Integrating absolute distances in collaborative representation for robust image classification

Conventional sparse representation based classification （SRC） represents a test sample with the coefficient solved by each training sample in all classes. As a special version and improvement to SRC, collaborative representation based classification （CRC） obtains representation with the contribution from all training samples and produces more promising results on facial image classification. In the solutions of representation coefficients, CRC considers original value of contributions from all samples. However, one prevalent practice in such kind of distance-based methods is to consider only absolute value of the distance rather than both positive and negative values. In this paper, we propose an novel method to improve collaborative representation based classification, which integrates an absolute distance vector into the residuals solved by collaborative representation. And we named it AbsCRC. The key step in AbsCRC method is to use factors a and b as weight to combine CRC residuals rescrc with absolute distance vector disabs and generate a new dviaetion r = a·rescrc b.disabs, which is in turn used to perform classification. Because the two residuals have opposite effect in classification, the method uses a subtraction operation to perform fusion. We conducted extensive experiments to evaluate our method for image classification with different instantiations. The experimental results indicated that it produced a more promising result of classification on both facial and non-facial images than original CRC method.

Age and Body Size of the Shangcheng Stout Salamander Pachyhynobius shangchengensis(Caudata:Hynobiidae)from Southeastern China

Age and body size a re critical for understanding life history evolution and ecology.In this study,the age and body size of the Shangcheng stout salamander,Pachyhynobius shangchengensis,from a population in Anhui Province,China,were studied by skeletochronology.The mean age was 8.8±0.2(mean±SD)years in females and 9.6±0.2 in males and ranged 5-13 years for both sexes.The mean age was significantly different between sexes.The mean body size and mass were(100.21±0.91)mm and(31.76±0.73)g in females,and(105.31±1.23)mm and(37.14±1.12)g in males,respectively.Males were significantly larger and heavier than females,indicating sexual size dimorphism.There was a significant positive correlation among body size,body mass,and age,suggesting that the oldest individuals are larger and heavier.The growth rate in males was significantly higher than in females.The present study provides preliminary data on life-history traits which can be helpful for future studies of this species and other hynobiid salamanders.

Geographic Variation in the Skull Morphometry of Four Populations of Batrachuperus karlschmidti(Urodela:Hynobiidae)

Geographic variation of morphology is an important topic of evolutionary biology,and research on geographic variation can provide insights on the formation,evolution,and adaptation of species and subspecies.The vertebrate skull is a developmentally and functionally complex morphological structure with multiple functions,that is susceptible to vary according to selection pressure.In this study,geographic variations in skull morphology of Batrachuperus karlschmidti from four different geographic populations(Shade,Gexi,Shangluokema,and Xinduqiao)were examined via geometric morphometrics.No significant differences were found among these populations with regard to skull size;however,significant variation was found in skull shape.The most notable shape changes are the relative sizes and positions of the frontal,maxilla,pterygoid,and vomer.Skull shape changes were not related to allometry.However,due to limitation of sample populations and size,the results of this study need to be further verified by more sample populations and individuals in the future.The results of this study contribute to our knowledge about these aspects of morphological variability in this species as well as in hynobiid salamanders.

Pose-robust feature learning for facial expression recognition

Automatic facial expression recognition （FER） from non-frontal views is a challenging research topic which has recently started to attract the attention of the research community. Pose variations are difficult to tackle and many face analysis methods require the use of sophisticated nor- malization and initialization procedures. Thus head-pose in- variant facial expression recognition continues to be an is- sue to traditional methods. In this paper, we propose a novel approach for pose-invariant FER based on pose-robust fea- tures which are learned by deep learning methods -- prin- cipal component analysis network （PCANet） and convolu- tional neural networks （CNN） （PRP-CNN）. In the first stage, unlabeled frontal face images are used to learn features by PCANet. The features, in the second stage, are used as the tar- get of CNN to learn a feature mapping between frontal faces and non-frontal faces. We then describe the non-frontal face images using the novel descriptions generated by the maps, and get unified descriptors for arbitrary face images. Finally, the pose-robust features are used to train a single classifier for FER instead of training multiple models for each spe- cific pose. Our method, on the whole, does not require pose/ landmark annotation and can recognize facial expression in a wide range of orientations. Extensive experiments on two public databases show that our framework yields dramatic improvements in facial expression analysis.