基于空间分割的数据简化和分类

数据简化的目的是简化数据集并保留有用的分类结构 .本文提出一个基于空间分隔的数据简化和分类算法 ,该算法将常规数据库的记录映射到多维空间上 ,从而将数据简化过程转变成在多维空间中同类数据的空间合并问题 ,也就是多维空间中不同类数据的空间分隔问题 ,最终得到一系列分隔空间 ,达到数据简化和分类的作用 .该方法用现实世界的 7个数据集进行评估 ,并与 C4.5所获得的结果进行比较 ,效果是显著的 ,并且结果唯一     

Adaptive unsupervised classification of polarimetric SAR images using the improved affinity propagation clustering algorithm

A robust automatic classification system is critical for polarimetric synthetic aperture radar (POLSAR) terrain processing. In most of the conventional classification methods, the number of classes could not be calculated before classification. In this article, we present a new unsupervised classification algorithm with an adaptive number of classes for POLSAR data which is capable of estimating the class numbers automatically. The approach is mainly composed of three operations. First, region-based feature map combining the polarimetric statistical and spatial information is constructed based on the turbopixel method. This is followed by a clustering step performed through an improved affinity propagation clustering with Wishart distance. Finally, the result of the improved affinity propagation clustering is classified using Wishart classifier. The proposed approach takes the spatial information into consideration and makes good use of the inherent statistical characteristics of POLSAR data. The performance of the proposed classification approach on three real datasets is presented and analysed, and the experimental results show that the approach provides more accurate estimation under the condition of various numbers of classes compared with existing methods.     

多尺度空间判别性概率潜在语义分析的场景分类

传统潜在语义分析(Latent Semantic Analysis, LSA)方法无法获得场景目标空间分布信息和潜在主题的判别信息。针对这一问题提出了一种基于多尺度空间判别性概率潜在语义分析(Probabilistic Latent Semantic Analysis, PLSA)的场景分类方法。首先通过空间金字塔方法对图像进行空间多尺度划分获得图像空间信息,结合PLSA模型获得每个局部块的潜在语义信息;然后串接每个特定局部块中的语义信息得到图像多尺度空间潜在语义信息;最后结合提出的权值学习方法来学习不同图像主题间的判别信息,从而得到图像的多尺度空间判别性潜在语义信息,并将学习到的权值信息嵌入支持向量基(Support Vector Machine, SVM)分类器中完成图像的场景分类。在常用的三个场景图像库(Scene-13、Scene-15和Caltech-101)上的实验表明,该方法平均分类精度比现有许多state-of-art方法均优。验证了其有效性和鲁棒性。     

Geometric discriminative features for aerial image retrieval in social media

The aerial image recognition is an important problem in multimedia information retrieval in social media. In this paper, we propose a new approach by integrating aerial image’s local features into a discriminative one which reflects both the geometric property and the color distribution of aerial image. Firstly, each aerial image is segmented into several regions in terms of their color intensities. And region connected graph (RCG), the links between the spatial neighboring regions, is presented to encode the spatial context of aerial images. Secondly, we mine frequent structures in the RCGs corresponding to training aerial images collected from social media. And a set of refined structures are selected among the frequent ones towards being more discriminative and less redundant. Finally, given a new aerial image, its sub-RCGs corresponding to all the refined structures are extracted and quantized into a discriminative feature for aerial image recognition. The experimental results validate the proposed method by providing a more accurate recognition result of the aerial images on different datasets from different social medias.     

Learning group-based dictionaries for discriminative image representation

Dictionary learning is a critical issue for achieving discriminative image representation in many computer vision tasks such as object detection and image classification. In this paper, a new algorithm is developed for learning discriminative group-based dictionaries, where the inter-concept (category) visual correlations are leveraged to enhance both the reconstruction quality and the discrimination power of the group-based discriminative dictionaries. A visual concept network is first constructed for determining the groups of visually similar object classes and image concepts automatically. For each group of such visually similar object classes and image concepts, a group-based dictionary is learned for achieving discriminative image representation. A structural learning approach is developed to take advantage of our group-based discriminative dictionaries for classifier training and image classification. The effectiveness and the discrimination power of our group-based discriminative dictionaries have been evaluated on multiple popular visual benchmarks.     

