- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Research on feature point extraction and matching machine learning method based on light field imaging
摘要： At present, there are many methods to realize the matching of specified images with features, and the basic components include image feature point detection, feature description, and image matching. Based on this background, this article has done different research and exploration around these three aspects. The image feature point detection method is firstly studied, which commonly include image edge information-based feature detection method, corner information-based detection method, and various interest operators. However, all of the traditional detection methods are involved in problems of large computation burden and time consumption. In order to solve this problem, a feature detection method based on image grayscale information-FAST operator is used in this paper, which is combined with decision tree theory to effectively improve the speed of extracting image feature points. Then, the feature point description method BRIEF operator is studied, which is a local expression of detected image feature points based on descriptors. Since the descriptor does not have rotation invariance, the detection operator is endowed by a direction that is proposed in this paper, and then the local feature description is conducted on the feature descriptor to generate a binary string array containing direction information. Finally, the feature matching machine learning method is analyzed, and the nearest search method is used to find the nearest feature point pair in Euclidean distance, of which the calculation burden is small. The simulation results show that the proposed nearest neighbor search and matching machine learning algorithm has higher matching accuracy and faster calculation speed compared with the classical feature matching algorithm, which has great advantages in processing a large number of array images captured by the light field camera.
关键词： Nearest neighbor search,Light field imaging,Image matching,Machine learning
更新于2025-09-23 15:23:52
-
Multispectral Airborne LiDAR Data in the Prediction of Boreal Tree Species Composition
摘要： Multispectral light detection and ranging (LiDAR) instruments, such as Optech Titan, record intensities at multiple wavelengths and these intensities can be used for tree species prediction in the same way as multispectral image data. In this paper, our main objective was to compare the accuracy of tree species prediction in a boreal forest area using multispectral LiDAR, the 1064-nm wavelength channel ('unispectral LiDAR'), and unispectral LiDAR with auxiliary aerial image data. We also evaluated the effect of the widely used intensity range correction method. We classified the main tree species of field plots using linear discriminant analysis (LDA) and predicted the species-specific volume proportions (%) for Scots pine (Pinus sylvestris), Norway spruce (Picea abies), and broadleaved trees using the k-nearest neighbor imputation. The effect of intensity correction on prediction errors for the dominant tree species was evaluated using optimal parameters derived from: 1) minimal intensity difference between flight lines; 2) parameters suggested by theory; and 3) uncorrected data. Although the range correction increased the classification accuracy slightly, it was observed to be ambiguous, and not consistent with theory for canopy echoes. Regardless, the intensity values were useful for the prediction of dominant tree species and species' volume proportions. The results for the dominant tree species classification using multispectral LiDAR [overall accuracy (OA) 88.2%, kappa 0.79] were comparable to the use of unispectral LiDAR and aerial images (OA 89.1%, kappa 0.81). We conclude that the multispectral LiDAR may become a useful tool in operational species-specific forest inventories.
关键词： laser backscatter intensity,k-nearest neighbor (k-NN),Intensity correction,linear discriminant analysis (LDA),multispectral airborne laser scanning,tree species classification
更新于2025-09-23 15:22:29
-
LSBs-based quantum color images watermarking algorithm in edge region
摘要： Based on the NEQR representation for quantum color and binary images, an enhanced quantum watermarking scheme is investigated through Gray code transform and least significant bit (LSB) steganography, which embeds a quantum binary image (i.e., watermark image) into the edge region of a quantum color image (i.e., carrier image) LSB and second LSB. The size of the carrier and watermark images are assumed to be 2n × 2n and 2n?1 × 2n?1, respectively. At first, the watermark image is resized into an appropriate size image with 4-qubit grayscale based on the nearest neighbor interpolation method, which is of the same size with the preselected edge region in carrier image. To enhance the security of the watermark image, the binary code of 4-qubit grayscale of watermark image is transformed into the corresponding Gray code, and one 3-Controlled-NOT gate is utilized to generate a quantum binary image |K 1(cid:2). To further scatter the watermark image qubits that are embedded into the LSB and second LSB of carrier image, the quantum image |K 1(cid:2) is employed to choose any two channels from the color image among the three channels of R, G and B (i.e., R, G or R, B channels would be chosen as the embedding channels). Furthermore, a quantum binary image |K 2(cid:2) is generated through XOR operation decided by the quantum image |K 1(cid:2), which is used to determine the embedding order of watermark image qubits. The extraction process is the inverse operation of embedding, which also needs the two quantum binary key images |K 1(cid:2) and |K 2(cid:2). Finally, the experiment results are simulated under the classical computer software MATLAB 2016(b), which illustrates that our investigated LSBs-based quantum watermarking has a better visual effect than some related works in terms of PSNR value.
