Image Classification by Hierarchical Spatial Pooling with Partial Least Squares Analysis
نویسندگان
چکیده
Recent coding-based image classification systems generally adopt a key step of spatial pooling operation, which characterizes the statistics of patch-level local feature codes over the regions of interest (ROI), to form the image-level representation for classification. In this paper, we present a hierarchical ROI dictionary for spatial pooling, to beyond the widely used spatial pyramid in image classification literature. By utilizing the compositionality among ROIs, it captures rich spatial statistics via an efficient pooling algorithm in deep hierarchy. On this basis, we further employ partial least squares analysis to learn a more compact and discriminative image representation. The experimental results demonstrate superiority of the proposed hierarchical pooling method relative to spatial pyramid, on three benchmark datasets for image classification.
منابع مشابه
Linear and Nonlinear Multivariate Classification of Iranian Bottled Mineral Waters According to Their Elemental Content Determined by ICP-OES
The combinations of inductively coupled plasma-optical emission spectrometry (ICP-OES) and three classification algorithms, i.e., partial least squares discriminant analysis (PLS-DA), least squares support vector machine (LS-SVM) and soft independent modeling of class analogies (SIMCA), for discriminating different brands of Iranian bottled mineral waters, were explored. ICP-OES was used for th...
متن کاملSpectral-spatial classification of hyperspectral images by combining hierarchical and marker-based Minimum Spanning Forest algorithms
Many researches have demonstrated that the spatial information can play an important role in the classification of hyperspectral imagery. This study proposes a modified spectral–spatial classification approach for improving the spectral–spatial classification of hyperspectral images. In the proposed method ten spatial/texture features, using mean, standard deviation, contrast, homogeneity, corr...
متن کاملتحلیل حرکت جریانات دریائی در تصاویر حرارتی سطح آب دریا
Oceanographic images obtained from environmental satellites by a wide range of sensors allow characterizing natural phenomena through different physical measurements. For instance Sea Surface Temperature (SST) images, altimetry data and ocean color data can be used for characterizing currents and vortex structures in the ocean. The purpose of this thesis is to derive a relatively complete frame...
متن کاملA Convolutional Neural Network based on Adaptive Pooling for Classification of Noisy Images
Convolutional neural network is one of the effective methods for classifying images that performs learning using convolutional, pooling and fully-connected layers. All kinds of noise disrupt the operation of this network. Noise images reduce classification accuracy and increase convolutional neural network training time. Noise is an unwanted signal that destroys the original signal. Noise chang...
متن کاملMultitemporal Fusion for the Detection of Static Spatial Patterns in Multispectral Satellite Images--with Application to Archaeological Survey
We evaluate and further develop a multitemporal fusion strategy that we use to detect the location of ancient settlement sites in the Near East and to map their distribution, a spatial pattern that remains static over time. For each ASTER images that has been acquired in our survey area in north-eastern Syria, we use a pattern classification strategy to map locations with a multispectral signal...
متن کامل