多特征融合与几何卷积的机载LiDAR点云地物分类

目的点云分类传统方法中大量依赖人工设计特征,缺乏深层次特征,难以进一步提高精度,基于深度学习的方法大部分利用结构化网络,转化为其他表征造成了3维空间结构信息的丢失,部分利用局部结构学习多层次特征的方法也因为忽略了机载数据的几何信息,难以实现精细分类。针对上述问题,本文提出了一种基于多特征融合几何卷积神经网络(multi-feature fusion and geometric convolutional neural network,MFFGCNN)的机载Li DAR(light detection and ranging)点云地物分类方法。方法提取并融合有效的浅层传统特征,并结合坐标尺度等预处理方法,称为APD模块(airporne laser scanning point cloud design module),在输入特征层面对典型地物有针对性地进行信息补充,来提高网络对大区域、低密度的机载Li DAR点云原始数据的适应能力和基础分类精度,基于多特征融合的几何卷积模块,称为FGC(multi-feature fusion and geometric convolution)算子,...     

Discriminative Random Fields

In this research we address the problem of classification and labeling of regions given a single static natural image. Natural images exhibit strong spatial dependencies, and modeling these dependencies in a principled manner is crucial to achieve good classification accuracy. In this work, we present Discriminative Random Fields (DRFs) to model spatial interactions in images in a discriminative framework based on the concept of Conditional Random Fields proposed by lafferty et al.(2001). The DRFs classify image regions by incorporating neighborhood spatial interactions in the labels as well as the observed data. The DRF framework offers several advantages over the conventional Markov Random Field (MRF) framework. First, the DRFs allow to relax the strong assumption of conditional independence of the observed data generally used in the MRF framework for tractability. This assumption is too restrictive for a large number of applications in computer vision. Second, the DRFs derive their classification power by exploiting the probabilistic discriminative models instead of the generative models used for modeling observations in the MRF framework. Third, the interaction in labels in DRFs is based on the idea of pairwise discrimination of the observed data making it data-adaptive instead of being fixed a priori as in MRFs. Finally, all the parameters in the DRF model are estimated simultaneously from the training data unlike the MRF framework where the likelihood parameters are usually learned separately from the field parameters. We present preliminary experiments with man-made structure detection and binary image restoration tasks, and compare the DRF results with the MRF results. Sanjiv Kumar is currently with Google Research, Pittsburgh, PA, USA. His contact email is: sanjivk@google.com.     

ON IMAGE CLASSIFICATION: CITY IMAGES VS. LANDSCAPES

Grouping images into semantically meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. Based on these groupings, effective indices can be built for an image database. In this paper, we show how a specific high-level classification problem (city images vs landscapes) can be solved from relatively simple low-level features geared for the particular classes. We have developed a procedure to qualitatively measure the saliency of a feature towards a classification problem based on the plot of the intra-class and inter-class distance distributions. We use this approach to determine the discriminative power of the following features: color histogram, color coherence vector, DCT coefficient, edge direction histogram, and edge direction coherence vector. We determine that the edge direction-based features have the most discriminative power for the classification problem of interest here. A weighted k-NN classifier is used for the classification which results in an accuracy of 93.9% when evaluated on an image database of 2716 images using the leave-one-out method. This approach has been extended to further classify 528 landscape images into forests, mountains, and sunset/sunrise classes. First, the input images are classified as sunset/sunrise images vs forest & mountain images (94.5% accuracy) and then the forest & mountain images are classified as forest images or mountain images (91.7% accuracy). We are currently identifying further semantic classes to assign to images as well as extracting low level features which are salient for these classes. Our final goal is to combine multiple 2-class classifiers into a single hierarchical classifier.     

