基于视觉显著性改进的水果图像模糊聚类分割算法

准确分割水果图像是采摘机器人实现视觉定位的关键技术。该文针对传统模糊聚类对初始聚类中心敏感、计算量大和易出现图像过分割等问题,结合机器人的视觉特性,提出了一种基于多尺度视觉显著性改进的水果图像模糊聚类分割算法。首先,选择适当的颜色模型把彩色水果图像转换为灰度图像;然后对灰度图像做不同尺度的高斯滤波处理,基于视觉显著性的特点,融合了多个不同尺度的高斯滤波图像,形成图像聚类空间;最后,用直方图和模拟退火粒子群算法对图像的传统模糊聚类分割算法进行了改进,用改进的算法分别对采集到的100张成熟荔枝和柑橘图像,各随机选取50张,进行图像分割试验。试验结果表明:该方法对成熟荔枝和柑橘的图像平均果实分割率分别为95.56%和93.68%,平均运行时间分别为0.724和0.790s,解决了水果图像过分割等问题,满足实际作业中采摘机器人对果实图像分割率和实时性的要求,为图像分割及其实时获取提供了一种新的基础算法,为视觉精确定位提供了有效的试验数据。     

色彩意象尺度在数控机床ICAID系统中的研究及应用

研究以数控机床ICAID系统中色彩设计过程为对象，进行了色彩意象尺度法实验和对设计者设计认知过程实验．通过心理量表测量、因子分析和口语分析，建立了数控机床产品的二维色彩意象认知空间，提出了色彩辅助设计过程模型框架．开发了配色器，并实现数控机床ICAID系统的产品色彩设计定义、检索、使用、修改的系统化应用．系统在互联网上得到了成功验证．     

基于TM遥感影像的鄱阳湖湿地分类研究

对覆盖鄱阳湖湿地的LandsatTM遥感影像进行了计算机自动分类技术方法的实验研究,采用了先对遥感影像数据进行非监督分类,在非监督分类的基础上进行人工解译,确定其类别属性,然后将人工解译后的非监督分类的分类属性表经过光谱聚类处理转化成适用于监督分类的分类模板文件,再执行监督分类的方法,有效地提高了湿地遥感影像分类的精度。     

概率神经网络的水稻种植面积遥感信息提取研究

为了提高水稻种植面积遥感信息提取精度,将根据水稻生长期所选择的多时相遥感影像经过大气校正和几何校正后,实施单波段统计、主成份变换和比值变换,选出最佳组合波段,通过分析概率神经网络(probabilistic neural network,PNN)的学习算法和基本结构,对最佳组合波段影像实现PNN模型分类,并将其分类结果与反向传播(back propagation,BP)神经网络模型和最小距离法的分类结果进行比较.结果表明:PNN模型比最小距离法的分类精度高出近6个百分点;PNN模型比BP模型的分类精度高出近13个百分点;对于水稻种植面积提取精度,PNN模型比最小距离法的结果高出15个百分点.从本次试验可知,PNN模型是一种有效的遥感影像分类方法,在作物种植面积提取方面将具有独到的功效.     

应用计算机图像处理技术识别玉米苗期田间杂草的研究

利用计算机图像处理技术分析了玉米苗期田间杂草的特征量，识别出田间杂草并确定了杂草的位置和生长状况。研究中采用双峰法滤除了土壤背景，根据投影面积、叶长、叶宽识别出了杂草，并且根据杂草投影面积确定出了杂草密度。实验结果表明，此方法可有效地识别出玉米苗期田间细长的单子叶杂草。     

Practical Method of High-Speed Access for Medical Digital Image Sequences

The high-speed access for medical digital image sequences was restricted to special device and complicated system in the past. The authors present a new method of high-speed access for medical digital image sequences which can be performed on general computer by means of the combination of Serial ATA(SATA) and Redundant Array of Independent Disk(RAID).Then they introduce the scheme of system configuration and software program. Lastly the testing result is given and the speediness,cheapness and conveniency of this method are elucidated.     

Visualization of the FEM Analysis Data of 3D on the Cut Plane

The colored patterns on arbitrary cut plane is an important method in 3D data-field visualization of finite element.By using the technology of the Object-Oriented Programming and the method of scan-line,the colored patterns on arbitrary cut plane are given.The example by the OPENGL of Visual C++ R6 can support the theory satisfactorily.     

Design of Vision System Based on Service Robot

A vision system based on the service robot is involved. In the system, picture signal is acquired by the picture sensor OV7635. Frame memory AL422B is used as data buffer memory, while CPLD controlled the time order DSP performed. In the software system of image processing, to accomplish color image segmentation and recognition, the threshold vector judgment and improved seed-fill algorithm is introduced, and the image geometric moment is calculated during the segmenting. In order to achieve a vision servo system which composed of image-based feedback and adaptive compensation, the deduced matrix-based Jacobian from the image moment is taken as image feature. Adopted the TFT LCD is adopted to straightly disolav the result of vision recognition and vision tracing.     

A New Solution to Reduce Blocking Artifacts Introduced by Standard Fractal Methods

Fractal image coding techniques usually partition the input image into small range blocks. This artificially introduces boundaries into the image resulting in the unpleasant blocking artifacts in the decoded images especially at high compression rate. Because the effect is especially responsible for the restrictions of the block-based coders, the solutions must be sought to reduce this blockiness. Recently two possible schemes have been proposed by other researchers: One may try to use overlapping blocks in the fractal transform, and the other to employ the combined fractal wavelet approach. An alternative solution is proposed, which employs the bilinear interpolation techniques and the resolution independence of fractal coding, in the sense that an image can be decoded at higher or lower resolutions than the original. Experiments show that the proposed scheme can eliminate the blocking artifacts.     

Representation of Uncertain Area in Image Based on Cloud-model

Aiming at the problem of representation of regions in the process of image processing, the paper presents a method applied to representation of spatial uncertain area in image based on Cloud-model. In two-dimension universe of discourse of image, the linguistic term of the polygons, which have uncertain edge, can be accomplished by relaxation iteration. The linguistic term of the polygons can be considered Cloud-core of Cloud-model. Based on the characteristics of pixels of transition region of fuzzy edge, Object-clouds of polygons can be constructed by Backward-cloud-generator. So Object-cloud can be representation model of spatial uncertain area and spatial uncertain area in image can be represented by digital characteristics of Object-cloud. Experiments testify the method. It enriches the cloud theory, and proposes a new idea for image comprehending and analyzing, especially remote sensing image.