图像微观结构的二值化表示与目标识别应用

该文提出一种新颖的基于二值图像微观结构模式(Binary Image Micorsructure Pattern,BIMP)表达和灰度图像微观结构二值模式(Gray Image Micorsruct Maximum Response Pattern,GIMMRP)编码方法。通过对图像3×3邻域结构进行二值编码,获得图像微观结构的描述,进而选取其中的重要执行模式子集和池化操作,实现整体图像的表示。为了检验算法的有效性,在ORL,YALE两个人脸公开数据集,MNIST,USPS两个手写数字公开数据集,以及非公开车标数据集上进行了测试,显示该方法具有很强的鉴别能力和鲁棒性,可以达到和超过很多最新算法的性能。

基于结构相似性准则的软形态滤波性能分析

基于图像形成模型和人眼视觉特性,提出两图灰度相似性和结构相似性的计算方法。根据图像形成模型和人眼视觉特性,分别计算滤波后图像与原始图像的灰度相似性和结构相似性,把它们的乘积作为评价标准。并利用图像质量评价方法测量在不同噪声水平、不同参数配置下,软形态滤波输出图像的图像质量,分析软形态滤波的去噪性能变化情况。结果表明,在笔者所设噪声条件下,在小模板时,软形态滤波可获得与经典形态滤波基本完全相同的去噪效果;在大模板时,通过调整参数,软形态滤波能表现良好的鲁棒性。

VEHICLE SEGMENTATION AND SHADOW HANDLER BASED ON EXTREMUM IMAGE

The shadows similar to the vehicle and the spots caused by vehicle lamps need to be accurately detected in the vehicle segmentation involved in the video-based traffic parameter measurement. Generally, the road surface is different from the vehicle surface in the gray-level architecture. An invariant gray-level architecture-the extremum image in the changing illumination environment is derived and a novel algorithm is presented for detecting shadows and spots. The gray-level structure that is not sensitive to the illumination is employed in the algorithm and the road surface mistaken as vehicles can be removed.

基于共生矩阵纹理特征提取的改进算法

深入研究灰度共生矩阵及其改进算法,针对其计算量大、耗时等问题,提出一种基于灰度共生混合结构和离散傅立叶变换的方法来实现纹理特征的提取。对傅立叶变换后的频谱图进行分块计算,以此降低计算时的灰度级,再采用正规化的方式减少特征的分布范围,并利用灰度共生混合结构算法计算一个5维的特征向量来描述图像的纹理。实验结果表明,改进后的算法降低了计算复杂度,极大地减少了图像纹理特征提取的时间。

Robust salt-dome detection using the ranking of texture-based attributes

The accurate interpretation and analysis of seismic data heavily depends on the robustness of the algorithms used. We focus on the robust detection of salt domes from seismic surveys. We discuss a novel feature-ranking classification model for saltdome detection for seismic images using an optimal set of texture attributes. The proposed algorithm overcomes the limitations of existing texture attribute-based techniques, which heavily depend on the relevance of the attributes to the geological nature of salt domes and the number of attributes used for accurate detection. The algorithm combines the attributes from the Gray-Level Co-occurrence Matrix （GLCM）, the Gabor filters, and the eigenstructure of the covariance matrix with feature ranking using the information content. The top-ranked attributes are combined to form the optimal feature set, which ensures that the algorithm works well even in the absence of strong reflectors along the salt-dome boundaries. Contrary to existing salt-dome detection techniques, the proposed algorithm is robust and eomputationally efficient, and works with small-sized feature sets. I used the Netherlands F3 block to evaluate the performance of the proposed algorithm. The experimental results suggest that the proposed workflow based on information theory can detect salt domes with accuracy superior to existing salt-dome detection techniques.

Iris Feature Extraction and Recognition Based on Fractal Dimension of Grayscale Extremums

This paper presented an individual recognition algorithm for human iris using fractal dimension of grayscale extremums for feature extraction.Firstly,iris region was localized from an eye image with modified circle detector stemmed from Daugman’s integro-differential operator.Then,segmentation was used to extract the iris and to exclude occlusion from eyelids and eyelashes.The extracted iris was normalized and mapped to polar coordinates for matching.In feature encoding,a new approach based on fractal dimension of grayscale extremums was designed to extract textural features of iris.Finally,a normalized correlation classifier was employed to determine the agreement of two iris feature templates,and the feature template was rotated left and right to avoid the interference from rotation of eyes and tilting of head.The experimental results show that fractal dimension of grayscale extremums can extract textural features from iris image effectively,and the proposed recognition algorithm is accurate and efficient.The proposed algorithm was tested on CASIA-IrisV3-Interval iris database and the performance was evaluated based on the analysis of both False Accept Rate(FAR)and False Reject Rate(FRR)curves.Experimental results show that the proposed iris recognition algorithm is effective and efficient.

Effect of Silica Fume on Early Performance of Precast Concrete with Early Strength Agents

The effect of silica fume on the early performance of precast concrete with an early strength agent was investigated.The ternary compounding technique of silica fume,fly ash and early strength agent were used to examine the compressive strength,heat of hydration,hydration products,and microstructures of the precast concrete.The experimental results showed that the optimum amount of silica fume in the precast concrete was 9%.Silica fume filled the fine pores between the cement particles.However,the cement hydration was mainly influenced by the waterto-cement ratio and cement particle size.As the hydration reaction continued,silica fume provided more nucleation sites,and the characteristic volcanic ash reaction increased both the hydration degree and hydration rate of the early strength agent doped cementitious materials.

The Economic Effect of Mineral Resources Exploitation in Bijie Prefecture in Guizhou

The exploitation of mineral resources plays an important role in promoting national economic development. Mining is an essential component of China's industrial economy. Using grey correlation method to analyze the correlative effect of mineral resources exploitation to relevant industries, using national income method to calculate the pulling effect of mineral resources exploitation to economic growth and using graphs as well as tables to analyze the income distribution effect, the article obtains active economic effect of mineral resources development in Bijie, Guizhou. Moreover, from the view of resources-cored effect, the article analyzes negative effects such as single industrial structure brought by mineral resource development. Through analysis, we find that mineral resources exploitation to some extent brings active effects including gross domestic product growth, local financial revenue growth and relevant industries development; however, its negative effects should not be ignored. The negative effect can be lightened by diversifying industrial structure and prolonging industrial chain.

A New Fast Edge Detection Algorithm Based on NAM-structured Plane Decomposition

The nonsymmetry and antipacking pattern representation model （NAM）, inspired by the concept of the packing problem, uses a set of subpatterns to represent an original pattern. The NAM is a promising method for image representation because of its ability to focus on the interesting subsets of an image. In this paper, we develop a new method for gray-scale image representation based on NAM, called NAM-structured plane decomposition （NAMPD）, in which each subpattern is associated with a rectangular region in the image. The luminance function of pixels in this region is approximated by an oblique plane model. Then, we propose a new and fast edge detection algorithm based on NAMPD. The theoretical analyses and experimental results presented in this paper show that the edge detection algorithm using NAMPD performs faster than the classical ones because it permits the execution of operations on subpatterns instead of pixels.