Hyperspectral image classification based on robust discriminative extraction of multiple spectral-spatial features

In hyperspectral image (HSI) processing, the inclusion of both spectral and spatial features, e.g. morphological features, shape features, has shown great success in classification of hyperspectral data. Nevertheless, there exist two main issues to address: (1) The multiple features are often treated equally and thus the complementary information among them is neglected. (2) The features are often degraded by a mixture of various kinds of noise, leading to the classification accuracy decreased. In order to address these issues, a novel robust discriminative multiple features extraction (RDMFE) method for HSI classification is proposed. The proposed RDMFE aims to project the multiple features into a common low-rank subspace, where the specific contributions of different types of features are sufficiently exploited. With low-rank constraint, RDMFE is able to uncover the intrinsic low-dimensional subspace structure of the original data. In order to make the projected features more discriminative, we make the learned representations optimal for classification. With intrinsic information preserving and discrimination capabilities, the learned projection matrix works well in HSI classification tasks. Experimental results on three real hyperspectral datasets confirm the effectiveness of the proposed method.     

基于多粒度空间混乱的细粒度图像分类算法

细粒度图像分类是计算机视觉领域一个具有挑战性的任务,在实际场景中具有很高的应用价值。其中不同子类别的物体整体轮廓差异较小,微小的判别性局部区域是分类的关键。然而,这些重要的局部区域的尺度可能不同, 不能用单一的标准去衡量它们。为了解决这个问题,本文提出了多粒度空间混乱模块来帮助神经网络学习如何寻找到不同尺度的判别性细节。该模块首先将图片划分为不同粒度的局部区域,然后随机打乱并重组构成新的输入图片。经过处理的图片具有区域无关性,从而迫使网络更好地在不同粒度层次下寻找有判别力的局部区域并从中学习特征。在3个广泛使用的细粒度图像分类数据集上的实验证明本文提出的模块可以有效地帮助网络寻找判别性局部区域从而提升了准确率并且网络不需要图片的任何部位标注信息。     

Fast and effective characterization for classification and similarity searches of 2D and 3D spatial region data

We propose a method for characterizing spatial region data. The method efficiently constructs a k-dimensional feature vector using concentric spheres in 3D (circles in 2D) radiating out of a region's center of mass. These signatures capture structural and internal volume properties. We evaluate our approach by performing experiments on classification and similarity searches, using artificial and real datasets. To generate artificial regions we introduce a region growth model. Similarity searches on artificial data demonstrate that our technique, although straightforward, compares favorably to mathematical morphology, while being two orders of magnitude faster. Experiments with real datasets show its effectiveness and general applicability.     

Semi-supervised hyperspectral image classification algorithm based on graph embedding and discriminative spatial information

Image classification is one of the important techniques in computer vision. Due to the limited access of labeled samples in hyperspectral images, semi-supervised learning (SSL) methods have been widely applied in hyperspectral image classification. Graph based semi-supervised learning provides an effective solution to model data in classification problems, of which graph construction is the critical step. In this paper we employ the graphs constructed with a typical manifold learning method-locally linear embedding (LLE), based on which semi-supervised classification is then conducted. To exploit the valuable spatial information contained in hyperspectral images, discriminative spatial information (DSI) is then extracted. The proposed classification method is evaluated using three real hyperspectral data sets, revealing state-of-art performance when compared with different classification methods.     

Learning extremely shared middle-level image representation for scene classification

Learning middle-level image representations is very important for the computer vision community, especially for scene classification tasks. Middle-level image representations currently available are not sparse enough to make training and testing times compatible with the increasing number of classes that users want to recognize. In this work, we propose a middle-level image representation based on the pattern that extremely shared among different classes to reduce both training and test time. The proposed learning algorithm first finds some class-specified patterns and then utilizes the lasso regularization to select the most discriminative patterns shared among different classes. The experimental results on some widely used scene classification benchmarks (15 Scenes, MIT-indoor 67, SUN 397) show that the fewest patterns are necessary to achieve very remarkable performance with reduced computation time.     

