oalib

Publish in OALib Journal

ISSN: 2333-9721

APC: Only $99

Submit

Any time

2019 ( 93 )

2018 ( 725 )

2017 ( 766 )

2016 ( 728 )

Custom range...

Search Results: 1 - 10 of 55330 matches for " GENG Guo-hua "
All listed articles are free for downloading (OA Articles)
Page 1 /55330
Display every page Item
Fast intra-prediction mode selection algorithm for H.264/AVC
H.264/AVC快速帧内预测模式选择算法

ZHANG Min,GENG Guo-hua,
张敏
,耿国华

计算机应用研究 , 2011,
Abstract: This paper proposed a fast prediction mode selection algorithm based on measurement of direction prediction mode, by measuring the intra-prediction direction of 4×4 block, it used the correlation between neighboring blocks and neighboring direction prediction mode to predict the intra-frame mode. Experimental results show that compared with the full searching algorithm, this algorithm can save the encoding time up to 40% averagely when guarantee the capability of the rate distortion and the bits rate, and it improves the encoding efficiency tremendously.
Nonlinear inverse diffusion image enhancement algorithm
一种非线性逆扩散图像增强算法

HUANG Shi-guo,GENG Guo-hua,
黄世国
,耿国华

计算机应用 , 2006,
Abstract: Traditional image enhancement algorithms could not eliminate noise and preserve textures at the same time. According to the principle of linear inverse diffusion, criteria on nonlinear inverse diffusion image enhancement algorithm were put forward and suitable diffusion coefficient was proposed, The experimental results show that this algorithm can enhance image effectively, eliminate the noise in the image and preserve the textures and details.
Sequence iterative 3D registration of multi-view point cloud for archaeological site
古遗址多视点云的渐进式三维配准*

LIU Jun,GENG Guo-hua,
刘军
,耿国华

计算机应用研究 , 2011,
Abstract: Aiming at the multi-resolution point cloud registration problems of the archaeological site scene,this paper put forward a 3D cloud registration method based on sequence iterative.Firstly,based on the synchronous scan image,a rough registration of the adjacent point cloud could be obtained in an interactive way.Secondly,based on a normal-based algorithm of registration sphere center,filtered the points of sphere surface from all scanned point cloud data according to the normal of data points and characteris...
Craniofacial similarity comparison in craniofacial reconstruction
颅面重构中颅面相似度比较*

ZHU Xin-yi,GENG Guo-hua,
朱新懿
,耿国华

计算机应用研究 , 2010,
Abstract: Current methods of craniofacial reconstruction always choose the reference skull or the facial template based on the values of race, gender, age, nutrition, but these values do not include the properties of the skull (shape value e.g.). In addition, whether the reconstruction resembles the person of the object skull or not is still a difficult problem. Therefore, this paper presented a method of craniofacial similarity comparison, in which classified landmarks into two categories and computed different distances, so the reference skull or facial template could be chosen for further computation and to estimate the final result. Experimental results demonstrate the results computed are consistent with what the volunteers chose.
Automatic Face Detection in Video Sequences in Complex Lighting Environments
复杂光照环境下视频人脸序列的自动检测方法

XIE Qian-ru,GENG Guo-hua,
谢倩茹
,耿国华

计算机科学 , 2011,
Abstract: Auto human face detection from video sequences is the base of studies for human face recognition and track- ing. This paper proposed an efficient and robust method to detect face in vido sequences. The key step of this work is to use the technique of image enhancement to alleviate the impact of human face detection caused by variation illumination such as local shadow and highlight The approach firstly strengthens the edge and detail information of images by means of high-frequency enhanced filtering and uses histogram-based technictue to adjust the brightness of the image,then ap- plies the Gabor wavclet to extract features of images,finally trains samples using the adaboost algorithm and complete face detection. The experimental results show that the approach can detect human face accurately under different light- ing conditions.
Design and realization of dynamic rectangle-based clustering approach
基于动态矩形的聚类方法的设计与实现

