Dynamic Hand Gesture Segmentation Method Based on Improved Kalman Filter and Weighted Skin-Color Model

Zhang Qiu-yu,Lu Jun-chi,Wei Hui-yi,Zhang Mo-yi,Duan Hong-xiang 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.6

In order to improve the problems of segmentation accuracy and real-time existing in dynamic hand gesture under complex backgrounds, this paper presents a kind of dynamic hand gesture segmentation method based on improved Kalman filter and weighted skin-color model. Firstly, improved Kalman filter is utilized to process hand gesture image of hand gesture video sequences and get rough hand gesture results. Secondly, weighted skin-color model is applied to process rough results of hand gesture segmentation and segment hand gesture. Finally, morphological method is utilized to deal with gesture segmentation result, getting rid of the holes in the hand gesture’s binary image to realize the segmentation of dynamic hand gesture. Experiments show that the proposed method can segment hand gesture from dynamic hand gesture video sequences with complex backgrounds effectively. And the accuracy of hand gesture segmentation is high.

Dynamic Hand Gesture Trajectory Recognition Based on Block Feature and Skin-Color Clustering

Zhang Qiu-yu,Lv Lu,Lu Jun-chi,Zhang Mo-yi,Duan Hong-xiang 보안공학연구지원센터 2016 International Journal of Multimedia and Ubiquitous Vol.11 No.12

In recent years, dynamic hand gesture recognition has been a research hotspot of human-computer interaction. Since most existing algorithms contain problems with high computational complexity, poor real-time performance and low recognition rate, which cannot satisfy the need of many practical applications. Moreover, key frames obtained by inter-frame difference degree algorithm contain less information, which leads to less identified species and lower recognition rate. To solve these problems, we present a dynamic hand gesture trajectory recognition method based on the theory of block feature to extract key frames and the skin-color clustering’s hand gesture segmentation. Firstly, this method extracts block feature of degree of difference between frames in hand gesture sequence to select key frames accurately. Secondly, the method based on skin-color clustering is applied to obtain the area of hand gesture after segmenting hand gestures from images. Finally, hidden Markov model (HMM), in which the angle data of hand gesture trajectories are input, is used for modeling and identifying dynamic hand gestures. Experimental results show that the method of key-frame extraction is used to obtain information of dynamic hand gestures accurately, which would improve the recognition rate of dynamic hand gesture recognition and, at the same time, can guarantee the real-time of hand gesture recognition system. The average recognition rate is up to 86.67%, and the average time efficiency is 0.39s.

Hand Gesture Segmentation Method Based on YCbCr Color Space and K-Means Clustering

Zhang Qiu-yu,Lu Jun-chi,Zhang Mo-yi,Duan Hong-xiang,Lv Lu 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.5

Aiming at the problems that current skin-color detection segmentation technologies have unsatisfied segmentation results under conditions of complex illumination or backgrounds, we present a new method based on YCbCr color space and K-means clustering algorithm for segmentation hand gesture. Firstly, image in RGB color space is converted to YCbCr color space; and then YCbCr color space of image is divided into luminance Y and chrominance Cb and Cr. Lastly, the binary image is achieved by clustering values of chrominance using k-means clustering algorithm, and hand gesture segmentation is completed by conducting morphological process of binary image obtained. The experimental results illustrate that the proposed method can segment hand gestures from complex backgrounds and obtain segmentation results. The phenomena of similar skin color interference and skin color overlapping are solved with this method effectively. In addition, it is robust to illumination condition.

A Dynamic Gesture Trajectory Recognition Based on Key Frame Extraction and HMM

Zhang Qiu-yu,Lv Lu,Zhang Mo-yi,Duan Hong-xiang,Lu Jun-chi 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.6

Aiming at changing high computational complexity, underdeveloped real time, low recognition rate of dynamic gesture recognition algorithms, this paper present a real-time dynamic gesture trajectory recognition method based on key frame extraction and HMM. Key frames are selected without keeping track of all the details of one dynamic gesture, which is based on difference degree between frames. The trajectory data stream, sorted by the time-warping algorithm, is used to construct the Hidden Markov Method model of dynamic gesture. Finally, optimal transition probabilities are employed to implement dynamic gesture recognition. The result of this experiment implies that this method has high robustness and real time. The average recognition rate of dynamic gesture (0~9) is up to 87.67%, and average time efficiency is 0.46s.

