This paper presents a matching strategy to improve the discriminative power of histogram-based keypoint descriptors by constraining the range of allowable dominant orientations according to the context of the scene under observation. This can be done when the descriptor uses a circular grid and quantized orientation steps, by computing or providing a global reference orientation based on the fe...

Abstract: In order to address the problem of the uncertainty of existing noise models and of the complexity and changeability of the edges and textures of low-resolution document images, this paper presents a projection onto convex sets (POCS) algorithm based on text features. The current method preserves the edge details and smooths the noise in text images by adding text features as constrain...

This paper is focused on the automatic recognition of human events in static images. Popular techniques use knowledge of the human pose for inferring the action, and the most recent approaches tend to combine pose information with either knowledge of the scene or of the objects with which the human interacts. Our approach makes a step forward in this direction by combining the human pose with t...

data envelopment analysis (dea) is a non-parametric approach for performance analysis of decision making units (dmus) which uses a set of inputs to produce a set of outputs without the need to consider internal operations of each unit. in recent years, there have been various studies dealt with two-stage production systems, i.e. systems which consume some inputs in their first stage to produce ...

Image fusion is defi ned as the process of combining two or more different images into a new single image retaining important features from each image with extended information content. There are two approaches to image fusion, namely spatial fusion and transform fusion and three levels namely pixel, feature and region level. In spatial fusion, the pixel values from the source images are direct...

A powerful framework for the representation, characterization and analysis of two-dimensional shapes, with special attention given to neurons, is presented. This framework is based on a recently reported approach to scale space skeletonization and respective reconstructions by using label propagation and the exact distance transform. This methodology allows a series of remarkable properties, in...

2 User reference: the sift function 1 2.1 Scale space parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 2.2 Detector parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.3 Descriptor parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.4 Direct access to SIFT components . . . . . . . ....

This paper addresses the problem of combining color and geometric invariants for object description by proposing a novel colored invariant local feature descriptor. The proposed approach uses scale-space theory to detect the most geometrically robust features in a physical-based color invariant space. The stability and the distinction of the detected features are compared with the SIFT approach...