Search

We have assessed the feasibility of delineating and identifying mineral ores from images of mine excavation faces, taking samples from a gallery mine in Sn ¿ W pegmatitic vein deposits for a case of study. This study consisted on: 1. Analysis of laboratory hyper-spectral images (450 ¿ 1780 nm) of the different minerals of interest from samples collected in the mine to evaluate spectral separability and machine-learning classification under close-to-optimal conditions. 2. Analysis and spectral classification of a hyper-spectral image (950 ¿ 1780 nm) of a panel of samples in the vertical position, acquired under room conditions from a distance of 2.5 m, as a previous test of (i) the deployment of the hyper-spectral equipment in the mine and (ii) the analysis of images acquired in sub-optimal conditions, closer to those expected to be present in gallery mines. 3. Automatic segmentation of conventional digital photos of the mine excavation front to delineate patches of mineral ores and estimate ore grade. The analysis of laboratory hyper-spectral images indicated that all spectral signatures are statistically separable although care has to be taken with quartz forms including numerous impurities. Classification (Linear Discriminant Analysis, Singular Vector Machines and Random Forest) of laboratory spectra had a very high accuracy rate (up to 98%). In the case of the panel, classification accuracy was highest using Random Forests (93.2%). Segmentation of a conventional image of the mine excavation face successfully delimited ore patches and provided area measurements, thus facilitating area-based ore grade estimates. Our results show the interest and feasibility of the combined use of conventional and hyper-spectral imagery to assess and map mineral ores in mine excavation faces objectively.

Hyper-spectral data can be analyzed to recover physical properties at large planetary scales. This involves resolving inverse problems which can be addressed within machine learning, with the advantage that, once a relationship between physical parameters and spectra has been established in a data-driven fashion, the learned relationship can be used to estimate physical parameters for new hyper-spectral observations. Within this framework, we propose a spatially-constrained and partially-latent regression method which maps high-dimensional inputs (hyper-spectral images) onto low-dimensional responses (physical parameters such as the local chemical composition of the soil). The proposed regression model comprises two key features. Firstly, it combines a Gaussian mixture of locally-linear mappings (GLLiM) with a partially-latent response model. While the former makes high-dimensional regression tractable, the latter enables to deal with physical parameters that cannot be observed or, more generally, with data contaminated by experimental artifacts that cannot be explained with noise models. Secondly, spatial constraints are introduced in the model through a Markov random field (MRF) prior which provides a spatial structure to the Gaussian-mixture hidden variables. Experiments conducted on a database composed of remotely sensed observations collected from the Mars planet by the Mars Express orbiter demonstrate the effectiveness of the proposed model., 12 pages, 4 figures, 3 tables

We present a lip segmentation method based on simulated Lambertian shadings. The input consists of hyper-spectral images generated by a prototype for medical applications.

[EN] Hyperspectral imaging systems are starting to be used as a scientific tool for food quality assessment. A typical hyperspectral image is composed of a set of a relatively wide range of monochromatic images corresponding to continuous wavelengths that normally contain redundant information or may exhibit a high degree of correlation. In addition, computation of the classifiers used to deal with the data obtained from the images can become excessively complex and time-consuming for such high-dimensional datasets, and this makes it difficult to incorporate such systems into an industry that demands standard protocols or high-speed processes. Therefore, recent works have focused on the development of new systems based on this technology that are capable of analysing quality features that cannot be inspected using visible imaging. Many of those studies have also centred on finding new statistical techniques to reduce the hyperspectral images to multispectral ones, which are easier to implement in automatic, non-destructive systems. This article reviews recent works that use hyperspectral imaging for the inspection of fruit and vegetables. It explains the different technologies available to acquire the images and their use for the non-destructive inspection of the internal and external features of these products. Particular attention is paid to the works aimed at reducing the dimensionality of the images, with details of the statistical techniques most commonly used for this task. © 2011 Springer Science+Business Media, LLC., This work was partially funded by the Instituto Nacional de Investigacion y Tecnologia Agraria y Alimentaria de Espana (INIA) through research project RTA2009-00118-C02-01 and by the Ministerio de Ciencia e Innovacion de Espana (MICINN) through research project DPI2010-19457, both projects with the support of European FEDER funds. This work was also been partially funded by the Universitat de Valencia through project UV-INV-AE11-41271.