ARPES study of the epitaxially grown topological crystalline insulator SnTe(111)

Zhang, Yi,Liu, Zhongkai,Zhou, Bo,Kim, Yeongkwan,Yang, Lexian,Ryu, Hyejin,Hwang, Choongyu,Chen, Yulin,Hussain, Zahid,Shen, Zhi-Xun,Mo, Sung-Kwan Elsevier 2017 Journal of electron spectroscopy and related pheno Vol.219 No.-

<P><B>Abstract</B></P> <P>SnTe is a prototypical topological crystalline insulator, in which the gapless surface state is protected by a crystal symmetry. The hallmark of the topological properties in SnTe is the Dirac cones projected to the surfaces with mirror symmetry, stemming from the band inversion near the L points of its bulk Brillouin zone, which can be measured by angle-resolved photoemission. We have obtained the (111) surface of SnTe film by molecular beam epitaxy on BaF<SUB>2</SUB>(111) substrate. Photon-energy-dependence of <I>in situ</I> angle-resolved photoemission, covering multiple Brillouin zones in the direction perpendicular to the (111) surface, demonstrate the projected Dirac cones at the Γ ¯ and M ¯ points of the surface Brillouin zone. In addition, we observe a Dirac-cone-like band structure at the Γ point of the bulk Brillouin zone, whose Dirac energy is largely different from those at the Γ ¯ and M ¯ points.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Topological crystalline insulator SnTe(111) thin film was grown on BaF<SUB>2</SUB>(111) substrate by using molecular beam epitaxy. </LI> <LI> The electronic structures of SnTe(111) with surface Dirac cones were studied by a wide-range photon-energy-dependent angle-resolved photoemission spectroscopy. </LI> <LI> A Dirac-cone-like band structure was observed at the Γ point of the bulk Brillouin zone of SnTe(111). </LI> </UL> </P>

Dynamics of Microbial Community Structure, Function and Assembly Mechanism with Increasing Stand Age of Slash Pine (Pinus elliottii) Plantations in Houtian Sandy Area, South China

Zhang Xiaoyang,Xiong Si-Yi,Wu Xiukun,Zeng Bei-Bei,Mo Yang-Mei,Deng Zhi-Cheng,Wei Qi,Gao Yang,Cui Licao,Liu Jianping,Long Haozhi 한국미생물학회 2023 The journal of microbiology Vol.61 No.11

Establishing slash pine plantations is the primary method for restoring sandification land in the Houtian area of South China. However, the microbial variation pattern with increasing stand age remains unclear. In this study, we investigated microbial community structure and function in bare sandy land and four stand age gradients, exploring ecological processes that determine their assembly. We did not observe a significant increase in the absolute abundance of bacteria or fungi with stand age. Bacterial communities were dominated by Chloroflexi, Actinobacteria, Proteobacteria, and Acidobacteria; the relative abundance of Chloroflexi significantly declined while Proteobacteria and Acidobacteria significantly increased with stand age. Fungal communities showed succession at the genus level, with Pisolithus most abundant in soils of younger stands (1- and 6-year-old). Turnover of fungal communities was primarily driven by stochastic processes; both deterministic and stochastic processes influenced the assembly of bacterial communities, with the relative importance of stochastic processes gradually increasing with stand age. Bacterial and fungal communities showed the strongest correlation with the diameter at breast height, followed by soil available phosphorus and water content. Notably, there was a significant increase in the relative abundance of functional groups involved in nitrogen fixation and uptake as stand age increased. Overall, this study highlights the important effects of slash pine stand age on microbial communities in sandy lands and suggests attention to the nitrogen and phosphorus requirements of slash pine plantations in the later stages of sandy management.

Characterization of Mutations in AlHK1 Gene from Alternaria Longipes: Implication of Limited Function of Two-Component Histidine Kinase on Conferring Dicarboximide Resistance

( Yi Yong Luo ),( Jin Kui Yang ),( Ming Liang Zhu ),( Jin Ping Yan ),( Minghe Mo ),( Ke Qin Zhang ) 한국미생물 · 생명공학회 2008 Journal of microbiology and biotechnology Vol.18 No.1

Four series (S, M, R, and W) of Alternaria longipes isolates were obtained based on consecutive selection with Dimethachlon (Dim) and ultraviolet irradiation. These isolates were then characterized according to their tolerance to Dim, sensitivity to osmotic stress, and phenotypic properties. All the selected Dim-resistant isolates showed a higher osmosensitivity than the parental strains, and the last generation was more resistant than the first generation in the M, R, and W series. In addition, the changes in the Dim resistance and osmotic sensitivity were not found to be directly correlated, and no distinct morphologic characteristics were found among the resistant and sensitive isolates, with the exception of the resistant isolate K-11. Thus, to investigate the molecular basis of the fungicide resistance, a group III two-component histidine kinase (HK) gene, AIHK1, was cloned from nineteen A. longipes isolates. AIHK1p was found to be comprised of a six 92-amino-acid repeat domain (AARD), HK domain, and response regulator domain, similar to the Os-1p from Neurospora crassa. A comparison of the nucleotide sequences of the AIHK1 gene from the Dim-sensitive and -resistant isolates revealed that all the resistant isolates contained a single-point mutation in the AARD of AIHK1p, with the exception of isolate K-11, where the AIHK1p contained a deletion of 107 amino acids. Moreover, the AIHK1p mutations in the isolates of each respective series involved the same amino acid substitution at the same site, although the resistance levels differed significantly in each series. Therefore, these findings suggested that a mutation in the AARD of AIHK1p was not the sole factor responsible for A. longipes resistance to dicarboximide fungicides.

