高钒高速钢碳化钒形态的数值化分析

针对碳化钒的不同形态,设计出定量分析软件,并利用形状因子K,实现了高钒高速钢不同碳化物形态数值化处理,当K介于0.785～1.000之间碳化钒形态为团球状;K≤0.223,碳化钒呈开花状.高钒高速钢当碳含量达到4.2%时,K为0.86和当量直径D为0.78μm,碳化物呈团球状均匀分布.     

THERMODYNAMICS AND PHASE EQUILIBRIUM OF Cu－Y－O，Cu－Y－S，Cu－Y－O－S LIQUID SOLUTIONS

ＴＨＥＲＭＯＤＹＮＡＭＩＣＳＡＮＤＰＨＡＳＥＥＱＵＩＬＩＢＲＩＵＭＯＦＣｕ－Ｙ－Ｏ，Ｃｕ－Ｙ－Ｓ，Ｃｕ－Ｙ－Ｏ－ＳＬＩＱＵＩＤＳＯＬＵＴＩＯＮＳ￥Ｄｕ，Ｔｉｎｇ；Ｌｉ，Ｇｕｏｄｏｎｇ（ＣｅｎｔｒａｌＩｒｏｎａｎｄＳｔｅｅｌＲｅｓｅａｒｃｈｉｎｓｔｉｔ...     

Intermetallic phase formation in directionally solidified Al−Si−Fe alloy

The present study has been undertaken to better understand the solidification behavior of Al−Si−Fe alloys containing 7wt.% Si and 0.9wt.% Fe, with particular regard to the formation of phase during controlled solidification and influence of growth rates on intermetallic phase selection. The alloys studied were Al-7Si-0.9Fe alloys, which were produced by a modified Bridgman solidification arrangement. These alloys were solidified unidirectionally with different growth rates (1–30mm/min). The solidified microstructure of these alloys consists of the growth of primary aluminum and multiple second phase reactions.     

基于细胞神经网络和网格特征的碑刻文字识别

碑刻作为文字的载体,具有极其重要的历史价值和艺术价值。但是,因为时间的久远,其拓本大量的噪声对碑刻文字的辨识产生一定的影响。针对这种情况,提出了一种新方法,首先利用细胞神经网络（CNN）技术,去除单个碑刻文字的噪声,然后用网格特征提取方法对其进行识别。本文在MATLAB平台上进行了实例模拟,取得了较好的效果。     

Perceptual image preview

Image preview is a convenient way to browse large or multiple images on small displays. However, current signal-level image resampling algorithms may remove many features of interest in the preview image. In this paper, we propose perceptual image preview which retains more perceptual features such that users can inspect features of interest by viewing the preview image only and without zooming in. This technology has two components, structure enhancement and perceptual feature visualization. Structure enhancement enhances the image structure while suppressing subtle details using a gradient modulation method, thus making the succedent perceptual features more apparent. For perceptual feature visualization, features of interest detected in the picture is visualized on the structure enhanced preview image. We demonstrate with two examples of most commonly used image quality features, image blur and noise. The effectiveness of the proposed method is validated by experimental results.     

遗传算法与文本特征选择方法相结合的研究

对文本特征选择的传统方法进行了深入分析并对各自的优缺点进行了详细的对比;其次,通过利用遗传算法自身的寻优特点,把它与传统特征选择方法相结合,并得出了算法。最后,在对各自算法进行了分析,表明了在性能上有了明显的提高。     

一种多分类器集成的手写体汉字识别方法

多分类器集成是手写体汉字识别领域的新方向。本文提出的多分类器集成方法通过改进的欧氏距离分类器将待识别汉字分类到某个粗分结果集中,然后根据粗分结果集选择1-N(one-against-rest)的SVM分类器对待识别汉字进行细分,最后用贝叶斯集成两级分类器。实验对国标一级汉字中的1034个手写汉字进行识别,证明了方案的有效性。     

改进自组织映射神经网络在指纹识别中的应用

改进自组织映射神经网络方法是将常规自组织映射神经网络方法结合确定性水平,对网络的输入矢量进行预处理。通过实验比较了这种改进的自组织映射神经网络识别方法与常规的自组织映射神经网络识别方法的识别效果,在识别性能上有了很大的提高。     

一种基于颜色自动相关图与小波变换的图像检索算法研究

随着图像数据量的不断丰富和人们需求的不断提高,基于内容的图像检索技术成为一个重要的研究课题。本文研究了基于颜色相关图与小波变换的图像检索算法,利用颜色相关图与小波变换,把图像分块分别提取图像的颜色特征与纹理特征,实现了图像的检索。实验结果说明了算法的有效性。     

多特征融合的蛋白质相互作用位点预测

蛋白质相互作用位点预测为蛋白质功能和药物设计的理解提供重要线索。而蛋白质的各种特征为蛋白质相互作用位点预测提供了大量有用信息,特别是进化信息、残基序列邻近和空间邻近性。不同的蛋白质特征对蛋白质间的相互作用的贡献也不一样。通过提取蛋白质序列谱、保守性和残基熵,提出了特征融合技术对蛋白质相互作用位点进行研究,采用SVM构建三种预测器,分别对各种不同的特征加以验证,实验结果表明了基于特征融合方法的有效性和正确性。