- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 OCEANS - MTS/IEEE Kobe Techno-Ocean (OTO) - Kobe, Japan (2018.5.28-2018.5.31)] 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO) - A Dimension-Reduced Modal Space Detector in Deep-Sea Environment
摘要： The matched correlation detector (MCD), combining the received data with the sound transfer function (namely the replica field) is theoretically optimal for underwater passive detection. However, it suffers from the model mismatch problem caused by environmental uncertainties. And furthermore, when applied to the deep-sea environment, it encounters the large search range problem. In this paper, we focus on the source detection problem in deep-sea environment. To overcome the disadvantages of MCD, we choose the modal space detector (MSD) which uses a vertical linear array (VLA). We derive the expression of the deep-sea MSD and further, to improve the signal-to-noise ratio (SNR) of the test statistic, we propose a dimension-reduced form of MSD, which is termed as DR-MSD for short. By numerical simulation, we discuss that how source frequency, array depth and array aperture influence the dimension reduction. And we point out that the dimension-reduced number in DR-MSD decreases when the source frequency and the VLA aperture increase. The numerical results also indicate that DR-MSD can alleviate the search burden and obtain a better detection performance when compared to traditional MSD.
关键词： underwater acoustic,passive source detection,Deep-sea environment,dimension reduction,MSD
更新于2025-09-23 15:22:29
-
[IEEE 2018 International Conference on Intelligent and Advanced System (ICIAS) - Kuala Lumpur, Malaysia (2018.8.13-2018.8.14)] 2018 International Conference on Intelligent and Advanced System (ICIAS) - Deep Features and Data Reduction for Classification of SD-OCT Images: Application to Diabetic Macular Edema
摘要： Diabetic Macular Edema (DME) is defined as the accumulation of extracellular fluids in the macular region of the eye, caused by Diabetic Retinopathy (DR) that will lead to irreversible vision loss if left untreated. This paper presents the use of a pre-trained Convolutional Neural Network (CNN) based model for the classification of Spectral Domain Optical Coherence Tomography (SD-OCT) images of Diabetic Macular Edema (DME) with feature reduction using Principal Component Analysis (PCA) and Bag of Words (BoW). The model is trained using SD-OCT dataset retrieved from the Singapore Eye Research Institute (SERI) and is evaluated using an 8-fold cross validation at the slide level and two patient leave out at the volume level. For the volume level, an accuracy of 96.88% is obtained for data that was preprocessed.
关键词： Diabetic Macular Edema,Dimension reduction,CNNs,SD-OCT
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Surface Defect Detection Based on Gradient LBP
摘要： The LBP histogram obtained based on the local binary pattern (LBP) method usually has a higher dimension, and not conducive to calculation. The LBP method adopts the gray difference value between single points as the LBP output value, which is not robust to noise and illumination. Therefore, this paper improves the traditional LBP method and proposes a surface defect detection method based on gradient local binary pattern (GLBP), which uses image sub-blocks to reduce the dimensionality of the LBP data matrix. The method adopts weighted binary output values in eight directions within the neighborhood to indicate local gray changes, which suppresses the effects of light and noise on the detection results. Experiments show that the method can determine the defect location well and provide good feature information for subsequent defect classification.
关键词： surface defect detection,gradient LBP,LBP,image sub-block division,LBP dimension reduction
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Superpixel Based Dimension Reduction for Hyperspectral Imagery
摘要： This paper focuses on dimension reduction (DR) technique for hyperspectral image (HSI). In this paper, we proposed a superpixel-based linear discriminant analysis (SP-LDA) dimension reduction method for HSI classification. Pixels within a local spatial neighborhood are expected to have similar spectral curves and share the same class label. To fully exploit the spatial structure, superpixel segmentation is firstly introduced to generate the superpixel map, which can adaptively explore the neighborhood structure information. Moreover, we extend the SP-LDA algorithm by combining the extracted feature from spectral and spatial dimensions, which can fully exploit complementary and consistent information from both dimensions. The experimental results on two standard hyperspectral datasets confirm the superiority of the proposed algorithms.
关键词： Hyperspectral image,superpixel,dimension reduction,spectral-spatial
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - A Novel Deep Learning Framework by Combination of Subspace-Based Feature Extraction and Convolutional Neural Networks for Hyperspectral Images Classification
摘要： Approaches based on deep learning have gained an increased attention in the recent years in particular Remote Sensing. Convolutional Neural Networks (CNNs) as one of these deep learning techniques has demonstrated remarkable performance in visual recognition applications. However, using well-known pre-train models such as GoogleNet and VGGNet in the area of hyperspectral image classification due to the high dimensionality and the insufficient training samples is intractable. The current study proposed a new and fixes CNN architecture for two real hyperspectral data sets. To overcome curse of dimensionality we perform a subspace-based feature extraction method by calculating the orthonormal basis of correlation matrix for each class to reduce the dimensionality of hyperspectral images and increasing signal to noise ratio. This framework combines the proposed CNN architecture and subspace reduction method to prepare informative features (from subspace method) and designing optimized CNN by considering limitation of training samples. Also, feature generated by subspace reduction method is compatible by the nature of class based CNNs and a logistic regression as a classifier in the last layer of proposed architecture. Experimental results from two real and well-known hyperspectral images, the Indiana Pines and the Pavia University scenes show that the proposed strategy leads to a performance improvement, as opposed to using the original data and conventional feature extraction strategies which have been employed during the recent approaches. The classification overall accuracy of ca. 98.1% and 98.3% were obtained in Indian Pine and Pavia University respectively.