Spin-resolved photoemission study of epitaxially grown MoSe₂ and WSe₂ thin films

Mo, Sung-Kwan,Hwang, Choongyu,Zhang, Yi,Fanciulli, Mauro,Muff, Stefan,Hugo Dil, J,Shen, Zhi-Xun,Hussain, Zahid IOP 2016 Journal of Physics, Condensed Matter Vol.28 No.45

<P>Few-layer thick MoSe<SUB>2</SUB> and WSe<SUB>2</SUB> possess non-trivial spin textures with sizable spin splitting due to the inversion symmetry breaking embedded in the crystal structure and strong spin–orbit coupling. We report a spin-resolved photoemission study of MoSe<SUB>2</SUB> and WSe<SUB>2</SUB> thin film samples epitaxially grown on a bilayer graphene substrate. We only found spin polarization in the single- and trilayer samples—not in the bilayer sample—mostly along the out-of-plane direction of the sample surface. The measured spin polarization is found to be strongly dependent on the light polarization as well as the measurement geometry, which reveals intricate coupling between the spin and orbital degrees of freedom in this class of material.</P>

Prognostic Value of Serum Epstein–Barr Virus Antibodies and Their Correlation with TNM Classification in Patients with Locoregionally Advanced Nasopharyngeal Carcinoma

Wan-Ru Zhang,Yu-Yun Du,Chun-Yan Guo,Han-Xing Zhou,Jie-Yi Lin,Xiao-Han Meng,Hao-Yuan Mo,Dong-Hua Luo 대한암학회 2021 Cancer Research and Treatment Vol.53 No.4

Purpose This study assessed the correlation between Epstein-Barr virus (EBV) biomarkers and the eighth American Joint Committee on Cancer staging system and the prognostic values of IgG antibodies against replication and transcription activator (Rta-IgG), IgA antibodies against Epstein-Barr nuclear antigen 1, and BamH1 Z transactivator (Zta-IgA) in locoregionally advanced nasopharyngeal carcinoma (NPC) patients. Materials and Methods Serum EBV antibody levels were measured by enzyme-linked immunosorbent assay in 435 newly diagnosed stage III-IVA NPC patients administered intensity-modulated radiation therapy±chemotherapy. The primary endpoint was progression-free survival (PFS). Results Rta-IgG and Zta-IgA levels were positively correlated with the N category and clinical stage. Patients with high Rta-IgG levels (> 29.07 U/mL) showed a significantly inferior prognosis as indicated by PFS (77% vs. 89.8%, p=0.004), distant metastasis–free survival (DMFS) (88.3% vs. 95.8%, p=0.021), and local recurrence-free survival (LRFS) (91.2% vs. 98.3%, p=0.009). High Rta-IgG levels were also significantly associated with inferior PFS and LRFS in multivariable analyses. In the low-level EBV DNA group (≤ 1,500 copies/mL), patients with high Rta-IgG levels had significantly inferior PFS and DMFS (both p < 0.05). However, in the high-level EBV DNA group, Rta-IgG levels were not significantly associated with PFS, DMFS, and LRFS. In the advanced T category (T3-4) subgroup, high Rta-IgG levels were also significantly associated with inferior PFS, DMFS, and LRFS (both p < 0.05). Conclusion Rta-IgG and Zta-IgA levels were strongly correlated with the TNM classification. Rta-IgG level was a negative prognostic factor in locoregionally advanced NPC patients, especially those with advanced T category or low EBV DNA level.

Functional Roles of the Aromatic Residues in the Stabilization of the [Fe4S4]Cluster in the Iro Protein from Acidithiobacillus ferrooxidans

( Jia Zeng ),( Qing Liu ),( Xiao Jian Zhang ),( Hong Yu Mo ),( Yi Ping Wang ),( Qian Chen ),( Yuan Dong Liu ) 한국미생물 · 생명공학회 2010 Journal of microbiology and biotechnology Vol.20 No.2