Phase congruency is an edge detector and measurement of the significant feature in the image. It is a robust method against contrast and illumination variation.  ...  Alavi in [7] developed a two-dimensional multi-scale phase congruency (2D-MSPC) software for detecting and evaluation of image features.  ... 
doi:10.12928/telkomnika.v18i6.17300 fatcat:iukelhztffhbnbb24e7ij27ns4

Improving Phase-Congruency Based Feature Detection through Automatic Scale-Selection [chapter]

Veit U. B. Schenk, Michael Brady
2003 Lecture Notes in Computer Science  
In this paper we present a novel method for computing phasecongruency by automatically selecting the range of scales over which a locally one-dimensional feature exists.  ...  Our method is based on the use of local energy computed in a multi-resolution steerable filter framework.  ...  Phase congruency can be shown to be directly related to local energy [10] which in the one-dimensional case is defined as LE 1D = I 2 + H 2 (2) where I is the input signal and H its Hilbert transform  ... 
doi:10.1007/978-3-540-24586-5_14 fatcat:vtpaudygsjgk5hgwfp7gbwafyu

Edge Detection Methods Based on Differential Phase Congruency of Monogenic Image [article]

Yan Yang, Kit Ian Kou, Cuiming Zou
2016 arXiv   pre-print
Edge Detection Methods Based on Differential Phase Congruency of Monogenic Image Abstract: Edge detection has been widely used in medical image processing and automatic diagnosis.  ...  Some novel edge detection algorithms,based on the monogenic scale-space, are proposed by detecting points of local extrema in local amplitude, the local attenuation and modified differential phase congruency  ...  The authors acknowledge financial support from the National Natural  ... 
arXiv:1607.00097v2 fatcat:qt6j6zg4ifhadjhp7bztk2xeb4

The Conformal Monogenic Signal of Image Sequences [chapter]

Lennart Wietzke, Gerald Sommer, Oliver Fleischmann, Christian Schmaltz
2009 Lecture Notes in Computer Science  
The phase congruency measure can be directly applied to detect rotationally invariant i1D and i2D image structures.  ...  One important local structural feature is the phase φ which can be calculated by means of the Hilbert transform [10] .  ...  //Generalized Hilbert transform in conformal space double a = pow(x1,2)+pow(x2,2)+pow(x3,2)+pow(x4,2); double pf = pow(pow(Fine ,2) + a,-2.5); double pc = pow(pow(Coarse,2) + a,-2.5); double f = Image3D  ... 
doi:10.1007/978-3-642-03061-1_15 fatcat:wfuhflaguzaxxl76jaxrdtnfkq

Edge, Ridge, and Blob Detection with Symmetric Molecules [article]

Rafael Reisenhofer, Emily J. King
2019 arXiv   pre-print
We present a novel approach to the detection and characterization of edges, ridges, and blobs in two-dimensional images which exploits the symmetry properties of directionally sensitive analyzing functions  ...  The proposed feature detectors are inspired by the notion of phase congruency, stable in the presence of noise, and by definition invariant to changes in contrast.  ...  Starck for suggesting that we extend the framework to the case of blob detection and M. Schäfer for insightful discussions on the subject of α-molecules. We are grateful to Q.  ... 
arXiv:1901.09723v2 fatcat:tzp6gg2vgrbndhzzejwjtdxgxi

A method for underwater image analysis using bi-dimensional empirical mode decomposition technique

Bo Liu, Yan Lin
2012 Ocean Systems Engineering  
We developed a joint algorithm based on BEMD and Canny operator to extract multi-pixel edge features at multiple scales in IMFs sub-images.  ...  The performance of the multipixel edge extraction algorithm for processing underwater image is demonstrated in the contrast experiment with both the proposed method and the phase congruency edge detection  ...  The use of phase congruency for marking image features has significant advantages over gradient-based method, since phase congruency is an illumination and SD h i k 1 - ( ) x y , ( ) h ik x y , ( ) - 2  ... 
doi:10.12989/ose.2012.2.2.137 fatcat:ttahppgqvbfffks4r2fiqjff54

Modeling edges at subpixel accuracy using the local energy approach

M. Kisworo, S. Venkatesh, G. West
1994 IEEE Transactions on Pattern Analysis and Machine Intelligence  
A candidate edge is modeled as one of a number of parametric edge models, and the fit is refined by a least-squared error fitting technique.  ...  In this paper we describe a new technique for 1-D and 2-D edge feature extraction to subpixel accuracy using edge models and the local energy approach.  ...  To locate these points of local phase congruency, it is necessary to consider a quadrature pair of functions, namely, the original profile and its Hilbert transform to define local energy.  ... 
doi:10.1109/34.277593 fatcat:mnjmvrrrkfeh3kdutpvwu5ssum

Feature detection algorithm based on a visual system model

E. Peli
2002 Proceedings of the IEEE  
a minimal level of phase congruence across scales.  ...  All parameters are directly derived from visual models and from measurements on human observers.  ...  The quadrature sine-phase filter can be computed from the inphase filter using a Hilbert transform [58] .  ... 
doi:10.1109/5.982407 fatcat:dhacdxnywba3pndbdrahbxb5wu
« Previous Showing results 1 — 15 out of 489 results