关键词： Dimension Reduction,Deep Learning,Feature Extraction,Convolutional Neural Network,Hyperspectral Image Classification,Subspace-based Feature Extraction
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Evaluation of Dimensional Reduction Methods on Urban Vegegation Classification Performance Using Hyperspectral Data
摘要： In the context of urban vegetation, hyperspectral imagery allows to discriminate biochemical properties of land surfaces. In this study, we test several dimension reductions to evaluate capacities of hyperspectral sensors to characterize tree families. The goal is to evaluate if a selection of differentiated and uncorrelated vegetation indices is an efficient method to reduce the dimension of hyperspectral images. This method is compared with conventional MNF and ACP approaches, and assessed on tree vegetation classifications performed using SVM classifier on two datasets at 4m and 8m spatial resolution. Results show that MNF combined with SVM classification is the better method to reduce hyperspectral dimension.
关键词： Urban vegetation,dimension reduction,SVM,hyperspectral data
更新于2025-09-09 09:28:46
-
[Smart Innovation, Systems and Technologies] Information Systems and Technologies to Support Learning Volume 111 (Proceedings of EMENA-ISTL 2018) || A Novel Filter Approach for Band Selection and Classification of Hyperspectral Remotely Sensed Images Using Normalized Mutual Information and Support Vector Machines
摘要： Band selection is a great challenging task in the classi?cation of hyperspectral remotely sensed images HSI. This is resulting from its high spectral resolution, the many class outputs and the limited number of training samples. For this purpose, this paper introduces a new ?lter approach for dimension reduction and classi?cation of hyperspectral images using information theoretic (normalized mutual information) and support vector machines SVM. This method consists to select a minimal subset of the most informative and relevant bands from the input datasets for better classi?cation ef?ciency. We applied our proposed algorithm on two well-known benchmark datasets gathered by the NASA’s AVIRIS sensor over Indiana and Salinas valley in USA. The experimental results were assessed based on different evaluation metrics widely used in this area. The comparison with the state of the art methods proves that our method could produce good performance with reduced number of selected bands in a good timing.
关键词： Support vector machines,Classi?cation,Dimension reduction,Band selection,Hyperspectral images,Normalized mutual information
更新于2025-09-09 09:28:46
-
Dimension Reduction for the Landau--de Gennes Model: The Vanishing Nematic Correlation Length Limit
摘要： We study nematic liquid crystalline films within the framework of the Landau--de Gennes theory in the limit when both the thickness of the film and the nematic correlation length are vanishingly small compared to the lateral extent of the film. We prove \Gamma -convergence for a sequence of singularly perturbed functionals with a potential vanishing on a high-dimensional set and a Dirichlet condition imposed on admissible functions. This then allows us to prove the existence of local minimizers of the Landau--de Gennes energy in the spirit of [R. V. Kohn and P. Sternberg, Proc. Roy. Soc. Edinburgh Sect. A, 111 (1989), pp. 69--84] despite the lack of compactness arising from the high-dimensional structure of the wells. The limiting energy consists of leading order perimeter terms, similar to Allen--Cahn models, and lower order terms arising from vortex structures reminiscent of Ginzburg--Landau models.
关键词： gamma convergence,thin film,nematic,dimension reduction
更新于2025-09-09 09:28:46
-
[IEEE 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) - Ankara, Turkey (2018.10.19-2018.10.21)] 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) - License Plate Recognition System by Using High Dimensional Model Representation
摘要： In this paper, it is proposed to match characters in content based images from real time scenes and extract the content as a text into the virtual environment by using the special called High Dimensional Model Representation (HDMR) for the system of License Plate Recognition. LPR is used to identify vehicles by reading license plates in image processing. Besides various techniques, a new matching algorithm is developed for the implementation of the LPR technology. LPR process is based on three major stages: Extraction of the license plate region from an image, segmentation of characters from the license plate region and recognition of characters which are segmented from the license plate. HDMR is used for working with high dimensional data based on image, at the stage of recognition of characters. The HDMR algorithm is used for matching the characters.
关键词： HDMR,character recognition,image processing,dimension reduction,license plate recognition
更新于2025-09-04 15:30:14