Online composite shape recognition based on relevance feedback

This paper describes a novel method of online composite shape recognition interms of the relevance feedback technology to capture a user's intentions incrementally, and adynamic user modeling method to adapt to various users' styles. First, the relevance feedback isadapted to refine the recognition results and reduce the ambiguity incrementally based on theestablishment of a feature-based vector model of a user's sketches. Secondly, a dynamic usermodeling is introduced to model the user's sketching habits based on recording and analyzinghistorical information incrementally. A model-based matching strategy is also employed in the methodto recognize sketches dynamically. Experiments prove that the proposed method is both effective andefficient.

A Neural Network Recognition Method of Shape Pattern

A new pattern recognition method of shape was presented based on artificial neural network theory.The method avoids the defects of shape pattern recognition with polynomials and it has strong disturbance resistance.It has been proved to be superior in recognizing different shape patterns by identifying many sorts of working sample books which the results are known.

Vision Based Hand Gesture Recognition Using 3D Shape Context

Hand gesture recognition is a popular topic in computer vision and makes human-computer interaction more flexible and convenient.The representation of hand gestures is critical for recognition.In this paper,we propose a new method to measure the similarity between hand gestures and exploit it for hand gesture recognition.The depth maps of hand gestures captured via the Kinect sensors are used in our method,where the 3D hand shapes can be segmented from the cluttered backgrounds.To extract the pattern of salient 3D shape features,we propose a new descriptor-3D Shape Context,for 3D hand gesture representation.The 3D Shape Context information of each 3D point is obtained in multiple scales because both local shape context and global shape distribution are necessary for recognition.The description of all the 3D points constructs the hand gesture representation,and hand gesture recognition is explored via dynamic time warping algorithm.Extensive experiments are conducted on multiple benchmark datasets.The experimental results verify that the proposed method is robust to noise,articulated variations,and rigid transformations.Our method outperforms state-of-the-art methods in the comparisons of accuracy and efficiency.

Circular object recognition based on shape parameters

To recognize circular objects rapidly in satellite remote sensing imagery, an approach using their geometry properties is presented. The original image is segmented to be a binary one by one dimension maximum entropy threshold algorithm and the binary image is labeled with an algorithm based on recursion technique. Then, shape parameters of all labeled regions are calculated and those regions with shape parameters satisfying certain conditions are recognized as circular objects. The algorithm is described in detail, and comparison experiments with the randomized Hough transformation （RHT） are also provided. The experimental results on synthetic images and real images show that the proposed method has the merits of fast recognition rate, high recognition efficiency and the ability of anti-noise and anti-jamming. In addition, the method performs well when some circular objects are little deformed and partly misshapen.

Extraction of affine invariant features for shape recognition based on ant colony optimization

A new approach to extraction of affine invariant features of contour image and matching strategy is proposed for shape recognition.Firstly,the centroid distance and azimuth angle of each boundary point are computed.Then,with a prior-defined angle interval,all the points in the neighbor region of the sample point are considered to calculate the average distance for eliminating noise.After that,the centroid distance ratios（CDRs） of any two opposite contour points to the barycenter are achieved as the representation of the shape,which will be invariant to affine transformation.Since the angles of contour points will change non-linearly among affine related images,the CDRs should be resampled and combined sequentially to build one-by-one matching pairs of the corresponding points.The core issue is how to determine the angle positions for sampling,which can be regarded as an optimization problem of path planning.An ant colony optimization（ACO）-based path planning model with some constraints is presented to address this problem.Finally,the Euclidean distance is adopted to evaluate the similarity of shape features in different images.The experimental results demonstrate the efficiency of the proposed method in shape recognition with translation,scaling,rotation and distortion.

