http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
An image thresholding method based on the target extraction
Yunjie Zhang,Yi Li,Zhijun Gao,Weina Wang 한국전산응용수학회 2008 Journal of applied mathematics & informatics Vol.26 No.3-4
In this paper an algorithm, based on extracting a certain target of an image, is proposed that is capable of performing bilevel threshold- ing of image with multimodal distribution. Each pixel in the image has a membership value which is used to denote the characteristic relationship between the pixel and its belonging region (i.e. the object or background). Using the membership values of image set, a new measurement, which simultaneously measures the measure of fuzziness and the conditional en- tropy of the image, is calculated. Then, thresholds are found by optimally minimizing calculated measurement. In addition, a fuzzy range is defined to improve the threshold values. The experimental results demonstrate that the proposed approach can select the thresholds automatically and ef- fectively extract the meaningful target from the input image. The resulting image can preserve the object region we target very well. In this paper an algorithm, based on extracting a certain target of an image, is proposed that is capable of performing bilevel threshold- ing of image with multimodal distribution. Each pixel in the image has a membership value which is used to denote the characteristic relationship between the pixel and its belonging region (i.e. the object or background). Using the membership values of image set, a new measurement, which simultaneously measures the measure of fuzziness and the conditional en- tropy of the image, is calculated. Then, thresholds are found by optimally minimizing calculated measurement. In addition, a fuzzy range is defined to improve the threshold values. The experimental results demonstrate that the proposed approach can select the thresholds automatically and ef- fectively extract the meaningful target from the input image. The resulting image can preserve the object region we target very well.
AN IMAGE THRESHOLDING METHOD BASED ON THE TARGET EXTRACTION
Zhang, Yunjie,Li, Yi,Gao, Zhijun,Wang, Weina Korean Society of Computational and Applied Mathem 2008 Journal of applied mathematics & informatics Vol.26 No.3-4
In this paper an algorithm, based on extracting a certain target of an image, is proposed that is capable of performing bilevel thresholding of image with multimodal distribution. Each pixel in the image has a membership value which is used to denote the characteristic relationship between the pixel and its belonging region (i.e. the object or background). Using the membership values of image set, a new measurement, which simultaneously measures the measure of fuzziness and the conditional entropy of the image, is calculated. Then, thresholds are found by optimally minimizing calculated measurement. In addition, a fuzzy range is defined to improve the threshold values. The experimental results demonstrate that the proposed approach can select the thresholds automatically and effectively extract the meaningful target from the input image. The resulting image can preserve the object region we target very well.
Gene Expression of Heart and Adipocyte Fatty Acid-binding Protein in Chickens by FQ-RT-PCR
Tu, Yunjie,Su, Yijun,Wang, Kehua,Zhang, Xueyu,Tong, Haibing,Gao, Yushi Asian Australasian Association of Animal Productio 2010 Animal Bioscience Vol.23 No.8
This study was to detect the expression of heart fatty acid-binding protein (H-FABP) and adipocyte fatty acid-binding protein (A-FABP) gene mRNA in different tissues of Rugao and Luyuan chickens at 56 d and 120 d by real-time fluorescence quantitative reverse transcription polymerase-chain reaction (FQ-RT-PCR). The primers were designed according to the sequences of HFABP, A-FABP and GAPDH genes in Gallus gallus, which were used as target genes and internal reference gene, respectively. The levels of H-FABP and A-FABP gene expression were detected by SYBR Green I FQ-RT-PCR. The relative H-FABP and A-FABP gene mRNA expression level was calculated with 2-$^{{\Delta}Ct}$. Melting curve analysis showed a single peak of three genes. Intramuscular fat (IMF) content in breast muscle and leg muscle of the two chicken breeds at 120 d was higher than at 56 d. IMF content in breast muscle and leg muscle at 56 d and 120 d in Luyuan was significantly higher than in Rugao, however, abdominal fat of Luyuan was significantly lower than that of Rugao. The relative H-FABP gene mRNA expression level in cardiac muscle was the highest in both chicken breeds. The relative H-FABP and A-FABP gene expression of different tissues in Luyuan was higher than in Rugao. H-FABP gene mRNA expression had a negative effect on IMF of leg and breast muscles, and was significantly negatively correlated with IMF content. The relative A-FABP gene mRNA level in abdominal fat was higher than in liver. The A-FABP gene mRNA was not expressed in leg, breast and cardiac muscles. A-FABP gene mRNA expression level was significantly positively correlated with abdominal fat and had a significant effect on abdominal fat but not IMF content.
Bearing Fault Diagnosis of Single-Channel Data by a 3D DCN with Bilinear LBP and Modified KPCA
Zhao Yunji,Zhou Menglin,Wang Li,Xu Xiaozhuo,Zhang Nannan 대한전기학회 2023 Journal of Electrical Engineering & Technology Vol.18 No.5
The vibration signal has the characteristics of nonlinear and non-stationary, and the distribution of fault feature information contained in it is not concentrated. In addition, the nonlinear coupling of fault-adjacent features in space is strong, resulting in poor spatial separability of fault information. At the same time, the fault diagnosis algorithm based on a convolutional neural network, cannot fully obtain the spatial distribution information of fault data due to its fixed geometric structure of convolution kernel. In order to solve the above problems, a novel fault diagnosis method for single-channel bearing fault data is proposed. First, the improved bilinear local binary pattern algorithm is used to extract time series constraint information between different points of the original fault data. Then, considering the strong nonlinear coupling of fault data adjacent features in space, this paper proposes the modified kernel principal component analysis. It obtains information on fault data in high-dimensional space by calculating the kernel space mapping matrix of different fault categories, kernelizing the sample matrix, and mapping the kernel space mapping matrix. Finally, based on this information, a 3D deformable convolution network (DCN) is introduced to obtain the spatial distribution information of fault data. DCN can adaptively adjust the shape of its own convolution kernel according to the input, which can obtain more comprehensive information and further improve the spatial separability of fault data. Experiments on CWRU and XJTU-SY both achieved 100% diagnostic accuracy, which shows the superiority of the proposed method.
Genetic Diversity of 14 Indigenous Grey Goose Breeds in China Based on Microsatellite Markers
Tu, Yunjie,Chen, K.W.,Zhang, S.J.,Tang, Q.P.,Gao, Y.S.,Yang, N. Asian Australasian Association of Animal Productio 2006 Animal Bioscience Vol.19 No.1
This experiment first cloned some microsatellite sequences for goose species by magnetic beads enriched method and studied the genetic structure research of 14 indigenous grey goose breeds using 19 developed and 12 searched microsatellite markers with middle polymorphism. According to the allele frequencies of 31 microsatellite sites, mean heterozygosity (H), polymorphism information content (PIC) and $D_A$ genetic distances were calculated for 31-microsatellite sites. The results showed that 25 of 31microsatellite sites were middle polymorphic, so the 25 microsatellite markers were effective markers for analysis of genetic relationship among goose breeds. The mean heterozygosity was between 0.4985 and 0.6916. The highest was in the Xupu (0.6916), and in the Yan was the lowest (0.4985) which was consistent with that of PIC. The phylogenetic tree was completed through analysis of UPGMA. Fencheng Grey, Shoutou, Yangjiang and Magang were grouped firstly, then Xongguo Grey, Wugang Tong, Changle and Youjiang were the second group; Gang, Yan Xupu and Yili were the third group; Yongkang Grey and Wuzeng were the fourth group. The results could provide basic molecular data for the research on the characteristics of local breeds in the eastern China, and a scientific basis for the conservation and utilization of those breeds.