In this paper we propose a novel feature, called directional entropy feature (DEF), to improve the performance of human detection under complicated background in images. DEF describe the regularity of region by computing the entropy value of edge points’ spatial distribution in specific direction

We present a framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source -channel approach as a special case. All knowledge sources are treated as feature functions, which depend on the source language

=−k the measure theoretic directional entropy per unit of length in the direction ω0. It is shown that hµ(T u F[−k,k] ) = uhµ(TF[−k,k]), hµ(Φu) = uhµ(Φ) and h⃗v(Φ u) = uh⃗v(Φ) for ⃗v ∈ Z2 where h is the measure-theoretic entropy. 1.

information-theoretic approach and the projection pursuit approach. Using maximum entropy approximations of differential entropy, we introduce a family of new contrast (objective) functions for ICA. These contrast functions enable both the estimation of the whole decomposition by minimizing mutual information

made in those models. Conditional random fields also avoid a fundamental limitation of maximum entropy Markov models (MEMMs) and other discriminative Markov models based on directed graphical models, which can be biased towards states with few successor states. We present iterative parameter estimation

equation for a propagating level set function, and use techniques borrowed from hyperbolic conservation laws. Topological changes, corner and cusp development, and accurate determination of geometric properties such as curvature and normal direction are naturally obtained in this setting. In this paper, we

This paper presents a new algorithm for the independent components analysis (ICA) problem based on efficient entropy estimates. Like many previous methods, this algorithm directly minimizes the measure of departure from independence according to the estimated Kullback-Leibler divergence between

Rank one transformations play a central role in the theory of ergodic measure preserving transformations. Having first been identified as a distinct class by Chacon in [3], their properties have been studied extensively (see for example [1], [7], [11], [6]). Rank one transformations have also served

Abstract not found

the directional entropy of neighboring edges for choosing between two interpolation methods, a directional along detected edges or a bilinear using the nearest neighboring pixels. Results show that the performance of the proposed method is subjectively and objectively (PSNR wise) better compared to both ‘single