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.

Perceptual organization is the process of assigning each part of a scene to a specified association of features to be a part of the same organization. In the twenty century, Gestalt psychologists formalized how image features tend to be grouped by giving a set of organizing principles. In this paper, we propose an approach for the detection of perceptual groups in an image. We are mainly interested in features grouped by the proximity law of Gestalt. We conceive an object-based model within a stochastic framework using a marked point process (MPP). We use a Bayesian learning method to extract perceptual groups in a scene. The proposed model tested on synthetic images proves the efficient detection of perceptual groups in noisy images.

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.

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.

Road extraction research has always been an active research on automatic identification of remote sensing images. With the availability of high spatial resolution images from new generation commercial sensors, how to extract roads quickly, accurately and automatically has been a cutting-edge problem in remote sensing related fields. In this paper, we present a novel road extraction approach which uses a scale space segmentation and two measures of the shape index to filter all regions from the result of the segmentation. The approach makes full use of spectral and geometric properties of roads in the imagery, and proposes a new algorithm named “Road Segments joint Algorithm” to ensure the continuity of roads.