scholarly journals Infrared and Visible Image Fusion Based on Co-occurrence Analysis Shearlet Transform Context-Aware

2022 ◽  
Vol 14 (2) ◽  
pp. 283
Author(s):  
Biao Qi ◽  
Longxu Jin ◽  
Guoning Li ◽  
Yu Zhang ◽  
Qiang Li ◽  
...  
Keyword(s):  
Intensity Variation ◽  
Saliency Map ◽  
Low Rank ◽  
Base Layer ◽  
Visible Image ◽  
Zero Crossing ◽  
Shearlet Transform ◽  
Zero Crossings ◽  
Regularization Term ◽  
Weighted Fusion

This study based on co-occurrence analysis shearlet transform (CAST) effectively combines the latent low rank representation (LatLRR) and the regularization of zero-crossing counting in differences to fuse the heterogeneous images. First, the source images are decomposed by CAST method into base-layer and detail-layer sub-images. Secondly, for the base-layer components with larger-scale intensity variation, the LatLRR, is a valid method to extract the salient information from image sources, and can be applied to generate saliency map to implement the weighted fusion of base-layer images adaptively. Meanwhile, the regularization term of zero crossings in differences, which is a classic method of optimization, is designed as the regularization term to construct the fusion of detail-layer images. By this method, the gradient information concealed in the source images can be extracted as much as possible, then the fusion image owns more abundant edge information. Compared with other state-of-the-art algorithms on publicly available datasets, the quantitative and qualitative analysis of experimental results demonstrate that the proposed method outperformed in enhancing the contrast and achieving close fusion result.

Determination of tonal signal parameters based on zero crossing detection

2021 ◽  
Vol 263 (5) ◽  
pp. 1794-1803
Author(s):  
Michal Luczynski ◽  
Stefan Brachmanski ◽  
Andrzej Dobrucki
Keyword(s):  
High Efficiency ◽  
Detection Algorithm ◽  
Sine Wave ◽  
Time Interval ◽  
Zero Crossing ◽  
Tonal Signal ◽  
Zero Crossings ◽  
Tonal Component ◽  
Signal Parameters ◽  
The Moment

This paper presents a method for identifying tonal signal parameters using zero crossing detection. The signal parameters: frequency, amplitude and phase can change slowly in time. The described method allows to obtain accurate detection using possibly small number of signal samples. The detection algorithm consists of the following steps: frequency filtering, zero crossing detection and parameter reading. Filtering of the input signal is aimed at obtaining a signal consisting of a single tonal component. Zero crossing detection allows the elimination of multiple random zero crossings, which do not occur in a pure sine wave signal. The frequency is based on the frequency of transitions through zero, the amplitude is the largest value of the signal in the analysed time interval, and the initial phase is derived from the moment at which the transition through zero occurs. The obtained parameters were used to synthesise a compensation signal in an active tonal component reduction algorithm. The results of the algorithm confirmed the high efficiency of the method.

scholarly journals Robust Image Hashing with Low-Rank Representation and Ring Partition

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Zhenjun Tang ◽  
Zixuan Yu ◽  
Zhixin Li ◽  
Chunqiang Yu ◽  
Xianquan Zhang
Keyword(s):  
Image Quality Assessment ◽  
Characteristic Curve ◽  
Visual Representation ◽  
Image Authentication ◽  
Saliency Map ◽  
Low Rank ◽  
Image Hashing ◽  
Copy Detection ◽  
Social Event Detection ◽  
Low Rank Representation

Image hashing has attracted much attention of the community of multimedia security in the past years. It has been successfully used in social event detection, image authentication, copy detection, image quality assessment, and so on. This paper presents a novel image hashing with low-rank representation (LRR) and ring partition. The proposed hashing finds the saliency map by the spectral residual model and exploits it to construct the visual representation of the preprocessed image. Next, the proposed hashing calculates the low-rank recovery of the visual representation by LRR and extracts the rotation-invariant hash from the low-rank recovery by ring partition. Hash similarity is finally determined by L2 norm. Extensive experiments are done to validate effectiveness of the proposed hashing. The results demonstrate that the proposed hashing can reach a good balance between robustness and discrimination and is superior to some state-of-the-art hashing algorithms in terms of the area under the receiver operating characteristic curve.

scholarly journals A Deep Multiscale Fusion Method via Low-Rank Sparse Decomposition for Object Saliency Detection Based on Urban Data in Optical Remote Sensing Images

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Cheng Zhang ◽  
Dan He
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Saliency Detection ◽  
Saliency Map ◽  
Low Rank ◽  
Optical Remote Sensing ◽  
Fusion Method ◽  
Remote Sensing Images ◽  
Sparse Decomposition ◽  
Depth Feature

