Centre symmetric quadruple pattern-based illumination invariant measure

A centre symmetric quadruple pattern-based illumination invariant measure(CSQPIM)is proposed to tackle severe illumination variation face recognition.First,the subtraction of the pixel pairs of the centre symmetric quadruple pattern(CSQP)is defined as the CSQPIM unit in the logarithm face local region,which may be positive or negative.The CSQPIM model is obtained by combining the positive and negative CSQPIM units.Then,the CSQPIM model can be used to generate several CSQPIM images by controlling the proportions of positive and negative CSQPIM units.The single CSQPIM image with the saturation function can be used to develop the CSQPIM-face.Multi CSQPIM images employ the extended sparse representation classification(ESRC)as the classifier,which can create the CSQPIM image-based classification(CSQPIMC).Furthermore,the CSQPIM model is integrated with the pre-trained deep learning(PDL)model to construct the CSQPIM-PDL model.Finally,the experimental results on the Extended Yale B,CMU PIE and Driver face databases indicate that the proposed methods are efficient for tackling severe illumination variations.

A novel method of determining the optimal polyhedral orientation for discrete global grid systems applicable to regionalscale areas of interest

The polyhedral discrete global grid system(DGGS)is a multi-resolution discrete earth reference model supporting the fusion and processing of multi-source geospatial information.The orientation of the polyhedron relative to the earth is one of its key design choices,used when constructing the grid system,as the efficiency of indexing will decrease if local areas of interest extend over multiple faces of the spherical polyhedron.To date,most research has focused on global-scale applications while almost no rigorous mathematical models have been established for determining orientation parameters.In this paper,we propose a method for determining the optimal polyhedral orientation of DGGSs for areas of interest on a regional scale.The proposed method avoids splitting local or regional target areas across multiple polyhedral faces.At the same time,it effectively handles geospatial data at a global scale because of the inherent characteristics of DGGSs.Results show that the orientation determined by this method successfully guarantees that target areas are located at the center of a single polyhedral face.The orientation process determined by this novel method reduces distortions and is more adaptable to different geographical areas,scales,and base polyhedrons than those employed by existing procedures.