关键词： Nearest neighbor interpolation,Gray code transform,Quantum watermarking,Least significant bit
更新于2025-09-23 15:21:21
-
Identification of Gravesa?? ophthalmology by laser-induced breakdown spectroscopy combined with machine learning method
摘要： Diagnosis of the Graves’ ophthalmology remains a significant challenge. We identified between Graves’ ophthalmology tissues and healthy controls by using laser-induced breakdown spectroscopy (LIBS) combined with machine learning method. In this work, the paraffin-embedded samples of the Graves’ ophthalmology were prepared for LIBS spectra acquisition. The metallic elements (Na, K, Al, Ca), non-metallic element (O) and molecular bands ((C-N), (C-O)) were selected for diagnosing Graves’ ophthalmology. The selected spectral lines were inputted into the supervised classification methods including linear discriminant analysis (LDA), support vector machine (SVM), k-nearest neighbor (kNN), and generalized regression neural network (GRNN), respectively. The results showed that the predicted accuracy rates of LDA, SVM, kNN, GRNN were 76.33%, 96.28%, 96.56%, and 96.33%, respectively. The sensitivity of four models were 75.89%, 93.78%, 96.78%, and 96.67%, respectively. The specificity of four models were 76.78%, 98.78%, 96.33%, and 96.00%, respectively. This demonstrated that LIBS assisted with a nonlinear model can be used to identify Graves’ ophthalmopathy with a higher rate of accuracy. The kNN had the best performance by comparing the three nonlinear models. Therefore, LIBS combined with machine learning method can be an effective way to discriminate Graves’ ophthalmology.
关键词： support vector machine (SVM),linear discriminant analysis (LDA),Graves’ ophthalmology,laser-induced breakdown spectroscopy (LIBS),k-nearest neighbor (kNN),generalized regression neural network (GRNN)
更新于2025-09-23 15:21:01
-
[IEEE 2019 Compound Semiconductor Week (CSW) - Nara, Japan (2019.5.19-2019.5.23)] 2019 Compound Semiconductor Week (CSW) - Persistent resonance frequency shift of MoS <sub/>2</sub> mechanical resonator by laser irradiation
摘要： Robust classification becomes challenging when each class consists of multiple subclasses. Examples include multi-font optical character recognition and automated protein function prediction. In correlation-based nearest-neighbor classification, the maximin correlation approach (MCA) provides the worst-case optimal solution by minimizing the maximum misclassification risk through an iterative procedure. Despite the optimality, the original MCA has drawbacks that have limited its wide applicability in practice. That is, the MCA tends to be sensitive to outliers, cannot effectively handle nonlinearities in datasets, and suffers from having high computational complexity. To address these limitations, we propose an improved solution, named regularized MCA (R-MCA). We first reformulate MCA as a quadratically constrained linear programming (QCLP) problem, incorporate regularization by introducing slack variables in the primal problem of the QCLP, and derive the corresponding Lagrangian dual. The dual formulation enables us to apply the kernel trick to R-MCA, so that it can better handle nonlinearities. Our experimental results demonstrate that the regularization and kernelization make the proposed R-MCA more robust and accurate for various classification tasks than the original MCA. Furthermore, when the data size or dimensionality grows, R-MCA runs substantially faster by solving either the primal or dual (whichever has a smaller variable dimension) of the QCLP. The source code of the proposed R-MCA methodology is available at http://data.snu.ac.kr/rmca.
关键词： SOCP,correlation,kernel trick,QP,maximin,QCLP,Nearest neighbor,regularization
更新于2025-09-23 15:21:01
-
[IEEE 2019 Compound Semiconductor Week (CSW) - Nara, Japan (2019.5.19-2019.5.23)] 2019 Compound Semiconductor Week (CSW) - $\mathbf{1545}\ \mu \mathbf{m}$ Quantum Dot Vertical Cavity Surface Emitting Laser with low threshold
摘要： Approximate Nearest Neighbor (ANN) search has become a popular approach for performing fast and efficient retrieval on very large-scale datasets in recent years, as the size and dimension of data grow continuously. In this paper, we propose a novel vector quantization method for ANN search which enables faster and more accurate retrieval on publicly available datasets. We define vector quantization as a multiple affine subspace learning problem and explore the quantization centroids on multiple affine subspaces. We propose an iterative approach to minimize the quantization error in order to create a novel quantization scheme, which outperforms the state-of-the-art algorithms. The computational cost of our method is also comparable to that of the competing methods.
关键词： vector quantization,Approximate nearest neighbor search,subspace clustering,large-scale retrieval,binary codes
更新于2025-09-23 15:21:01
-
KNN-Based Representation of Superpixels for Hyperspectral Image Classification
摘要： Superpixel segmentation has been demonstrated to be a powerful tool in hyperspectral image (HSI) classification. Each superpixel region can be regarded as a homogeneous region, which is composed of a series of spatial neighboring pixels. However, a superpixel region may contain the pixels from different classes. To further explore the optimal representations of superpixels, a new framework based on two k selection rules is proposed to find the most representative training and test samples. The proposed method consists of the following four steps: first, a superpixel segmentation algorithm is performed on the HSI to cluster the pixels with similar spectral features into the same superpixel. Then, a domain transform recursive filtering is used to extract the spectral–spatial features of the HSI. Next, the k nearest neighbor (KNN) method is utilized to select k1 representative training samples and k2 test pixels for each superpixel, which can effectively overcome the within-class variations and between-class interference, respectively. Finally, the class label of superpixels can be determined by measuring the averaged distances among the selected training and test samples. Experiments conducted on four real hyperspectral datasets show that the proposed method provides competitive classification performances with respect to several recently proposed spectral–spatial classification methods.