GAO Yuan,GENG Guo-hua,WANG Yi,
高原
,耿国华,王怡

计算机应用 , 2006,
Abstract: A dynamic rectangle-based clustering approach(DRCA) was presented.The number of data that needed to be examined for clustering was reduced,and in each procedure of clustering,the position comparison between numbers was used without any distance comparison,which made DRCA had the nearly linear time complexity with the size of dataset. The experiment results show that the DRCA is correct and efficient.
Chaotic Hybrid Bacterial Colony Chemotaxis Algorithm Based on Tent Map
Jia-Ze Sun,Guo-Hua Geng,Shu-Yan Wang,Ming-Quan Zhou
Journal of Software , 2012, DOI: 10.4304/jsw.7.5.1030-1037
Abstract: Aiming at improving the global convergence speed of bacterial colony chemotaxis (BCC) optimization algorithm, a new chaotic hybrid bacterial colony chemotaxis (CHBCC) algorithm is introduced through the technique of hybrid algorithm. By integrating elitist strategy and chaotic optimization into bacterial colony chemotaxis optimization algorithm, it greatly enhances the local searching efficiency and global searching performance. Furthermore, the bacteria are divided into two sub-swarms and perform different operations to co-evolve, one sub-swarm searches via BCC and the other searches via chaos algorithm based on Tent Map at the same time. Simulation results on some benchmark functions show that CHBCC is pretty efficient to solve complex problems. It has high optimization efficiency, good global performance, and stable optimization outcomes. The performance of CHBCC is evidently better than BCC and BC.
Canonical LR Parsing Algorithm Based on State Backtracking Technique
基于状态回朔技术的规范LR分析算法

WANG Qiang-hua HOU Hong GENG Guo-hua,
王强华
,侯红,耿国华

计算机科学 , 2009,
Abstract: With its excellent characteristics,LR analysis technique has gained extensive use in pratical.But the practicability of the canonical LR parser,recognizer for the LR(1)language,is strictly limited for the sake of its push down automaton's complexity.Taking advantage of state backtracking technique,we can solve this problem radically.The principles and constructing techniques of the canonical LR parser based on states backtracking technique were presented.
3D model deformation and editing based on geometric feature
基于几何特征的三维模型变形与编辑*

DONG Jian-jun,GENG Guo-hua,ZHOU Ming-quan,
董建军
,耿国华,周明全

计算机应用研究 , 2009,
Abstract: This paper presented a deformation and edition algorithm based on 3D calculation for 3D craniofacial model.The algorithm iteratively calculated feature geometric parameters of face after each deform. When requirement was fitted,it broke and stored model; or else the algorithm kept going on until model deforms to satisfying result.In order to improve the technique of free-form deformation in flexibility of user interaction and modification,improved the algorithm of point constrained deformation. Experiments ...
3D model relevance feedback retrieval algorithm based on range image
一个相关反馈三维模型深度图像检索算法

WANG Xiao-feng,GENG Guo-hua,ZHANG Fei,
王小凤
,耿国华,张 飞

计算机应用研究 , 2012,
Abstract: In 3D model retrieval area, compared to shape features and topological structure features, the method based on image has the advantages that it is easy to realize and the retrieval results are good. But the existing image retrieval methods in 3D model do not consider the depth information and the features cannot express all information of 3D model. This paper proposed the 3D-model relevance feedback retrieval algorithm based on range images. Firstly, this algorithm computed the features of edge direction histogram and Zernike moment of 3D model's range images, then the feature distance was used to retrieval 3D model, and relevance feedback was used to build the classification and label the 3D model in database, at last the trained classification was used to retrieval and label the 3D model. The experiments show that the algorithm improves the accuracy and practicability of system, and realizes the relevance feedback retrieval and the 3D model's label which lay the foundation for semantic retrieval.
Page 1 /55330
Display every page Item


Home
Copyright © 2008-2017 Open Access Library. All rights reserved.