This work presents a novel local image descriptor based on the concept of pointwise signal regularity. Local image regions are extracted using either an interest point or an interest region detector, and discriminative feature vectors are constructed by uniformly sampling the pointwise Hölderian regularity around each region center. Regularity estimation is performed using local image oscillati...

Improving the matching reliability of low-altitude images is one of the most challenging issues in recent years, particularly for images with large viewpoint variation. In this study, an approach for low-altitude remote sensing image matching that is robust to the geometric transformation caused by viewpoint change is proposed. First, multiresolution local regions are extracted from the images ...

With the growing amount of inappropriate content on the Internet, such as pornography, arises the need to detect and filter such material. The reason for this is given by the fact that such content is often prohibited in certain environments (e.g., schools and workplaces) or for certain publics (e.g., children). In recent years, many works have been mainly focused on detecting pornographic imag...

According to the rotational invariance of Harris corner detector and the robustness of Sift descriptor. An improved Harris-Sift corner descriptor was proposed. At first, the algorithm given multi-scale strategy to Harris corner, improved corner counting method and removed redundant points at the same time, then, the corner was directly applied to low-pass Gaussian filter image. Based on the his...

Based on the feature matching theory about SIFT (Scale-Invariant Feature Transform) keypoints, the concentric circle structure and the color feature vector of scale-invariant descriptor are proposed in this paper. In the concentric circle structure, the radiuses of the concentric circles are proportional to the scale factor, which can achieve the scale invariance. To achieve the rotation invari...

Constructing accurate training tuples is crucial for unsupervised local descriptor learning, yet challenging due to the absence of patch labels. The state-of-the-art approach constructs with heuristic rules, which struggle precisely depict real-world transformations, in spite enabling fast model convergence. A possible solution alleviate problem clustering-based approach, can capture realistic ...

Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. Such a descriptor--based on a set of oriented Gaussian derivative filters-is used in our recognition system. We report here an evaluation of several techniques for orientation estimation to achieve rotation invariance...

This paper presents a novel feature descriptor termed principal component analysis (PCA)-based Advanced Local Octa-Directional Pattern (ALODP-PCA) for content-based image retrieval. The conventional approaches compare each pixel of an with certain neighboring pixels providing discrete information. proposed in this work utilizes the local intensity all eight directions its neighborhood. octa-dir...

Feature vectors can be anything from simple surface normals to more complex feature descriptors. Feature extraction is important in order to solve various computer vision problems: e.g. registration, object recognition and scene understanding. Most of these techniques cannot be computed online due to their complexity and the context where they are applied. Therefore computing these features in ...

In this paper we propose a novel texture recognition feature called Fractal Weighted Local Binary Pattern (FWLBP). It has been observed that fractal dimension (FD) measure is relatively invariant to scale-changes, and presents a good correlation with human perception of surface roughness. We have utilized this property to construct a scale-invariant descriptor. We have sampled the input image u...