Evaluation of CD109, PCP4 and SEMA3D genes for their association with Ovine Johne's disease in Turkish sheep.

Johne's disease is a chronic, contagious, zoonotic disease that affects numerous species including livestock and sometimes humans. The disease is globally distributed in sheep populations and caused by Mycobacterium avium Subsp. paratuberculosis (MAP). A previous genome-wide association study identified single nucleotide polymorphism (SNP) markers associated with OJD serostatus in CD109, PCP4, and SEMA3D genes. Our aim was to evaluate the same markers for association with OJD seroprevalence in Turkish sheep in a retrospective matched case-control study. The serological status for OJD in 1801 sheep was determined for four native and four composite breeds from three research flocks. One hundred eleven matched case-control pairs were constructed according to breed type and age from 1750 comingled ewes reared in the same environment. A Single Nucleotide Primer Extension (SNuPE) assay was designed to genotype PCP4-Intron 1, PCP4-3'UTR, SEMA3D, CD109-intron 2 and CD109-intron 8 markers and a McNemar's test was performed on the matched pairs. An association with these five markers was not detected with the OJD serostatus in Turkish sheep (power of detection, 0.95; odds ratio >3; McNemar's p < .05). Thus, a wider search may be needed to identify any major underlying genetic risk factors for OJD in Turkish sheep.

Pairwise Identity Verification via Linear Concentrative Metric Learning.

This paper presents a study of metric learning systems on pairwise identity verification, including pairwise face verification and pairwise speaker verification, respectively. These problems are challenging because the individuals in training and testing are mutually exclusive, and also due to the probable setting of limited training data. For such pairwise verification problems, we present a general framework of metric learning systems and employ the stochastic gradient descent algorithm as the optimization solution. We have studied both similarity metric learning and distance metric learning systems, of either a linear or shallow nonlinear model under both restricted and unrestricted training settings. Extensive experiments demonstrate that with limited training pairs, learning a linear system on similar pairs only is preferable due to its simplicity and superiority, i.e., it generally achieves competitive performance on both the labeled faces in the wild face dataset and the NIST speaker dataset. It is also found that a pretrained deep nonlinear model helps to improve the face verification results significantly.

Improving Zernike moments comparison for optimal similarity and rotation angle retrieval.

Zernike moments constitute a powerful shape descriptor in terms of robustness and description capability. However the classical way of comparing two Zernike descriptors only takes into account the magnitude of the moments and loses the phase information. The novelty of our approach is to take advantage of the phase information in the comparison process while still preserving the invariance to rotation. This new Zernike comparator provides a more accurate similarity measure together with the optimal rotation angle between the patterns, while keeping the same complexity as the classical approach. This angle information is particularly of interest for many applications, including 3D scene understanding through images. Experiments demonstrate that our comparator outperforms the classical one in terms of similarity measure. In particular the robustness of the retrieval against noise and geometric deformation is greatly improved. Moreover, the rotation angle estimation is also more accurate than state-of-the-art algorithms.