The urban data provides a wealth of information that can support the life and work for people. In this work, we research the object saliency detection in optical remote sensing images, which is conducive to the interpretation of urban scenes. Saliency detection selects the regions with important information in the remote sensing images, which severely imitates the human visual system. It plays a powerful role in other image processing. It has successfully made great achievements in change detection, object tracking, temperature reversal, and other tasks. The traditional method has some disadvantages such as poor robustness and high computational complexity. Therefore, this paper proposes a deep multiscale fusion method via low-rank sparse decomposition for object saliency detection in optical remote sensing images. First, we execute multiscale segmentation for remote sensing images. Then, we calculate the saliency value, and the proposal region is generated. The superpixel blocks of the remaining proposal regions of the segmentation map are input into the convolutional neural network. By extracting the depth feature, the saliency value is calculated and the proposal regions are updated. The feature transformation matrix is obtained based on the gradient descent method, and the high-level semantic prior knowledge is obtained by using the convolutional neural network. The process is iterated continuously to obtain the saliency map at each scale. The low-rank sparse decomposition of the transformed matrix is carried out by robust principal component analysis. Finally, the weight cellular automata method is utilized to fuse the multiscale saliency graphs and the saliency map calculated according to the sparse noise obtained by decomposition. Meanwhile, the object priors knowledge can filter most of the background information, reduce unnecessary depth feature extraction, and meaningfully improve the saliency detection rate. The experiment results show that the proposed method can effectively improve the detection effect compared to other deep learning methods.

scholarly journals Geometry-Aware Face Completion and Editing

2019 ◽  
Vol 33 ◽  
pp. 2506-2513 ◽  
Author(s):  
Linsen Song ◽  
Jie Cao ◽  
Lingxiao Song ◽  
Yibo Hu ◽  
Ran He
Keyword(s):  
Face Image ◽  
Experimental Results ◽  
Low Rank ◽  
Generation Task ◽  
Regularization Term ◽  
Face Region ◽  
Facial Landmark ◽  
Structure Generator ◽  
Shape And Size ◽  
Face Appearance

Face completion is a challenging generation task because it requires generating visually pleasing new pixels that are semantically consistent with the unmasked face region. This paper proposes a geometry-aware Face Completion and Editing NETwork (FCENet) by systematically studying facial geometry from the unmasked region. Firstly, a facial geometry estimator is learned to estimate facial landmark heatmaps and parsing maps from the unmasked face image. Then, an encoder-decoder structure generator serves to complete a face image and disentangle its mask areas conditioned on both the masked face image and the estimated facial geometry images. Besides, since low-rank property exists in manually labeled masks, a low-rank regularization term is imposed on the disentangled masks, enforcing our completion network to manage occlusion area with various shape and size. Furthermore, our network can generate diverse results from the same masked input by modifying estimated facial geometry, which provides a flexible mean to edit the completed face appearance. Extensive experimental results qualitatively and quantitatively demonstrate that our network is able to generate visually pleasing face completion results and edit face attributes as well.

The Automatic Extraction of Pitch Perturbation Using Microcomputers

1989 ◽  
Vol 32 (3) ◽  
pp. 689-697 ◽  
Author(s):  
Jodelle F. Deem ◽  
Walter H. Manning ◽  
Joseph V. Knack ◽  
Joseph S. Matesich
Keyword(s):  
Relative Sensitivity ◽  
Sine Wave ◽  
Automatic Extraction ◽  
Sample Duration ◽  
Pitch Period ◽  
Zero Crossing ◽  
Zero Crossings ◽  
Extraction Procedures ◽  
Vocal Fold Vibration ◽  
Analysis System

A program for the automatic extraction of jitter (PAEJ) was developed for the clinical measurement of pitch perturbations using a microcomputer. The program currently includes 12 implementations of an algorithm for marking the boundary criteria for a fundamental period of vocal fold vibration. The relative sensitivity of these extraction procedures for identifying the pitch period was compared using sine waves. Data obtained to date provide information for each procedure concerning the effects of waveform peakedness and slope, sample duration in cycles, noise level of the analysis system with both direct and tape recorded input, and the influence of interpolation. Zero crossing extraction procedures provided lower jitter values regardless of sine wave frequency or sample duration. The procedures making use of positive- or negative-going zero crossings with interpolation provided the lowest measures of jitter with the sine wave stimuli. Pilot data obtained with normal-speaking adults indicated that jitter measures varied as a function of the speaker, vowel, and sample duration.

A Fringe Signal Processing Method With Multi-Sample Zero-Crossing Detection Based on DSP and its Application in Absolute Gravimeters

2016 ◽  
Author(s):  
Jin Qian ◽  
Kang Wu ◽  
Lijun Wang
Keyword(s):  
Signal Processing ◽  
Processing Method ◽  
Counting Method ◽  
Zero Crossing ◽  
Zero Crossings ◽  
Signal Processing Method ◽  
The Absolute ◽  
Free Falling ◽  
The Impact ◽  
Electronic Counting

The absolute gravitation acceleration (g) is generally measured by observation of a free-falling test mass in a vacuum chamber based on laser interference. Usually the free-falling object trajectory is obtained by timing the zero-crossings of the interference fringe signal. A traditional way to time the zero-crossings is electronic counting method, of which the resolution is limited in principle. In this paper, a fringe signal processing method with multi-sample zero-crossing detection based on Digital Signal Processor (DSP) is proposed and realized for the application in absolute gravimeters. The principle and design of the fringe signal processing method are introduced. The measuring precision is evaluated both theoretically and from numerical software simulations with MATLAB®, and verified by hardware simulated free-falling experiments. The results show that the absolute error of the gravity acceleration measurement introduced by the fringe signal processing method is less than 0.5 μGal (1 μGal = 1×10−8 m/s2), and the impact on the standard deviation is about 2 μGal. This method can effectively reduce the systematic error of the traditional electronic counting method, and satisfy the requirements for precision and portability, especially for field ready absolute gravimeters.

Sign in / Sign up

Export Citation Format

Share Document