Topic
Dimensionality reduction
About: Dimensionality reduction is a research topic. Over the lifetime, 21987 publications have been published within this topic receiving 579272 citations. The topic is also known as: dimension reduction & dimensional reduction.
Papers published on a yearly basis
Papers
More filters
TL;DR: The best performing feature representations were two-dimensional density maps closely followed by morphometric statistics, which both continued to perform well even when neurons were only partially traced, implying that they can be suitable for dimensionality reduction or clustering.
Abstract: Quantitative analysis of neuronal morphologies usually begins with choosing a particular feature representation in order to make individual morphologies amenable to standard statistics tools and machine learning algorithms. Many different feature representations have been suggested in the literature, ranging from density maps to intersection profiles, but they have never been compared side by side. Here we performed a systematic comparison of various representations, measuring how well they were able to capture the difference between known morphological cell types. For our benchmarking effort, we used several curated data sets consisting of mouse retinal bipolar cells and cortical inhibitory neurons. We found that the best performing feature representations were two-dimensional density maps closely followed by morphometric statistics, which both continued to perform well even when neurons were only partially traced. The same representations performed well in an unsupervised setting, implying that they can be suitable for dimensionality reduction or clustering.
6 citations
15 Apr 2007
TL;DR: The subspace generalization power of the kernel correlation feature analysis (KCFA) method for producing compact low dimensional subspace that has good representation ability and discrimination to unseen datasets and produces good verification and identification rates compared to other subspace methods such as PCA.
Abstract: In this paper we analyze and demonstrate the subspace generalization power of the kernel correlation feature analysis (KCFA) method for producing compact low dimensional subspace that has good representation ability to work on unseen, untrained datasets. Examining the portability of an algorithm across different datasets is an important practical aspect of face recognition applications where the technology cannot be dataset-dependant in real-world practical applications. In most face recognition literature, algorithms are demonstrated on datasets by training on some part of the dataset and testing on the remainder. In general, the training and testing data have the same people but different capture sessions so essentially, some of the expected variation and people are modeled in the training set. In this paper we describe how we efficiently build a compact feature space using kernel correlation filter analysis on the generic training set of the FRGC dataset, and test the built subspace on other well-known face datasets. We show that the feature subspace produced by KCFA has good representation and discrimination to unseen datasets and produces good verification and identification rates compared to other subspace methods such as PCA. Its efficiency, lower dimensionality (the KCFA is only a 222 dimensional subspace) and discriminative power make it more practical and powerful than PCA as a powerful lower dimensionality reduction method for modeling faces and facial variations.
6 citations
Posted Content•
TL;DR: In this article, a Bayesian estimation approach with an appropriate hierarchical model with hidden markovian variables was proposed to jointly do data reduction, spectral classification, and image segmentation of hyperspectral images.
Abstract: Hyperspectral images can be represented either as a set of images or as a set of spectra. Spectral classification and segmentation and data reduction are the main problems in hyperspectral image analysis. In this paper we propose a Bayesian estimation approach with an appropriate hiearchical model with hidden markovian variables which gives the possibility to jointly do data reduction, spectral classification and image segmentation. In the proposed model, the desired independent components are piecewise homogeneous images which share the same common hidden segmentation variable. Thus, the joint Bayesian estimation of this hidden variable as well as the sources and the mixing matrix of the source separation problem gives a solution for all the three problems of dimensionality reduction, spectra classification and segmentation of hyperspectral images. A few simulation results illustrate the performances of the proposed method compared to other classical methods usually used in hyperspectral image processing.
6 citations
TL;DR: The reduced scattering representation improves the recognition performance when combining with lower-layer scattering network features and is evaluated on Malayalam printed and handwritten character recognition using support vector machine classifier.
Abstract: Scattering convolution network generates stable feature representation by applying a sequence wavelet decomposition operation on input signals. The feature representation in higher layers of the network builds a large-dimensional feature vector, which is often undesirable in most of the applications. Dimension reduction techniques can be applied on these higher-dimensional feature descriptors to produce an informative representation. In this paper, singular value decomposition is applied to the higher-layer scattering representation to generate informative feature descriptors. The effectiveness of the reduced scattering representation is evaluated on Malayalam printed and handwritten character recognition using support vector machine classifier. The reduced scattering representation improves the recognition performance when combining with lower-layer scattering network features.
6 citations
Patent•
21 Oct 2015
TL;DR: In this article, a spectrum image lossless identification model establishing method for seeds and a seed identification method is proposed. But the method is not suitable for the detection of seeds in the field of medical applications.
Abstract: The invention provides a spectrum image lossless identification model establishing method for seeds and a seed identification method. The seed identification method includes the steps that transmittance spectrum images of various kinds of seed grains are obtained through near infrared light with different wavelengths, after preprocessing of difference calculation and the like is conducted on the multi-band images, multiple image feature extraction methods are used for extracting image features, dimension reduction is conducted on each image feature, multiple sets of feature data are obtained, the separability of each set of feature data is calculated, the optimal feature data and the corresponding optimal image feature extracting method are obtained, the optimal feature data are used for establishing the spectrum image lossless identification model of seeds, the seed images to be identified are collected, and the obtained model is used for identification. According to the spectrum image lossless identification model establishing method for the seeds and the seed identification method, the spectrum image lossless identification model of the seeds is established through short-wave near infrared transmission imaging, lossless identification of the seeds is achieved, depth information of samples can be collected, the detecting precision is improved, the image sample collecting speed is high, and the detecting efficiency is greatly improved.
6 citations