基于Batch Normalization的UNet视网膜血管分割算法

视网膜血管的提取可以通过卷积神经网络学习的方法,但这种方法容易受到初始图像质量的影响,存在网络学习速度慢、效率低的问题.针对这一问题,提出了一种融合Batch Normalization和UNet卷积神经网络的视网膜血管分割算法.以视网膜图像的三原色通道作为网络的输入数据,然后利用融合批归一化的UNet卷积神经网络对分割模型进行训练,进一步优化网络效率.经过测试和验证,结果表明,在DRIVE公开数据集上,该方法能够更好地提取周围血管结构,灵敏度、准确度、特异性和曲线下面积均较好.

基于TZ Normalization规整的话者确认阈值选取

针对说话人确认中,各目标话者模型输出评分分布不一致而导致系统确认阈值设置的困难,本文采取了通过评分规整确定系统最小检测代价函数(DCF)确认阈值的方法。在分析了已有的两种评分规整方法Z norm a l-ization和T norm a lization的基础上,提出了一种结合两者优点的组合规整方法——TZ norm a lization,并据此给出了一种阈值动态修正方法,有效地提高了系统的性能和阈值选取的鲁棒性。对历年的N IST(手机电话语音)评测语料库进行了实验,表明了该方法的有效性。

基于CNN和Group Normalization的校园垃圾图像分类

为解决大学校园的垃圾回收分类问题,提出了一种基于卷积神经网络和归一化技术的垃圾图像分类方法,不需要对输入的图像进行复杂的处理,网络模型即可根据算法提取图像特征,通过加入群组归一化(Group Normalization)和网络模型各层之间的协作,克服传统分类算法的缺点,实现对垃圾图像的分类。实验表明,该识别方法具有较高准确率,可以较好识别不可回收及可回收垃圾。

Evaluation of Two Absolute Radiometric Normalization Algorithms for Pre-processing of Landsat Imagery

In order to evaluate radiometric normalization techniques, two image normalization algorithms for absolute radiometric correction of Landsat imagery were quantitatively compared in this paper, which are the Illumination Correction Model proposed by Markham and Irish and the Illumination and Atmospheric Correction Model developed by the Remote Sensing and GIS Laboratory of the Utah State University. Relative noise, correlation coefficient and slope value were used as the criteria for the evaluation and comparison, which were derived from pseudo-invarlant features identified from multitemporal Landsat image pairs of Xiamen （厦门） and Fuzhou （福州） areas, both located in the eastern Fujian （福建） Province of China. Compared with the unnormalized image, the radiometric differences between the normalized multitemporal images were significantly reduced when the seasons of multitemporal images were different. However, there was no significant difference between the normalized and unnorrealized images with a similar seasonal condition. Furthermore, the correction results of two algorithms are similar when the images are relatively clear with a uniform atmospheric condition. Therefore, the radiometric normalization procedures should be carried out if the multitemporal images have a significant seasonal difference.

基于Moment Normalization和M序列的二值水印算法

针对因特网上数字图像的版权保护、认证和完整性等问题,基于DCT变换、image moment normalization和m序列,提出了一种二值水印嵌入算法,实现了二值图像的嵌入和提取。根据m序列的伪随机性和抗干扰性能,使水印具有良好的隐蔽性和稳健性;使用了moment normalization能抵制各种几何攻击。实验表明该算法具有很好的鲁棒性、实用性和可操作性。

Identification of stable normalization genes for quantitative real-time PCR in porcine articular cartilage

