Unsupervised classification of a forest’s image by texture model features

In the capacity of texture features, the parameters of the SAR model for unlabeled classification image of forest landscape are used. We compare the results for two systems of features: the SAR model and the popular Haralik statistics. The histogram clustering algorithm arrange the hierarchy of distributions better by cluster isolation.     

Driver’s eye blinking detection using novel color and texture segmentation algorithms

In this paper we propose a system that measures eye blinking rate and eye closure duration. The system consists of skin-color segmentation, facial features segmentation, iris positioning and blink detection. The proposed skin-segmentation procedure is based on a neural network approximation of a RGB skin-color histogram. This method is robust and adaptive to any skin-color training set. The largest remaining skin-color region among skin-color segmentation results is further segmented into open/closed eyes, lips, nose, eyebrows, and the remaining facial regions using a novel texture segmentation algorithm. The segmentation algorithm classifies pixels according to the highest probability among the estimated facial feature class probability density functions (PDFs). The segmented eye regions are analyzed with the Circular Hough transform with the purpose of finding iris candidates. The finial iris position is selected according to the location of the maximum correlation value obtained from correlation with a predefined mask. The positions of irises and eye states are monitored through time to estimate eye blinking frequency and eye closure duration. The method of the driver drowsiness detection using these parameters is illustrated. The proposed system is tested on CCD and CMOS cameras under different environmental conditions and the experimental results show high system performance.     

Contact type dependency of texture classification in a whiskered mobile robot

Actuated artificial whiskers modeled on rat macrovibrissae can provide effective tactile sensor systems for autonomous robots. This article focuses on texture classification using artificial whiskers and addresses a limitation of previous studies, namely, their use of whisker deflection signals obtained under relatively constrained experimental conditions. Here we consider the classification of signals obtained from a whiskered robot required to explore different surface textures from a range of orientations and distances. This procedure resulted in a variety of deflection signals for any given texture. Using a standard Gaussian classifier we show, using both hand-picked features and ones derived from studies of rat vibrissal processing, that a robust rough-smooth discrimination is achievable without any knowledge of how the whisker interacts with the investigated object. On the other hand, finer discriminations appear to require knowledge of the target’s relative position and/or of the manner in which the whisker contact its surface. Electronic Supplementary Material  The online version of this article () contains supplementary material, which is available to authorized users.

La transformation en ondelettes pour l'extraction de la texture‐couleur. Application à la classification combinée des images (HRV) de SPOT

L'objectif de ce travail est de tester l'apport de l'information texture‐couleur à la classification des images SPOT (une seule date) pour l'établissement de cartes d'occupation du sol. Souvent la texture et la couleur sont abordées d'une façon complètement séparée. Dans ce travail, elles sont intégrées dans un seul modèle dit modèle de texture‐couleur, afin d'étendre efficacement l'analyse de la texture pour les images multispectrales. Pour cela, la représentation habituelle de la texture, fondée sur la prise en compte des variations locales de contraste, est enrichie par l'adjonction d'une connaissance sur ses variations spectrales. Afin de tester l'apport de cette information, deux classifications ont été réalisées sur des images HRV (XS) de SPOT de la région d'Oran prise comme zone test pour la variété des thèmes en présence et son relief relativement accidenté. La première est purement spectrale et la seconde utilise en plus des canaux bruts, ceux de la texture‐couleur. Les résultats montrent, qu'en plus d'une amélioration significative de 18.9% du taux global de bonne classification obtenu par rapport à celui de 75.9% donné par l'approche purement spectrale, l'information de texture‐couleur a permis une meilleure discrimination entre les thèmes présentant une importante confusion après classification.

Texture and colour are often used in a separated scheme without consideration of their mutual interactions. In this work they are combined in an integrative approach using the wavelet transformation technique. For that, texture–colour features are defined as wavelet coefficients covariance after colour space transformation. Colour–texture new channels are then used in addition to the radiometric channels to conduct a supervised classification process.

In order to asses the texture–colour contribution, two classifications have been performed on the HRV (XS) SPOT images over the city of Oran (west of Algeria) taken as a test zone for its thematic variety, heterogeneity and relatively uneven topography. The first approach uses only spectral information while the second combines the radiometric and texture–colour information in a multi‐resolution classification scheme.

Results show that the proposed approach brings significant improvement of 18.9% to the global classification rate compared to 75.9% given by the spectral approach. The texture–colour feature allowed better discrimination of confused items.