| 1. | Observing lots of palm images and their palm - line undirected graph and analyzing the experts ’ knowledge , we extract the recognition features of cross structure and mi structure
观察大量的手掌图像及其相应的掌纹线无向图,并结合手掌诊病专家知识,分别提取出十字纹和米字纹的识别特征。 |
| 2. | The above research results show that the proposed pd recognition features set and fic method , can be effectively used for pd pattern recognition and good recognition results are achieved
以上研究表明，提出的局部放电识别特征集与分形图像压缩方法，能够有效地应用于局部放电模式自动识别，并获得了良好的识别效果。 |
| 3. | Caption recognition feature extraction using wavelet transformation and the combination of statistical language model and hidden markov model methods finally achieved the identification of caption
基于统计机器学习的字幕识别提取小波变换的特征并使用隐马尔可夫模型和统计语言模型的识别技术相结合的机器学习方法，实现字幕文字的识别。 |
| 4. | We provide a chinese layout analysis method base on fuzzy connectedness and recognition features for complex document layout . this is a process including the input document images . , skew correction and texts / graphics segmentation
本文针对复杂的中文版面，提出了一个基于模糊连接度和识别特征的中文版面分析方法，完成了一个图像输入、倾斜校正、版面图文分割的过程。 |
| 5. | And then in - depth researches are made in vehicle recognition features extraction and recognition method . in addition , a vehicle target recognition method with neural network is tested . the main results are as follows : 1
主要内容如下: 1 .本文所处理的数据源随着拍摄时间的变化视频图像的亮度有很大的差异,而且拍摄背景比较复杂,同一车辆目标在不同角度和姿态下其光照与纹理也有较大的变化。 |
| 6. | This eye tracker can accurately track every tiny eye movements during lasik surgery ; iris recognition features the safest measure as no two irises are identical , this ensures the correct eye is treated . these advance technologies in turn maximize the chance of having best surgical outcomes
这眼球追踪器能准确地追踪手术时眼球的轻微移动由于没有两只眼睛的虹膜是完全相同的，虹膜辨识技术就可准确地辨识不同的虹膜，这安全措施确保眼睛得到正确的治疗，令手术更精确和安全，视力效果更理想。 |
| 7. | A combined recognition feature extraction method based on vehicle target contour is given . this kind of recognition feature includes global shape features and local statistic features of target contour ’ s horizontal and vertical part . it can be used in visible light and infrared situation , and it has good stability and consistency even if the illumination and texture changed
基于这些特点,本文给出一种基于车辆目标轮廓的组合识别特征提取方法,所提取的组合特征包括以车辆目标轮廓为基础的全局形状矩特征和以车辆目标轮廓纵横向分量为基础的局部统计特征,该方法具有较强的稳定性和一致性。 |
| 8. | Furthermore , good compression effectivity is presented in application to compression of pd gray intensity images . according to the research on difference degree between computational values of fractal features extracted from decoded pd images and that from original images , it is shown elementarily that the proposed method is effective for application in pd pattern auto - recognition system . ( 4 ) this paper brings forward pd pattern auto - recognition project based on the above recognition features and fractal compression of pd gray intensity images and designs the classifier with back - propagation neural network ( bpnn )
( 3 )研究了局部放电灰度图像的四叉树分形图像压缩方法，通过仿真实验证明采用本文算法能够获得一定的图像压缩比，在局部放电灰度图像压缩应用中显示了良好的压缩效果，进一步研究了局部放电解码图像的识别结果与原始图像之结果的差异程度，研究结果初步表明该方法应用于局部放电模式自动识别系统中是有效的； ( 4 )研究了基于局部放电解码图像的bpnn识别方法及，通过分析对解码图像的识别效果，验证了设计的系统模式识别方案的有效性，同时表明该方案能够满足实地局部放电模式自动识别和远程数据通讯及自动识别的需要。 |
| 9. | In the dissertation are discussed the infrared video object recognition features , the infrared rosette scan subimage technology , the fast object recognition and tracking technology and the design - consideration of miniature system , etc . based on those , system experimenting is made and good results are shown
本文研究远程红外目标识别特征，玫瑰扫描亚成像与目标检测，快速目标识别跟踪技术及小型化系统的研制等，并在此基础上进行了系统实验，取得了良好的结果。 |
| 10. | A parallel distributed sequential fusion detection algorithm is also developed for the multi - band target detection problem . the optimized fusion algorithm is determined based on the theory analysis and the experiment ’ s results . the exo - atmospheric ballistic target ’ s optical signature and recognition feature is studied
针对多波段条件下的目标融合检测问题,采用并行分布式序贯融合算法对各通道的检测结果进行融合处理,并根据理论分析和仿真实验结果确定了最佳的序贯融合检测算法。 |