Background： Expression levels for genes of interest must be normalized with an appropriate reference, or housekeeping gene, to make accurate comparisons of quantitative real-time PCR results. The purpose of this study was to identify the most stable housekeeping genes in porcine articular cartilage subjected to a mechanical injury from a panel of 10 candidate genes. Results： Ten candidate housekeeping genes were evaluated in three different treatment groups of mechanically impacted porcine articular cartilage. The genes evaluated were： beta actin, beta-2-microglobulin, glyceraldehyde-3-phosphate dehydrogenase, hydroxymethylbilane synthase, hypoxanthine phosphoribosyl transferase, peptidylprolyl isomerase A （cyclophilin A）, ribosomal protein L4, succinate dehydrogenase flavoprotein subunit A, TATA box binding protein, and tyrosine 3-monooxygenase/tryptophan 5-monooxygenase activation protein--zeta polypeptide The stability of the genes was measured using geNorm, BestKeeper, and NormFinder software. The four most stable genes measured via geNorm were （most to least stable） succinate dehydrogenase flavoprotein, subunit A, peptidylprolyl isomerase A, glyceraldehyde-3-phosphate dehydrogenase, beta actin; the four most stable genes measured via BestKeeper were glyceraldehyde-3-phosphate dehydrogenase, peptidylprolyl isomerase A, beta actin, succinate dehydrogenase flavoprotein, subunit A; and the four most stable genes measured via NormFinder were peptidylprolyl isomerase A, sucdnate dehydrogenase flavoprotein, subunit A, glyceraldehyde-3-phosphate dehydrogenase, beta actin. Conclusions： BestKeeper, geNorm, and NormFinder all generated similar results for the most stable genes in porcine articular cartilage. The use of these appropriate reference genes will facilitate accurate gene expression studies of porcine articular cartilage and suggest appropriate housekeeping genes for articular cartilage studies in other species.

Normalization of Hydrodynamic Coefficients in Morison Equation

The hydrodynamic coefficients C-d and C-m are not only dependent on the size of slender cylinder, its location in water, KC number and Re number, but also vary with environmental conditions, i.e., in regular waves or in irregular waves, in pure waves or in wave-current coexisting field. In this paper, the normalization of hydrodynamic coefficients for various environmental conditions is discussed. When a proper definition of KC number and proper characteristic values of irregular waves are used, a unified relationship between C-d, C-m and KC number for regular waves, irregular waves, pure waves and wave-current coexisting field can be obtained.

Application of well log normalization in coalfield seismic inversion

During the process of coal prospecting and exploration, different measurement time, different logging instruments and series can lead to systematic errors in well logs. Accordingly, all logging curves need to be normalized in the mining area. By studying well-logging normalization methods, and focusing on the characteristics of the coalfield, the frequency histogram method was used in accordance with the condition of the Guqiao Coal Mine. In this way, the density and sonic velocity at marker bed in the non-key well were made to close to those in the key well, and were eventually equal. Well log normalization was completed when this method was applied to the entire logging curves. The results show that the scales of logging data were unified by normalizing coal logging curves, and the logging data were consistent with wave impedance inversion data. A satisfactory inversion effect was obtained.

3D numerical study of tumor blood perfusion and oxygen transport during vascular normalization

The changes of blood perfusion and oxygen transport in tumors during tumor vascular normalization are studied with 3-dimensional mathematical modeling and numerical simulation. The models of tumor angiogenesis and vascular-disrupting are used to simulate ＂un-normalized＂ and ＂normalized＂ vasculatures. A new model combining tumor hemodynamics and oxygen transport is developed. In this model, the intravasculartransvascular-interstitial flow with red blood cell（RBC） delivery is tightly coupled, and the oxygen resource is produced by heterogeneous distribution of hematocrit from the flow simulation. The results show that both tumor blood perfusion and hematocrit in the vessels increase, and the hypoxia microenvironment in the tumor center is greatly improved during vascular normalization. The total oxygen content inside the tumor tissue increases by about 67%, 51%, and 95% for the three approaches of vascular normalization,respectively. The elevation of oxygen concentration in tumors can improve its metabolic environment, and consequently reduce malignancy of tumor cells. It can also enhance radiation and chemotherapeutics to tumors.