Conference name: 23rd Signal Processing and Communications Applications Conference, SIU 2015 Date of Conference: 16-19 May 2015 Hiperspektral hedef tespiti için yürütülen çalışmalar genel olarak iki sınıfta degerlendirilebilir. İlk sınıf olan anomali tespit yöntemlerinde, hedefin görüntünün geri kalanından farklı oldugu bilgisi kullanılarak görüntü analiz edilmektedir. Diğer sınıfta ise daha önceden bilgisi edinilmiş hedefe ait spektral imza ile görüntüdeki herbir piksel arasındaki benzerlik bulunarak hedefin konumu tespit edimektedir. Her iki sınıf yöntemin de önemli bir dezavantajı hiperspektral görüntü piksellerini bagımsız olarak degerlendirip, aralarındaki komşuluk ilişkilerini gözardı etmesidir. Bu makalede anomali tespit ve imza tabanlı tespit yakla¸sımlarını, pikseller arası komşuluk ilişkilerini de göz önünde bulundurarak birleştiren çizge yaklaşımına dayalı yeni bir yöntem önerilmiştir. Hedeflerin hem imza bilgisine sahip olundugu hem de anomali sayılabilecek ölçülerde olduğu varsayılarak önerilen çizge yaklaşımında önplan için imza bilgisi kullanan özgün bir türev tabanlı uyumlu filtre önerilmiştir. Arkaplan için ise seyreklik bilgisi kullanarak Gauss karışım bileşeni kestirimi yapan yeni bir anomali tespit yöntemi geliştirilmiştir. Son olarak komşular arası benzerligi tanımlamak için ise spektral bir benzerlik ölçütü olan spektral açı eleştiricisi kullanılmıştır. Önerilen çizge tabanlı yöntemin önplan, arkaplan ve komşuluk ilişkilerini uygun şekilde birleştirdigi ve önceki yöntemlere göre hedefi gürültüden arınmış bir bütün şeklinde başarıyla tespit edebildigi gözlemlenmiştir. The studies on hyperspectral target detection until now, has been treated in two approaches. Anomaly detection can be considered as the first approach, which analyses the hyperspectral image with respect to the difference between target and the rest of the hyperspectral image. The second approach compares the previously obtained spectral signature of the target with the pixels of the hyperspectral image in order to localize the target. A distinctive disadvantage of the aforementioned approaches is to treat each pixel of the hyperspectral image individually, without considering the neighbourhood relations between the pixels. In this paper, we propose a target detection algorithm which combines the anomaly detection and signature based hyperspectral target detection approaches in a graph based framework by utilizing the neighbourhood relations between the pixels. Assuming that the target signature is available and the target sizes are in the range of anomaly sizes, a novel derivative based matched filter is first proposed to model the foreground. Second, a new anomaly detection method which models the background as a Gaussian mixture is developed. The developed model estimates the optimal number of components forming the Gaussian mixture by means of utilizing sparsity information. Finally, the similarity of the neighbouring hyperspectral pixels is measured with the spectral angle mapper. The overall proposed graph based method has successfully combined the foreground, background and neighbouring information and improved the detection performance by locating the target as a whole object free from noises. © 2015 IEEE.

ISBN: 978-364221568-1; International audience; The open problem of the generalization of mathematical morphology to vector images is handled in this paper using the paradigm of depth functions. Statistical depth functions provide from the "deepest" point a "center-outward ordering" of a multidimensional data distribution and they can be therefore used to construct morphological operators. The fundamental assumption of this data-driven approach is the existence of "background/foreground" image representation. Examples in real color and hyperspectral images illustrate the results.

ISBN: 978-142447994-8; International audience; A novel approach for vectorial ordering is introduced in this paper. The generic framework is based on a supervised learning formulation which leads to reduced orderings. A training set for the background and another training set for the foreground are needed as well as a supervised method to construct the ordering mapping. In particular, we consider here a kriging-based vectorial ordering. This supervised ordering may then used for the extension of mathematical morphology to vectorial images. Application of morphological processing to hyperspectral image illustrates the performance of proposal operators.

Healthy and midge-damaged wheat kernels obtained from five growing locations across western Canada were imaged using a near-infrared (NIR) hyperspectral imaging system (700-1100 nm) and an area-scan colour camera. Six statistical features (maximum, minimum, mean, median, standard deviation, and variance) and histogram features from the significant wavelength images of hyperspectral data were extracted and given as input to three statistical classifiers (linear, quadratic, and Mahalanobis). From the colour images, a total of 230 features (123 colour, 56 textural, and 51 morphological features) were extracted and the top ten features were selected and given as input to the statistical classifiers. The NIR hyperspectral image features combined with the top 10 colour image features gave the highest average accuracy of 95.3-99.3% in classifying healthy and midge-damaged wheat kernels. (C) 2009 IAgrE. Published by Elsevier Ltd. All rights reserved. Refereed/Peer-reviewed