关键词： superpixel segmentation,hyperspectral image classification,k nearest neighbor (KNN),Domain transform recursive filtering (RF)
更新于2025-09-23 15:21:01
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Atomic Layer Deposited Al <sub/>x</sub> Ni <sub/>y</sub> O as Hole Selective Contact for Silicon Solar Cells
摘要： Approximate Nearest Neighbor (ANN) search has become a popular approach for performing fast and efficient retrieval on very large-scale datasets in recent years, as the size and dimension of data grow continuously. In this paper, we propose a novel vector quantization method for ANN search which enables faster and more accurate retrieval on publicly available datasets. We define vector quantization as a multiple affine subspace learning problem and explore the quantization centroids on multiple affine subspaces. We propose an iterative approach to minimize the quantization error in order to create a novel quantization scheme, which outperforms the state-of-the-art algorithms. The computational cost of our method is also comparable to that of the competing methods.
关键词： vector quantization,Approximate nearest neighbor search,subspace clustering,large-scale retrieval,binary codes
更新于2025-09-23 15:19:57
-
[IEEE 2019 IEEE 8th International Conference on Advanced Optoelectronics and Lasers (CAOL) - Sozopol, Bulgaria (2019.9.6-2019.9.8)] 2019 IEEE 8th International Conference on Advanced Optoelectronics and Lasers (CAOL) - Approach to Assessing Quality Indicators
摘要： Aiming and efficient improving accuracy, this paper presents a hardware-friendly template reduction (TR) method for the nearest neighbor (NN) classifiers by introducing the concept of critical boundary vectors. A hardware system is also implemented to demonstrate the feasibility of using an field-programmable gate array (FPGA) to accelerate the proposed method. Initially, k-means centers are used as substitutes for the entire template set. Then, to enhance the classification performance, critical boundary learning algorithm, which vectors are selected by a novel is completed within a single iteration. Moreover, to remove noisy boundary vectors that can mislead the classification in a generalized manner, a global categorization scheme has been explored and applied to the algorithm. The global characterization automatically categorizes each classification problem and rapidly selects the boundary vectors according to the nature of the problem. Finally, only critical boundary vectors and k-means centers are used as the new template set for classification. Experimental results for 24 data sets show that the proposed algorithm can effectively reduce the number of template vectors for classification with a high learning speed. At the same time, it improves the accuracy by an average of 2.17% compared with the traditional NN classifiers and also shows greater accuracy than seven other TR methods. We have shown the feasibility of using a proof-of-concept FPGA system of 256 64-D vectors to accelerate the proposed method on hardware. At a 50-MHz clock frequency, the proposed system achieves a 3.86 times higher learning speed than on a 3.4-GHz PC, while consuming only 1% of the power of that used by the PC.
关键词： FPGA classifier,learning system,template reduction (TR),nearest neighbor (NN)
更新于2025-09-23 15:19:57
-
[IEEE 2019 International Conference on Signal Processing and Communication (ICSC) - NOIDA, India (2019.3.7-2019.3.9)] 2019 International Conference on Signal Processing and Communication (ICSC) - Fabrication of CZTS Thin Films based Solar Cells using Vacuum Deposition Techniques: A Status Review
摘要： For many computer vision and machine learning problems, large training sets are key for good performance. However, the most computationally expensive part of many computer vision and machine learning algorithms consists of finding nearest neighbor matches to high dimensional vectors that represent the training data. We propose new algorithms for approximate nearest neighbor matching and evaluate and compare them with previous algorithms. For matching high dimensional features, we find two algorithms to be the most efficient: the randomized k-d forest and a new algorithm proposed in this paper, the priority search k-means tree. We also propose a new algorithm for matching binary features by searching multiple hierarchical clustering trees and show it outperforms methods typically used in the literature. We show that the optimal nearest neighbor algorithm and its parameters depend on the data set characteristics and describe an automated configuration procedure for finding the best algorithm to search a particular data set. In order to scale to very large data sets that would otherwise not fit in the memory of a single machine, we propose a distributed nearest neighbor matching framework that can be used with any of the algorithms described in the paper. All this research has been released as an open source library called fast library for approximate nearest neighbors (FLANN), which has been incorporated into OpenCV and is now one of the most popular libraries for nearest neighbor matching.
关键词： big data,Nearest neighbor search,approximate search,algorithm configuration
更新于2025-09-19 17:13:59