Optical-Elevation Data Co-Registration and Classification-Based Height Normalization for Building Detection in Stereo VHR Images

Building detection in very high resolution (VHR) images is crucial for mapping and analysing urban environments. Since buildings are elevated objects, elevation data need to be integrated with images for reliable detection. This process requires two critical steps: optical-elevation data co-registration and aboveground elevation calculation. These two steps are still challenging to some extent. Therefore, this paper introduces optical-elevation data co-registration and normalization techniques for generating a dataset that facilitates elevation-based building detection. For achieving accurate co-registration, a dense set of stereo-based elevations is generated and co-registered to their relevant image based on their corresponding image locations. To normalize these co-registered elevations, the bare-earth elevations are detected based on classification information of some terrain-level features after achieving the image co-registration. The developed method was executed and validated. After implementation, 80% overall-quality of detection result was achieved with 94% correct detection. Together, the developed techniques successfully facilitate the incorporation of stereo-based elevations for detecting buildings in VHR remote sensing images.

Identification and evaluation of reference genes for normalization in quantitative real-time PCR analysis in the premodel tree Betula luminifera

Betula luminifera is a commercial tree species that is emerging as a new model system for tree genomics research. A draft genomic sequence is expected to be publicly available in the near future, which means that an explosion of gene expression studies awaits. Thus, the work of selecting appropriate reference genes for q PCR normalization in different tissues or under various experimental conditions is extremely valuable. In this study, ten candidate genes were analyzed in B. luminifera subjected to different abiotic stresses and at various flowering stages.The expression stability of these genes was evaluated using three distinct algorithms implemented using ge Norm,Norm Finder and Best Keeper. The best-ranked reference genes varied across different sample sets, though RPL39,MDH and EF1 a were determined as the most stable by the three programs among all tested samples. RPL39 and EF1 a should be appropriate for normalization in N-starved roots,while the combination of RPL39 and MDH should be appropriate for N-starved stems and EF1 a and MDH should be appropriate in N-starved leaves. In PEG-treated（osmotic） roots, MDH was the most suitable, whereas EF1 a was suitable for PEG-treated stems and leaves. TUA was also stably expressed levels in PEG-treated plants. The combination of RPL39 and TUB should be appropriate for heat-stressed leaves and flowering stage. For reference gene validation, the expression levels of SOD and NFYA-3were investigated. This work will be beneficial to future studies on gene expression under different abiotic stress conditions and flowering status in B. luminifera.

Selection of suitable internal controls for gene expression normalization in rats with spinal cord injury

There is a lack of systematic research on the expression of internal control genes used for gene expression normalization in real-time reverse transcription polymerase chain reaction in spinal cord injury research.In this study,we used rat models of spinal cord hemisection to analyze the expression stability of 13 commonly applied reference genes:Actb,Ankrd27,CypA,Gapdh,Hprt1,Mrpl10,Pgk1,Rictor,Rn18s,Tbp,Ubc,Ubxn11,and Ywhaz.Our results show that the expression of Ankrd27,Ubc,and Tbp were stable after spinal cord injury,while Actb was the most unstable internal control gene.Ankrd27,Ubc,Tbp,and Actb were consequently used to investigate the effects of internal control genes with differing stabilities on the normalization of target gene expression.Target gene expression levels and changes over time were similar when Ankrd27,Ubc,and Tbp were used as internal controls but different when Actb was used as an internal control.We recommend that Ankrd27,Ubc,and Tbp are used as internal control genes for real-time reverse transcription polymerase chain reaction in spinal cord injury research.This study was approved by the Administration Committee of Experimental Animals,Jiangsu Province,China(approval No.20180304-008)on March 4,2018.

