Search results for "Contextual image classification"
showing 10 items of 105 documents
Shape Description for Content-Based Image Retrieval
2000
The present work is focused on a global image characterization based on a description of the 2D displacements of the different shapes present in the image, which can be employed for CBIR applications.To this aim, a recognition system has been developed, that detects automatically image ROIs containing single objects, and classifies them as belonging to a particular class of shapes.In our approach we make use of the eigenvalues of the covariance matrix computed from the pixel rows of a single ROI. These quantities are arranged in a vector form, and are classified using Support Vector Machines (SVMs). The selected feature allows us to recognize shapes in a robust fashion, despite rotations or…
Cluster kernels for semisupervised classification of VHR urban images
2009
In this paper, we present and apply a semisupervised support vector machine based on cluster kernels for the problem of very high resolution image classification. In the proposed setting, a base kernel working with labeled samples only is deformed by a likelihood kernel encoding similarities between unlabeled examples. The resulting kernel is used to train a standard support vector machine (SVM) classifier. Experiments carried out on very high resolution (VHR) multispectral and hyperspectral images using very few labeled examples show the relevancy of the method in the context of urban image classification. Its simplicity and the small number of parameters involved make it versatile and wor…
Dataset shift adaptation with active queries
2011
In remote sensing image classification, it is commonly assumed that the distribution of the classes is stable over the entire image. This way, training pixels labeled by photointerpretation are assumed to be representative of the whole image. However, differences in distribution of the classes throughout the image make this assumption weak and a model built on a single area may be suboptimal when applied to the rest of the image. In this paper, we investigate the use of active learning to correct the shifts that may appear when training and test data do not come from the same distribution. Experiments are carried out on a VHR remote sensing classification scenario showing that active learni…
Microaneurysm detection with radon transform-based classification on retina images.
2012
The creation of an automatic diabetic retinopathy screening system using retina cameras is currently receiving considerable interest in the medical imaging community. The detection of microaneurysms is a key element in this effort. In this work, we propose a new microaneurysms segmentation technique based on a novel application of the radon transform, which is able to identify these lesions without any previous knowledge of the retina morphological features and with minimal image preprocessing. The algorithm has been evaluated on the Retinopathy Online Challenge public dataset, and its performance compares with the best current techniques. The performance is particularly good at low false p…
Using active learning to adapt remote sensing image classifiers
2011
The validity of training samples collected in field campaigns is crucial for the success of land use classification models. However, such samples often suffer from a sample selection bias and do not represent the variability of spectra that can be encountered in the entire image. Therefore, to maximize classification performance, one must perform adaptation of the first model to the new data distribution. In this paper, we propose to perform adaptation by sampling new training examples in unknown areas of the image. Our goal is to select these pixels in an intelligent fashion that minimizes their number and maximizes their information content. Two strategies based on uncertainty and cluster…
Texture classification for content-based image retrieval
2002
An original approach to texture-based classification of regions, for image indexing and retrieval, is presented. The system addresses automatic macro-textured ROI detection, and classification: we focus our attention on those objects that can be characterized by a texture as a whole, like trees, flowers, walls, clouds, and so on. The proposed architecture is based on the computation of the /spl lambda/ vector from each selected region, and classification of this feature by means of a pool of suitably trained support vector machines (SVM). This approach is an extension of the one previously developed by some of the authors to classify image regions on the basis of the geometrical shape of th…
Introducing Pseudo-Singularity Points for Efficient Fingerprints Classification and Recognition
2010
Fingerprint classification and matching are two key issues in automatic fingerprint recognition. Generally, fingerprint recognition is based on a set of relevant local characteristics, such as ridge ending and bifurcation (minutiae). Fingerprint classification is based on fingerprint global features, such as core and delta singularity points. Unfortunately, singularity points are not always present in a fingerprint image: the acquisition process is not ideal, so that the fingerprint is broken, or the fingerprint belongs to the arch class. In the above cases, pseudo-singularity-points will be detected and extracted to make possible fingerprint classification and matching. As result, fingerpr…
Multi-temporal and Multi-source Remote Sensing Image Classification by Nonlinear Relative Normalization
2016
Remote sensing image classification exploiting multiple sensors is a very challenging problem: data from different modalities are affected by spectral distortions and mis-alignments of all kinds, and this hampers re-using models built for one image to be used successfully in other scenes. In order to adapt and transfer models across image acquisitions, one must be able to cope with datasets that are not co-registered, acquired under different illumination and atmospheric conditions, by different sensors, and with scarce ground references. Traditionally, methods based on histogram matching have been used. However, they fail when densities have very different shapes or when there is no corres…
Simplified spiking neural network architecture and STDP learning algorithm applied to image classification
2015
Spiking neural networks (SNN) have gained popularity in embedded applications such as robotics and computer vision. The main advantages of SNN are the temporal plasticity, ease of use in neural interface circuits and reduced computation complexity. SNN have been successfully used for image classification. They provide a model for the mammalian visual cortex, image segmentation and pattern recognition. Different spiking neuron mathematical models exist, but their computational complexity makes them ill-suited for hardware implementation. In this paper, a novel, simplified and computationally efficient model of spike response model (SRM) neuron with spike-time dependent plasticity (STDP) lear…
Optimal band selection for future satellite sensor dedicated to soil science
2009
Hyperspectral imaging systems could be used for identifying the different soil types from the satellites. However, detecting the reflectance of the soils in all the wavelengths involves the use of a large number of sensors with high accuracy and also creates a problem in transmitting the data to earth stations for processing. The current sensors can reach a bandwidth of 20 nm and hence, the reflectance obtained using the sensors are the integration of reflectance obtained in each of the wavelength present in the spectral band. Moreover, not all spectral bands contribute equally to classification and hence, identifying the bands necessary to have a good classification is necessary to reduce …