Complex Object Shapes Recognition. Automatic Aid Photointerpretation in a Satellite Image

The interpretation of geological structures on earth observation images involves like many other domains to both visual observation as well as specialized knowledge. To help this process and make it more objective, we propose a method to extract the components of complex shapes with a geological significance. Thus, remote sensing allows the production of digital recordings reflecting the objects’ brightness measures on the soil. These recordings are often presented as images and ready to be computer automatically processed. The numerical techniques used exploit the morphology ma- thematical transformations properties. Presentation shows the operations’ sequences with tailored properties. The example shown is a portion of an anticline fraction in which the organization shows clearly oriented entities. The results are obtained by a procedure with an interest in the geological reasoning: it is the extraction of entities involved in the observed structure and the exploration of the main direction of a set of objects striking the structure. Extraction of elementary entities is made by their physical and physiognomic characteristics recognition such as reflectance, the shadow effect, size, shape or orientation. The resulting image must then be stripped frequently of many artifacts. Another sequence has been developed to minimize the noise due to the direct identification of physical measures contained in the image. Data from different spectral bands are first filtered by an operator of grayscale morphology to remove high frequency spatial components. The image then obtained in the treatment that follows is therefore more compact and closer to the needs of the geologist. The search for significant overall direction comes from interception measures sampling a rotation from 0 to 180 degrees. The results obtained show a clear geological significance of the organization of the extracted objects.

A method for coastal oil tank detection in polarimetric SAR images based on recognition of T-shaped harbor

To automatically detect oil tanks in polarimetric synthetic aperture radar（SAR） images, a coastal oil tank detection method is proposed based on recognition of T-shaped harbor. First of all, the T-shaped harbor is detected to locate the region of interest（ROI） of oil tanks. Then all suspicious targets in the ROI are extracted by the segmentation of strong scattering targets and the classifier of H/α. The template targets are selected from the suspicious targets by the combination of a proposed circular degree parameter and the similarity parameter（SP） of the polarimetric coherency matrix. Finally, oil tanks are detected according to the statistics of the similarity parameter between each suspicious target and template targets in ROI. Polarimetric SAR data acquired by RADARSAT-2 over Berkeley and Singapore areas are used for testing. Experiment results show that most of the targets are correctly detected and the overall detection rate is close to 80%.The false rate is effectively reduced by the proposed algorithm compared with the method without T-shaped harbor recognition.

Flame image recognition of alumina rotary kiln by artificial neural network and support vector machine methods

Based on the Fourier transform, a new shape descriptor was proposed to represent the flame image. By employing the shape descriptor as the input, the flame image recognition was studied by the methods of the artificial neural network(ANN) and the support vector machine(SVM) respectively. And the recognition experiments were carried out by using flame image data sampled from an alumina rotary kiln to evaluate their effectiveness. The results show that the two recognition methods can achieve good results, which verify the effectiveness of the shape descriptor. The highest recognition rate is 88.83% for SVM and 87.38% for ANN, which means that the performance of the SVM is better than that of the ANN.

Fuzzy Jamming Pattern Recognition Based on Statistic Parameters of Signal’s PSD

In order to recognize the jamming pattern in anti-jamming, a novel fuzzy jamming recognition method based on statistic parameters of received signal’s power spectral density (PSD) is proposed. It exploits PSD’s shape factor and skewness of received signal as classified characters of jamming pattern. After the mean center and variance of each jamming pattern are calculated by using some jamming samples, an exponential fuzzy membership function is used to calculate the membership value of the recognized sample. Finally, the jamming pattern of received signal is recognized by the maximum membership principle. The simulation results show that the proposed algorithm can recognize common eight jamming patterns accurately.

STUDY OF RECOGNITION TECHNIQUE OF RADAR TARGET'S ONE-DIMENSIONAL IMAGES BASED ON RADIAL BASIS FUNCTION NETWORK

This paper studies the problem applying Radial Basis Function Network(RBFN) which is trained by the Recursive Least Square Algorithm(RLSA) to the recognition of one dimensional images of radar targets. The equivalence between the RBFN and the estimate of Parzen window probabilistic density is proved. It is pointed out that the I/O functions in RBFN hidden units can be generalized to general Parzen window probabilistic kernel function or potential function, too. This paper discusses the effects of the shape parameter a in the RBFN and the forgotten factor A in RLSA on the results of the recognition of three kinds of kernel function such as Gaussian, triangle, double-exponential, at the same time, also discusses the relationship between A and the training time in the RBFN.