Identification of normalization factors for quantitative realtime RT-PCR analysis of gene expression in Pacific abalone Haliotis discus hannai

Quantitative real-time reverse transcription-polymerase chain reaction （qRT-PCR） is widely used in studies of gene expression. In most of these studies, housekeeping genes are used as internal references without validation. To identify appropriate reference genes for qRT-PCR in Pacific abalone Haliotis discus hannai, we examined the transcription stability of six housekeeping genes in abalone tissues in the presence and absence of bacterial infection. For this purpose, abalone were infected with the bacterial pathogen Fibrio anguillarum for 12 h and 48 h. The mRNA levels of the housekeeping genes in five tissues （digestive glands, foot muscle, gill, hemocyte, and mantle） were determined by qRT-PCR. The PCR data was subsequently analyzed with the geNorm and NormFinder algorithms. The results show that in the absence of bacterial infection, elongation factor-l-alpha and beta-actin were the most stably expressed genes in all tissues, and thus are suitable as cross-tissue type normalization factors. However, we did not identify any universal reference genes post infection because the most stable genes varied between tissue types. Furthermore, for most tissues, the optimal reference genes identified by both algorithms at 12 h and 48 h post-infection differed. These results indicate that bacterial infection induced significant changes in the expression of abalone housekeeping genes in a manner that is dependent on tissue type and duration of infection. As a result, different normalization factors must be used for different tissues at different infection points.

Selection and Validation of Reference Genes for Normalization of RT-qPCR Analysis in Developing or Abiotic-Stressed Tissues of Loquat (Eriobotrya japonica)

Loquat(Eriobotrya japonica Lindl.)is a subtropical evergreen fruit tree that produces fruits with abundant nutrients and medicinal components.Confirming suitable reference genes for a set of loquat samples before qRT-PCR experiments is essential for the accurate quantification of gene expression.In this study,eight candidate reference genes were selected from our previously published RNA-seq data,and primers for each candidate reference gene were designed and evaluated.The Cq values of the candidate reference genes were calculated by RT-qPCR in 31 different loquat samples,including 12 subgroups of developing or abiotic-stressed tissues.Different combinations of stable reference genes were screened according to a comprehensive rank,which was synthesized from the results of four algorithms,including the geNorm,NormFinder,BestKeeper andΔCt methods.The screened reference genes were verified by normalizing EjLGA1 in each subgroup.The obtained suitable combinations of reference genes for accurate normalization were GAPDH,EF1αand ACT for floral development;GAPDH,UBCE and ACT for fruit setting;EF1α,GAPDH and eIF2B for fruit ripening;ACT,EF1αand UBCE for leaves under heat stress;eIF2B,UBCE and EF1αfor leaves under freezing stress;EF1α,TUA and UBCE for leaves under salt stress;ACT,EF1αand eIF2B for immature pulp under freezing stress;ACT,UBCE and eIF2B for immature seeds under freezing stress;EF1α,eIF2B and UBCE for both immature pulp and seeds under freezing stress;UBCE,TUB and TUA for red-fleshed fruits under cold-storage stress;eIF2B,RPS3 and TUB for white-fleshed fruits under coldstorage stress;and eIF2B,UBCE and RPS3 for both red-and white-fleshed fruits under cold-storage stress.This study obtained different combinations of stable reference genes for accurate normalization in twelve subgroups of developing or abiotic-stressed tissues in loquat.To our knowledge,this is the first report to obtain stable reference genes for normalizing gene expression of abiotic-stressed tissues in E.japonica.The use of the three most stable reference genes could increase the reliability of future quantification experiments.

Face Orientation Normalization Using Eye Positions

Despite the fact that progress in face recognition algorithms over the last decades has been made, changing lighting conditions and different face orientation still remain as a challenging problem. A standard face recognition system identifies the person by comparing the input picture against pictures of all faces in a database and finding the best match. Usually face matching is carried out in two steps： during the first step detection of a face is done by finding exact position of it in a complex background （various lightning condition）, and in the second step face identification is performed using gathered databases. In reality detected faces can appear in different position and they can be rotated, so these disturbances reduce quality of the recognition algorithms dramatically. In this paper to increase the identification accuracy we propose original geometric normalization of the face, based on extracted facial feature position such as eyes. For the eyes localization lbllowing methods has been used： color based method, mean eye template and SVM （Support Vector Machine） technique. Experimental investigation has shown that the best results for eye center detection can be achieved using SVM technique. The recognition rate increases statistically by 28% using face orientation normalization based on the eyes position.

