scholarly journals Robust Affine Invariant Descriptors

2011 ◽  
Vol 2011 ◽  
pp. 1-15 ◽  
Author(s):  
Jianwei Yang ◽  
Zirun Chen ◽  
Wen-Sheng Chen ◽  
Yunjie Chen
Keyword(s):  
Additive Noise ◽  
Experimental Results ◽  
Affine Invariant ◽  
General Contour ◽  
Robust To Noise ◽  
Gray Values

An approach is developed for the extraction of affine invariant descriptors by cutting object into slices. Gray values associated with every pixel in each slice are summed up to construct affine invariant descriptors. As a result, these descriptors are very robust to additive noise. In order to establish slices of correspondence between an object and its affine transformed version, general contour (GC) of the object is constructed by performing projection along lines with different polar angles. Consequently, affine in-variant division curves are derived. A slice is formed by points fall in the region enclosed by two adjacent division curves. To test and evaluate the proposed method, several experiments have been conducted. Experimental results show that the proposed method is very robust to noise.

scholarly journals Extraction of Affine Invariant Features Using Fractal

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Jianwei Yang ◽  
Guosheng Cheng ◽  
Ming Li
Keyword(s):  
Pattern Recognition ◽  
Feature Vector ◽  
Fractal Dimensions ◽  
Input Pattern ◽  
Experimental Results ◽  
Central Projection ◽  
Affine Invariant ◽  
Invariant Features ◽  
General Contour ◽  
New Feature

An approach based on fractal is presented for extracting affine invariant features. Central projection transformation is employed to reduce the dimensionality of the original input pattern, and general contour (GC) of the pattern is derived. Affine invariant features cannot be extracted from GC directly due to shearing. To address this problem, a group of curves (which are called shift curves) are constructed from the obtained GC. Fractal dimensions of these curves can readily be computed and constitute a new feature vector for the original pattern. The derived feature vector is used in question for pattern recognition. Several experiments have been conducted to evaluate the performance of the proposed method. Experimental results show that the proposed method can be used for object classification.

scholarly journals Cutting Affine Moment Invariants

2012 ◽  
Vol 2012 ◽  
pp. 1-12 ◽  
Author(s):  
Jianwei Yang ◽  
Ming Li ◽  
Zirun Chen ◽  
Yunjie Chen
Keyword(s):  
Image Processing ◽  
Closed Curve ◽  
Experimental Results ◽  
Moment Invariants ◽  
Affine Invariant ◽  
Original Image ◽  
Invariant Features ◽  
General Contour ◽  
Classification Tasks ◽  
Affine Moment Invariants

The extraction of affine invariant features plays an important role in many fields of image processing. In this paper, the original image is transformed into new images to extract more affine invariant features. To construct new images, the original image is cut in two areas by a closed curve, which is called general contour (GC). GC is obtained by performing projections along lines with different polar angles. New image is obtained by changing gray value of pixels in inside area. The traditional affine moment invariants (AMIs) method is applied to the new image. Consequently, cutting affine moment invariants (CAMIs) are derived. Several experiments have been conducted to evaluate the proposed method. Experimental results show that CAMIs can be used in object classification tasks.

A Novel Illumination Compensation Method Using Wavelet Packet Transformation

2011 ◽  
Vol 317-319 ◽  
pp. 897-900
Author(s):  
Zhen Hua Zhao ◽  
Xiao Hong Hao
Keyword(s):  
Multiplicative Noise ◽  
Additive Noise ◽  
Recognition Performance ◽  
Wavelet Packet ◽  
Recognition Rate ◽  
Face Image ◽  
Experimental Results ◽  
Illumination Compensation ◽  
Wavelet Packet Transformation ◽  
Facial Images

A novel illumination compensate method is proposed in this paper to improve recognition performance. A modified lighting model called Lambertin which includes additive noise and multiplicative noise are presented firstly. Then, additive noise is removed by using wavelet packet transformation. Next, the processed image is transformed into logarithm domain and the multiplicative noise, which has been named additive noise, is removed by means of the same above algorithm. Finally, a compensated face image is obtained. We examine the proposed method on Yale extended B database compared with other methods. Experimental results show that our algorithm improves by 3%~12% recognition rate. It can effectively adjust the facial images for varying illumination conditions and also improve the recognition performance and robustness.