Recognition of Curvature Radius in Robot Moving in Bent Pipe

This paper translates the recognifion of curvatare radius in robot moving in bent pipe into an issue of shape-from-shading, and introduces genetic algorithms into the optimizaton process to improve the efficiency of optimization.Experiments prove that thes method can satisfy the autonomous control requrement for robot moving in bent pipe in both speed and accuray.

国家赋权、社会形塑、自我体认:乡村医生身份建构三维考察

乡村医生是在村级卫生室从事医疗卫生服务工作的基层卫生人员,是一个特殊的社会群体。乡村医生具有医生、农民、半农半医等多元身份,其中医生身份面临着国家定位模糊、社会公众质疑以及个体自我怀疑的困境。破解乡村医生身份困境,建构乡村医生的医生身份,需要国家、社会和乡村医生自身共同发挥作用。国家需要通过制订确立乡村医生身份的法律制度规范、逐步将乡村医生纳入事业编制等手段,以国家赋权形式对其身份予以确认;新闻媒体、文艺工作者、社科理论研究者、人大代表和政协委员等社会组织和个人应该发挥职业优势和专业特长,合力形塑乡村医生的医生身份;乡村医生要发挥自我体认这一内生动力,积极主动地开展医生身份重塑。

基于多模态关系建模的三维形状识别方法

为了充分利用点云和多视图两种模态数据之间的局部空间关系以进一步提高三维形状识别精度,提出一个基于多模态关系的三维形状识别网络,首先设计多模态关系模块(multimodal relation module,MRM),该模块可以提取任意一个点云的局部特征和一个多视图的局部特征之间的关系信息,以得到对应的关系特征.然后,采用由最大池化和广义平均池化组成的级联池化对关系特征张量进行处理,得到全局关系特征.多模态关系模块分为两种类型,分别输出点-视图关系特征和视图-点关系特征.提出的门控模块采用自注意力机制来发现特征内部的关联信息,从而将聚合得到的全局特征进行加权来实现对冗余信息的抑制.详尽的实验表明多模态关系模块可以使网络获得更优的表征能力;门控模块可以让最终的全局特征更具判别力,提升检索任务的性能.所提网络在三维形状识别标准数据集ModelNet40和ModelNet10上分别取得了93.8%和95.0%的分类准确率以及90.5%和93.4%的平均检索精度,在同类工作中处于先进水平.

基于点云的马鞍形焊缝提取和轨迹生成方法

马鞍形焊缝自动焊接存在焊缝难以识别定位以及焊枪姿态难以规划的问题,为了实现马鞍形焊缝的自动焊接,选取实际装配的管类交叉结构件作为研究对象,提出一种基于点云的马鞍形焊缝识别与规划方法。根据马鞍形焊缝的空间语义特征,提出基于法向量和空间距离的紧耦合约束的方法提取焊缝关键点,之后用三次B样条曲线对关键点进行近似拟合,得到最终的空间焊接曲线。实验表明,提取出的焊缝轨迹与真实轨迹相比,最大误差为0.68mm,最大均方根误差为0.29。该方法具有较高的精度和鲁棒性,可满足实际焊接的需求。此方法的实用性不仅局限于马鞍形焊缝,也能处理其他具有曲线变化的焊缝。

Noise‐tolerant matched filter scheme supplemented with neural dynamics algorithm for sea island extraction