Robust Radiometric Normalization of the near Equatorial Satellite Images Using Feature Extraction and Remote Sensing Analysis

Relative radiometric normalization (RRN) minimizes radiometric differences among images caused by inconsistencies of acquisition conditions rather than changes in surface. Scale invariant feature transform (SIFT) has the ability to automatically extract control points (CPs) and is commonly used for remote sensing images. However, its results are mostly inaccurate and sometimes contain incorrect matching caused by generating a small number of false CP pairs. These CP pairs have high false alarm matching. This paper presents a modified method to improve the performance of SIFT CPs matching by applying sum of absolute difference (SAD) in a different manner for the new optical satellite generation called near-equatorial orbit satellite and multi-sensor images. The proposed method, which has a significantly high rate of correct matches, improves CP matching. The data in this study were obtained from the RazakSAT satellite a new near equatorial satellite system. The proposed method involves six steps: 1) data reduction, 2) applying the SIFT to automatically extract CPs, 3) refining CPs matching by using SAD algorithm with empirical threshold, and 4) calculation of true CPs intensity values over all image’ bands, 5) preforming a linear regression model between the intensity values of CPs locate in reverence and sensed image’ bands, 6) Relative radiometric normalization conducting using regression transformation functions. Different thresholds have experimentally tested and used in conducting this study (50 and 70), by followed the proposed method, and it removed the false extracted SIFT CPs to be from 775, 1125, 883, 804, 883 and 681 false pairs to 342, 424, 547, 706, 547, and 469 corrected and matched pairs, respectively.

Speaker Verification Based on Log-Likelihood Score Normalization

Due to differences in the distribution of scores for different trials, the performance of a speaker verification system will be seriously diminished if raw scores are directly used for detection with a unified threshold value. As such, the scores must be normalized. To tackle the shortcomings of score normalization methods, we propose a speaker verification system based on log-likelihood normalization (LLN). Without a priori knowledge, LLN increases the separation between scores of target and non-target speaker models, so as to improve score aliasing of “same-speaker” and “different-speaker” trials corresponding to the same test speech, enabling better discrimination and decision capability. The experiment shows that LLN is an effective method of scoring normalization.

Cyclic shear behavior of en-echelon joints under constant normal stiffness conditions

To reveal the mechanism of shear failure of en-echelon joints under cyclic loading,such as during earthquakes,we conducted a series of cyclic shear tests of en-echelon joints under constant normal stiffness(CNS)conditions.We analyzed the evolution of shear stress,normal stress,stress path,dilatancy characteristics,and friction coefficient and revealed the failure mechanisms of en-echelon joints at different angles.The results show that the cyclic shear behavior of the en-echelon joints is closely related to the joint angle,with the shear strength at a positive angle exceeding that at a negative angle during shear cycles.As the number of cycles increases,the shear strength decreases rapidly,and the difference between the varying angles gradually decreases.Dilation occurs in the early shear cycles(1 and 2),while contraction is the main feature in later cycles(310).The friction coefficient decreases with the number of cycles and exhibits a more significant sensitivity to joint angles than shear cycles.The joint angle determines the asperities on the rupture surfaces and the block size,and thus determines the subsequent shear failure mode(block crushing and asperity degradation).At positive angles,block size is more greater and asperities on the rupture surface are smaller than at nonpositive angles.Therefore,the cyclic shear behavior is controlled by block crushing at positive angles and asperity degradation at negative angles.

Higher order asymptotic behaviour of partial maxima of random sample from generalized Maxwell distribution under power normalization

In this article, the higher order asymptotic expansions of cumulative distribution function and probability density function of extremes for generalized Maxwell distribution are established under nonlinear normalization. As corollaries, the convergence rates of the distribu- tion and density of maximum are obtained under nonlinear normalization.