Multidimensional local spatial autocorrelation measure for integrating spatial and spectral information in hyperspectral image band selection

Hyperspectral band selection aims at the determination of an optimal subset of spectral bands for dimensionality reduction without loss of discriminability. Many conventional band selection approaches depend on the concept of “statistical distance” measure between the probability distributions characterizing sample classes. However, the maximization of separability does not necessarily guarantee that a classification process results in the best classification accuracies. This paper presents a multidimensional local spatial autocorrelation (MLSA) measure that quantifies the spatial autocorrelation of the hyperspectral image data. Based on the proposed spatial measure, a collaborative band selection strategy is developed that combines both spectral separability measure and spatial homogeneity measure for hyperspectral band selection without losing the spectral details useful in classification processes. The selected band subset by the proposed method shows both larger separability between classes and stronger spatial similarity within class. Case studies in biomedical and remote sensing applications demonstrate that the MLSA-based band selection approach improves object classification accuracies in hyperspectral imaging compared with conventional approaches.     

聚焦—识别网络架构的细粒度图像分类

目的 细粒度图像分类是指对一个大类别进行更细致的子类划分,如区分鸟的种类、车的品牌款式、狗的品种等。针对细粒度图像分类中的无关信息太多和背景干扰问题,本文利用深度卷积网络构建了细粒度图像聚焦—识别的联合学习框架,通过去除背景、突出待识别目标、自动定位有区分度的区域,从而提高细粒度图像分类识别率。方法 首先基于Yolov2（youonly look once v2）的网络快速检测出目标物体,消除背景干扰和无关信息对分类结果的影响,实现聚焦判别性区域,之后将检测到的物体（即Yolov2的输出）输入双线性卷积神经网络进行训练和分类。此网络框架可以实现端到端的训练,且只依赖于类别标注信息,而无需借助其他的人工标注信息。结果 在细粒度图像库CUB-200-2011、Cars196和Aircrafts100上进行实验验证,本文模型的分类精度分别达到84.5%、92%和88.4%,与同类型分类算法得到的最高分类精度相比,准确度分别提升了0.4%、0.7%和3.9%,比使用两个相同D（dence）-Net网络的方法分别高出0.5%、1.4%和4.5%。结论 使用聚焦—识别深度学习框架提取有区分度的区域对细粒度图像分类有积极作用,能够滤除大部分对细粒度图像分类没有贡献的区域,使得网络能够学习到更多有利于细粒度图像分类的特征,从而降低背景干扰对分类结果的影响,提高模型的识别率。     

Methods of Intellectual Analysis in Medical Diagnostic Tasks Using Smart Feature Selection

The paper deals with a computer technique for high-performance processing, analysis and interpretation of medical and diagnostic images. We propose a new approach to the analysis of different classes of images based on evaluation of aggregate geometric and texture parameters of allocated regions of interest which are supposed to be a basic feature set. The developed efficient feature-space generation technique is based on Big Data mining of unstructured information by applying the discriminative analysis methods. The technique makes it possible to extract regions of interest on fundus images containing four classes of objects: exudates, intact areas, thick vessels, and thin vessels. The use of Big Data technology made it possible, due to involving large amounts of data, to improve the training sample and reduce classification errors that ensured an increase of diagnosis accuracy up to 95%. The proposed technique has been applied to the coagulate location problem, that is a crucial problem of diabetic retinopathy treatment. The experiment results on real eye fundus images proved a considerable increase of treatment effectiveness.     

A novel plane extraction approach using supervised learning

This paper presents a novel approach for the classification of planar surfaces in an unorganized point clouds. A feature-based planner surface detection method is proposed which classifies a point cloud data into planar and non-planar points by learning a classification model from an example set of planes. The algorithm performs segmentation of the scene by applying a graph partitioning approach with improved representation of association among graph nodes. The planarity estimation of the points in a scene segment is then achieved by classifying input points as planar points which satisfy planarity constraint imposed by the learned model. The resultant planes have potential application in solving simultaneous localization and mapping problem for navigation of an unmanned-air vehicle. The proposed method is validated on real and synthetic scenes. The real data consist of five datasets recorded by capturing three-dimensional(3D) point clouds when a RGBD camera is moved in five different indoor scenes. A set of synthetic 3D scenes are constructed containing planar and non-planar structures. The synthetic data are contaminated with Gaussian and random structure noise. The results of the empirical evaluation on both the real and the simulated data suggest that the method provides a generalized solution for plane detection even in the presence of the noise and non-planar objects in the scene. Furthermore, a comparative study has been performed between multiple plane extraction methods.