Achieving high‐precision extraction of sea islands from high‐resolution satellite remote sensing images is crucial for effective resource development and sustainable management.Unfortunately,achieving such accuracy for sea island extraction presents significant challenges due to the presence of extensive background interference.A more widely applicable noise‐tolerant matched filter(NTMF)scheme is proposed for sea island extraction based on the MF scheme.The NTMF scheme effectively suppresses the background interference,leading to more accurate and robust sea island extraction.To further enhance the accuracy and robustness of the NTMF scheme,a neural dynamics algorithm is supplemented that adds an error integration feedback term to counter noise interference during internal computer operations in practical applications.Several comparative experiments were conducted on various remote sensing images of sea islands under different noisy working conditions to demonstrate the superiority of the proposed neural dynamics algorithm‐assisted NTMF scheme.These experiments confirm the ad-vantages of using the NTMF scheme for sea island extraction with the assistance of neural dynamics algorithm.

基于改进YOLOv8的中药材图像识别

针对传统中药材检测任务中识别效率低、受主观因素影响较大的问题,文章选取77种中药材作为研究对象。采用自行拍摄图像和在互联网获取图像的方式,并结合旋转平移、高斯噪声等数据增强技术,最终构建了一个包含4万多张图像的数据集。在模型改进方面,对第八代只看一次目标检测算法(You Only Look Once version 8,YOLOv8)的Backbone部分进行了针对性的优化,引入了DSConv和Biformer注意力机制。DSConv能够自适应地关注细长和曲折的局部特征,而Biformer则通过双层路由机制,实现了内容感知的稀疏模式,提高了模型对图像细节和关键目标的识别能力。实验结果表明,改进后的YOLOv8模型的精确率、召回率和平均精度分别达到了96.4%、98.0%和97.7%,相较于原模型的精确率和平均精度分别增长了1.7百分点和1.0百分点。在中药材检测任务上取得了显著的性能提升效果。

一种自复位摇摆墙的改进Bouc-Wen滞回模型

Bouc-Wen模型是一种可表征结构及构件刚度、强度退化等的多功能非线性光滑滞回模型,可广泛应用于各类结构滞回行为的描述。自复位摇摆墙(Self-centering rocking wall, SCRW)结构由于其优越的抗震和自复位性能,滞回曲线呈“旗帜型”。为了更好地表征这种“旗帜型”滞回特性,在Bouc-Wen模型的基础上,建立一种具有较高精度和较好实用性的改进Bouc-Wen滞回模型。改进的Bouc-Wen模型参数是决定结构滞回性能力学特征的关键。由于该模型参数众多且选择范围不明确,为适应该类模型参数高效识别的需求,通过在MATLAB/Simulink环境中搭建程序框图,实现了对该理论模型控制参数的定性及定量分析,并运用遗传算法对10个SCRW试验结果进行参数识别,对识别结果进行统计分析,建立各参数与滞回曲线关键点的关系式,基于统计结果给出了各参数的建议取值范围;最后,通过SCRW拟静力试验对改进的滞回模型和参数取值范围进行了验证。结果表明:这种单自由度改进的Bouc-Wen滞回模型能较好地反映SCRW在往复荷载作用下无残余变形和强度、刚度退化特点的“旗帜型”滞回特性。所提出的参数取值范围显著提升了改进Bouc-Wen模型的识别精度与效率,识别过程对类似模型的参数识别具有参考价值。

基于LVQ神经网络的青年女性胸部识别模型构建

为提高青年女性胸部形态分类的准确率,填补文胸号型分类体系存在的缺陷,结合青年女性胸部体型特征构建了一种基于LVQ神经网络的青年女性胸部识别模型。研究运用非接触式激光三维技术共采集216个青年女大学生胸部数据,将因子分析提取的9个胸部特征指标采用K-means聚类法,通过手肘图、轮廓系数图确定K值,最终将胸型分为4类。在此基础上构建LVQ神经网络胸型识别模型,以9项胸部特征指标为输入,4种胸型为输出,进行LVQ神经网络的训练。研究结果表明:模型经训练及测试后,识别精度达到95%,Kappa系数为0.932。与BP、PNN神经网络模型相比,在运算效率、模型精度和稳定性方面,LVQ神经网络模型的表现要明显优于其他两种神经网络。