Multi-Layer Model Based on Multi-Scale and Multi-Feature Fusion for SAR Images

Zhai, Aobo; Wen, Xianbin; Xu, Haixia; Yuan, Liming; Meng, Qingqi

doi:10.3390/rs9101085

Cited by 8 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature-layer fusion [37,38] is a multi-modal fusion method, which utilizes and integrates various information more effectively. And if one of the biometric systems is poor in performance, it will overly affect the overall recognition performance in score-layer fusion [39].…”

Section: Fingerprint and Finger Vein Feature Layer Fusion Recognitionmentioning

confidence: 99%

Feature-Level Fusion of Finger Vein and Fingerprint Based on a Single Finger Image: The Use of Incompletely Closed Near-Infrared Equipment

Shen

Yao

et al. 2020

Symmetry

View full text Add to dashboard Cite

Due to its portability, convenience, and low cost, incompletely closed near-infrared (ICNIR) imaging equipment (mixed light reflection imaging) is used for ultra thin sensor modules and have good application prospects. However, equipment with incompletely closed structure also brings some problems. Some finger vein images are not clear and there are sparse or even missing veins, which results in poor recognition performance. For these poor quality ICNIR images, however, there is additional fingerprint information in the image. The analysis of ICNIR images reveals that the fingerprint and finger vein in a single ICNIR image can be enhanced and separated. We propose a feature-level fusion recognition algorithm using a single ICNIR finger image. Firstly, we propose contrast limited adaptive histogram equalization (CLAHE) and grayscale normalization to enhance fingerprint and finger vein texture, respectively. Then we propose an adaptive radius local binary pattern (ADLBP) feature combined with uniform pattern to extract the features of fingerprint and finger vein. It solves the problem that traditional local binary pattern (LBP) is unable to describe the texture features of different sizes in ICNIR images. Finally, we fuse the feature vectors of ADLBP block histogram for a fingerprint and finger vein, and realize feature-layer fusion recognition by a threshold decision support vector machine (T-SVM). The experimentation results showed that the performance of the proposed algorithm was noticeably better than that of the single model recognition algorithm.

show abstract

Section: Fingerprint and Finger Vein Feature Layer Fusion Recognitionmentioning

confidence: 99%

Feature-Level Fusion of Finger Vein and Fingerprint Based on a Single Finger Image: The Use of Incompletely Closed Near-Infrared Equipment

Shen

Yao

et al. 2020

Symmetry

View full text Add to dashboard Cite

show abstract

“…Therefore, it is important to reduce the scattering and absorption effects to improve the imaging quality for various applications, such as underwater imaging [2], remote sensing [3], haze removal [4][5][6], and biological detection [7,8]. On the one hand, it has been proposed to numerically remove the negative effect based on computer vision methods [9,10]. On the other hand, the physical methods to reconstruct image could achieve more real target's information.…”

Section: Introductionmentioning

confidence: 99%

Performances of Polarization-Retrieve Imaging in Stratified Dispersion Media

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

We constructed an active imaging model within 10 km of the atmosphere from the satellite to the ground based on Monte Carlo (MC) algorithm, and, because of the inhomogeneous distributions of the scattering particles in atmosphere environment, 10 km atmosphere layer was divided into ten layers in our model. The MC algorithm was used to simulate the transmission process of photons through the atmosphere. By launching lasers of linear polarization states from satellites to ground, the intensity, degree of polarization (DoP), polarization difference (PD), and polarization retrieve (PR) images can be obtained. The contrast of the image, peak signal to noise ratio (PSNR), and structural similarity index (SSI) were used to evaluate the imaging quality. The simulated results demonstrate that the contrast of images is degraded as the atmosphere becomes worse. However, PR imaging have a better contrast and better visibility in different atmospheric conditions. Meanwhile, we found that Mueller matrix (MM) can retrieve the original images very well in a certain range of atmospheric conditions. Finally, the simulation also shows that different wavelengths of light sources have different penetration characteristics, and, in general, infrared light shows better performances than visible light for imaging.

show abstract

“…In [15], the author proposed a joint vibration and acoustic diagnosis method based on multi-feature fusion and improved Quantum Particle Swarm Optimization (QPSO) -Regression Vector Machine (RVM) to diagnose mechanical failures of conventional circuit breakers. In [16], the author's method showed good performance and visualization in quantitative evaluation. In [17,18], the author proposed a low-resolution face recognition technology based on the one-dimensional hidden Markov model, and finally used the Canonical Correlation Analysis (CCA) method to combine the simplified features.…”

Section: Introductionmentioning

confidence: 99%

Multi-Feature Fusion Algorithm in VR Panoramic Image Detail Enhancement Processing

Zhu

2020

IEEE Access

View full text Add to dashboard Cite

VR panoramic image is an image imaging technology that covers a wide range of scenes. Its imaging range is much larger than that of traditional imaging systems, and it can fully reflect all the information of the imaging space. However, the current VR panoramic images have the problems that the details are not obvious enough and the processing is not comprehensive enough. In view of the shadow problem in VR panoramic images, this paper proposes a multi-feature fusion VR panoramic image shadow elimination algorithm, which uses HSV color features and LBP / LSFP texture features to obtain shadow detection results, and then obtains the final detection results by fusion. The experimental results prove that while ensuring a low missed detection rate, the false detection rate is greatly reduced. The comprehensive evaluation index Avg in this paper is improved by 3.4% compared with the shadow elimination algorithm based on a single feature. This paper proposes an image saliency detection algorithm and image detail enhancement algorithm based on multi-feature fusion. The final saliency map is obtained through linear fusion. Experiments prove that the image detail enhancement algorithm based on multi-feature fusion mentioned in this paper has achieved very good results. This paper compares the performance of single-feature and multi-feature fusion algorithms. HSV, LBP and LSFP obtain 93.39% accuracy and 0.8708 correlation coefficient. The effect of multi-fusion fusion is better than that of single feature.

show abstract

Multi-Layer Model Based on Multi-Scale and Multi-Feature Fusion for SAR Images

Cited by 8 publications

References 24 publications

Feature-Level Fusion of Finger Vein and Fingerprint Based on a Single Finger Image: The Use of Incompletely Closed Near-Infrared Equipment

Feature-Level Fusion of Finger Vein and Fingerprint Based on a Single Finger Image: The Use of Incompletely Closed Near-Infrared Equipment

Performances of Polarization-Retrieve Imaging in Stratified Dispersion Media

Multi-Feature Fusion Algorithm in VR Panoramic Image Detail Enhancement Processing

Contact Info

Product

Resources

About