EVOLUTIONS OF PLANAR POLYGONS

1995 ◽  
Vol 09 (06) ◽  
pp. 991-1014 ◽  
Author(s):  
ALFRED M. BRUCKSTEIN ◽  
GUILLERMO SAPIRO ◽  
DORON SHAKED
Keyword(s):  
General Theory ◽  
Experimental Results ◽  
Curve Evolution ◽  
Affine Invariant ◽  
Polygonal Approximation ◽  
Curve Shortening Flow ◽  
Planar Curves ◽  
Cyclic Pursuit ◽  
Invariant Differential ◽  
Curve Shortening

Evolutions of closed planar polygons are studied in this work. In the first part of the paper, the general theory of linear polygon evolutions is presented, and two specific problems are analyzed. The first one is a polygonal analog of a novel affine-invariant differential curve evolution, for which the convergence of planar curves to ellipses was proved. In the polygon case, convergence to polygonal approximation of ellipses, polygo nal ellipses, is proven. The second one is related to cyclic pursuit problems, and convergence, either to polygonal ellipses or to polygonal circles, is proven. In the second part, two possible polygonal analogues of the well-known Euclidean curve shortening flow are presented. The models follow from geometric considerations. Experimental results show that an arbitrary initial polygon converges to either regular or irregular polygonal approximations of circles when evolving according to the proposed Euclidean flows.

scholarly journals DoPAMINE: Double-Sided Masked CNN for Pixel Adaptive Multiplicative Noise Despeckling

2019 ◽  
Vol 33 ◽  
pp. 4031-4038
Author(s):  
Sunghwan Joo ◽  
Sungmin Cha ◽  
Taesup Moon
Keyword(s):  
Neural Network ◽  
Multiplicative Noise ◽  
Additive Noise ◽  
State Of The Art ◽  
Unbiased Estimate ◽  
Experimental Results ◽  
Fine Tuning ◽  
Noisy Image ◽  
Supervised Training ◽  
The Given

We propose DoPAMINE, a new neural network based multiplicative noise despeckling algorithm. Our algorithm is inspired by Neural AIDE (N-AIDE), which is a recently proposed neural adaptive image denoiser. While the original NAIDE was designed for the additive noise case, we show that the same framework, i.e., adaptively learning a network for pixel-wise affine denoisers by minimizing an unbiased estimate of MSE, can be applied to the multiplicative noise case as well. Moreover, we derive a double-sided masked CNN architecture which can control the variance of the activation values in each layer and converge fast to high denoising performance during supervised training. In the experimental results, we show our DoPAMINE possesses high adaptivity via fine-tuning the network parameters based on the given noisy image and achieves significantly better despeckling results compared to SAR-DRN, a state-of-the-art CNN-based algorithm.

Spectra analysis and network coherence for weighted folded hypercube

2019 ◽  
Vol 33 (11) ◽  
pp. 1950094 ◽  
Author(s):  
Meifeng Dai ◽  
Jiaojiao He ◽  
Huiling Wu ◽  
Xianbin Wu
Keyword(s):  
Steady State ◽  
Additive Noise ◽  
Second Order ◽  
Weight Factor ◽  
Consensus Process ◽  
Spectra Analysis ◽  
Laplacian Eigenvalues ◽  
Low Coherence ◽  
Folded Hypercube ◽  
Robust To Noise

Weighted folded hypercube is an charming variance of the famous hypercube and is superior to the weighted hypercube in many criteria. We mainly study the scaling of network coherence for the weighted folded hypercube that is controlled by a weight factor. Network coherence quantifies the steady-state variance of these fluctuations, and it can be regarded as a measure of robustness of the consensus process to the additive noise. If networks with small steady-state variance have better network coherence, it can be regarded as more robust to noise than networks with low coherence. We firstly calculate the spectra of weighted folded hypercube and obtain the leading terms of network coherence that are quantified as the sum and square sum of reciprocals of all nonzero Laplacian eigenvalues. Finally, the results show that network coherence depends on iterations and weight factor. Meanwhile, with larger order, the scatings of the first- and second-order network coherence of weighted folded hypercube decrease with the increasing of weight factor.

