Search

Color is very important feature for image representation, it assumes very essential in the human visual recognition process. Although, several color extension of Local Binary Pattern processes the color texture from the three color channels separately (Marginal way). Aware of the high interaction that exists between different channels in the color image, this work introduces a new vector process to define a local descriptor for color images named Local Binary Quaternion Rotation Pattern (LBQRP). In this LBQRP purpose, the quaternion representation is used to represent color texture. The distance between two color can be expressed as the angle of rotation between two unit quaternions using the geodesic distance. After a LBQRP coding, local histograms are extracted and used as features. Experiments on three challenging color datasets: Vistex, Outex-TC13 and USPtex are carried out to evaluate the LBQRP performance in texture classification. Results show the high efficiency of the proposed approach facing to several stat-of-art methods.

The human visual system receives sensory inputs from the environment and converts them into the perception of real objects such as desks, buildings, and cars. This phenomenon is known as visual perception. It is an effortless process which makes sense of the visual information. Recently, the ultimate goal for machine vision researches is to imitate the human visual perception and to understand the intricate data processing done by the human brain. In this paper, we propose a methodology inspired by Gestalt theory of perception to quantify the human visual perception. Our goal is to add a quantitative aspect for the visual perception in order to be easily integrated into the image processing tasks. Tests on synthetic images show good performance on images with Gaussian noise proving its efficiency to detect perceptual groups.

Texture discrimination was studied a lot for texture classification/recognition in image databases, but less under the metrological point of view. In this work, we focused on the metrological behaviour related to the human vision for Control Quality purposes. Inside this study, we introduce as a pair a novel texture feature associated to an adapted similarity measure. The main idea was to define a compact representation adapted from the human visual characteristics in order to obtain an accurate description of the texture. Combined to an adapted similarity measure, the obtained pair feature/similarity becomes highly efficient. Performance Classification of the proposed texture feature is assessed on six popular and challenging databases used to provide the reference results in the state-of-the-art. Obtained results show the efficiency and the robustness of the proposed pair feature/similarity measure defined by the relocated Colour Contrast Occurrence Matrix.

International audience; For metrological purposes, distance between texture images is crucial. This work study as a pair the couple texture feature/similarity measure. Starting from the Colour Contrast Occurrence Matrix (C2O) definition, we propose an adapted similarity measure improving texture retrieval. In a second step, we propose a modified version of the C2O definition including the texture's colour average inside a modified similarity measure. Performance in texture retrieval is assessed for four challenging datasets: Vistex, Stex, Outex-TC13 and KTH-TIPS2b databases facing to the recent results from the state-of-the-art. Results show the high efficiency of the proposed approach based on a simple pair fea-ture/similarity measure facing to more complex approaches including Convolutional Neural Networks.

The continuous development of pattern recognition approaches increases the need for evaluation tools to quantify algorithms performance and establish precise inter-algorithm comparison. So far, few performance evaluating metrics in pattern recognition algorithms are known in the literature, especially in remote sensing images. In this paper, four metrics are proposed for this purpose. The advantages and drawbacks of these metrics are first described, then some experimentation results are the presented in order to validate our contribution.

NURBS (Non-uniform rational B-splines) has become the industry standard tools for the representation, design and data exchange of geometric information to be processed and used by computers because of their useful geometrical properties. The problem of the parameterization of data points in NURBS curve/surface has been considered by several of researchers. We propose in this paper a new parameterization method for NURBS approximation. The current methods of parameterization such as centripetal method uses only the previous knot vector to calculate the recent knot. In this paper, we give a new parameterization method based on the correlation of the nodes. This approach inherits the advantages of the relation and position of the knots.

The representation and description of shapes or regions that have been segmented out of an image are early steps in the operation of most Computer vision systems; they serve as a precursor to several possible higher level tasks such as object/character recognition. In this context, skeletons have good properties for data reduction and representation. In this paper we present a novel shape representation scheme, named ”NURBS Skeleton”, based on the thinning medial axis method, the pruning process and the Non Uniform Rational B-Spline (NURBS) curves approximation for the modeling step.

Automatic network road extraction from high resolution remotely sensed images has been under study by computer scientists for over 30 years. In fact, Conventional methods to create and update road information rely heavily on manual work and therefore are very expensive and time consuming. This paper presents an efficient and computationally fast method to extract road from very high resolution images automatically. We propose in this paper a new approach for following roads path based on a quaternionic wavelet transform insuring a good local space-frequency analysis with very important directional selectivity. In fact, the rich phase information given by this hypercomplex transform overcomes the lack of shift invariance property shown by the real discrete wavelet transform and the poor directional selectivity of both real and complex wavelet transform.

The raster-vector conversion of remote sensing image is a very important task in the extraction and updating of linear objects in cartographic processes. In this paper we present a vectorization method, based on constrained Delaunay triangulation, for line extraction. The constraints are provided by a preprocessing step insuring that these edges belong to line structures in the original image. The vectorization is performed using CDT and resulting triangles are grouped into polygins that make up the vector image. The skeleton of these polygons represents the extracted linear structures. The algorithm is automatic, fast and has very satisfing results when tested on road segments.