EXPERIMENTAL STUDY OF IMPULSIVE SYNCHRONIZATION OF CHAOTIC AND HYPERCHAOTIC CIRCUITS

1999 ◽  
Vol 09 (07) ◽  
pp. 1393-1424 ◽  
Author(s):  
MAKOTO ITOH ◽  
TAO YANG ◽  
LEON O. CHUA
Keyword(s):  
Spread Spectrum ◽  
Communication Systems ◽  
Additive Noise ◽  
Experimental Results ◽  
Impulsive Synchronization ◽  
State Variable ◽  
Chua’S Oscillator ◽  
Chaotic Circuits ◽  
Driving Circuit ◽  
Short Impulse

In this paper, experimental results on impulsive synchronization of two kinds of chaotic circuits; namely, Chua's oscillator and a hyperchaotic circuit, are presented. To impulsively synchronize two Chua's oscillators, synchronization impulses sampled from one state variable of the driving circuit are transmitted to the driven circuit. To impulsively synchronize two hyperchaotic circuits, synchronizing impulses sampled from two signals of the driving circuit are sent to the driven circuit. Our experimental results show that the accuracy of impulsive synchronization depends on both the period and the width of the impulse. The ratio between the impulse width and impulse period for "almost-identical" synchronization increases as the impulse period increases. The robustness of impulsive synchronization to additive noise is also experimentally studied. For sufficiently short impulse periods, no significant differences are observed between impulsive and continuous synchronizations. The performance of chaotic spread spectrum communication systems based on impulsive synchronization is also studied experimentally.

scholarly journals An Image Encryption Scheme Using 2D Generalized Sawtooth Maps

2014 ◽  
Vol 12 (6) ◽  
pp. 3570-3579
Author(s):  
Ruisong Ye ◽  
Wenping Yu
Keyword(s):  
Statistical Analysis ◽  
Detailed Analysis ◽  
Image Encryption ◽  
Experimental Results ◽  
Encryption Scheme ◽  
Brute Force ◽  
Key Space ◽  
Image Pixels ◽  
Brute Force Attack ◽  
Gray Values

In this paper, a new image encryption scheme based on 2D generalized sawtooth map is proposed. Utilizing the chaoticnature of 2D generalized sawtooth maps, image pixel positions are scrambled and image pixels gray values are changedto encrypt the plain-images. Experimental results have been carried out with detailed analysis to demonstrate that theproposed image encryption scheme possesses large key space to resist brute-force attack and possesses good statisticalproperties to frustrate statistical analysis attacks.

scholarly journals Just Shake Them Together: Imitation-Resistant Secure Pairing of Smart Devices via Shaking

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Congcong Shi ◽  
Lei Xie ◽  
Chuyu Wang ◽  
Peicheng Yang ◽  
Yubo Song ◽  
...  
Keyword(s):  
Experimental Study ◽  
Wireless Channel ◽  
Identity Authentication ◽  
Experimental Results ◽  
Smart Devices ◽  
Generation Process ◽  
Key Generation ◽  
Multiple Sensors ◽  
Symmetric Key ◽  
Robust To Noise

In traditional device-to-device (D2D) communication based on wireless channel, identity authentication and spontaneous secure connections between smart devices are essential requirements. In this paper, we propose an imitation-resistant secure pairing framework including authentication and key generation for smart devices, by shaking these devices together. Based on the data collected by multiple sensors of smart devices, these devices can authenticate each other and generate a unique and consistent symmetric key only when they are shaken together. We have conducted comprehensive experimental study on shaking various devices. Based on this study, we have listed several novel observations and extracted important clues for key generation. We propose a series of innovative technologies to generate highly unique and completely randomized symmetric keys among these devices, and the generation process is robust to noise and protects privacy. Our experimental results show that our system can accurately and efficiently generate keys and authenticate each other.

An Analytic Measure for the Difficulty of Human Control

1967 ◽  
Vol 20 (2) ◽  
pp. 167-175
Author(s):  
Walter M. Hollister
Keyword(s):  
Stress Level ◽  
Additive Noise ◽  
Experimental Results ◽  
Performance Function ◽  
Human Control ◽  
Exchange Programme

An important consideration in the design of systems for human control is the difficulty of the task. An analytic measure of this subjective consideration is denned. The difficulty is a function of the lead factor which is an integrated measure of the amount of lead the human must produce. The theory together with experimental results imply that the performance function minimized by a human controller includes the amount of control as well as the amount of error. The difficulty is constrained by the capability, training and stress level of the operator. Remnant is accounted for by assuming that the operator generates additive noise as a function of the difficulty. The model is used to explain Bernotat's experimental results with prediction display.This work was performed while the author was a guest professor at the Institut für Flugführung as part of the exchange programme between M.I.T. and the Technische Universität, Berlin.

Sign in / Sign up

Export Citation Format

Share Document