基于特征面分割的自动特征识别

相交特征的识别是自动特征识别的难点,提出一种新的基于图的特征识别算法,首先构造加工面邻接图(MFAG),然后通过特征匹配快速识别出孤立特征,通过特征面的延拓、求交与分割,主动找出特征痕迹,分解出基本特征子图,从而识别出相交特征.该算法使孤立特征和相交特征的识别模式统一,同时有利于与交互特征定义集成.     

A system for recognition and modification of machining features on prismatic components

A recognition process of the features in a part model resorts to the knowledge of an application engineer. The knowledge is encoded as rules of the recognition procedure at the beginning that are applied to the part model during the recognition process. Such a human interaction is difficult to control in extracting the intended features because the intended features by the application engineer may change from one engineer to the other and the external situations. Instead, we treat the result of the recognition process as a rough extraction and allow the user interactively modify the result. In this paper, we present a feature recognition system where the user can inspect the result of the recognition and delete recognized features interactively.     

基于双链遗传算法的复杂特征识别方法研究

子图匹配问题是典型的非多项式算法问题,但又是基于图的特征识别方法的基础,导致目前提出的基于图的特征识别方法很难实现交叉特征识别、包含凸边的特征识别等问题。针对特征识别的需求,提出了一种双链遗传算法。该算法采用双链结构描述特征识别问题的染色体,一条链描述面信息,另一条描述特征对于面的分割。同时根据双链的特点,定义了双链染色体的交叉、变异、选择、半表留复制等运算。实验证明双链遗传算法具有解决特征识别的可行性,且结果较其他特征识别方法识别特征范围更广和可以合并被分割的特征、识别包含凸边的特征等优点。     

A feature recognition system with interactive feature inspection and deletion capabilities

A recognition process of the features in a part model uses the knowledge of an application engineer. The knowledge is encoded as rules of the recognition procedure that are applied to the part model during the recognition process. Such a human interaction is difficult to control in extracting the moulding features because the features moulding of the application engineer may change from one engineer to the other and external conditions may change. Instead, we treat the result of the recognition process as a first approximation of the user's intention and let the user interactively modify the result. In this paper, we present a feature recognition system where the user can inspect the result of the recognition and delete the recognised features interactively.     

基于语义的特征分离与结合

针对21／2维特征模型,应用基于语义的特征识别方法加工特征的识别。结合实例介绍了21／2维特征的生成语义和加工语义,在特征转换过程中不同语义邻接特征的分离。以及相同语义特征转换而成的加工特征之间的结合。最后介绍了基于特征语义的特征识别的流程。     

Multi – oil droplet recognition of oil-water two-phase flow based on integrated features

Multi-oil droplet target recognition is one of the applications of machine vision in the measurement of oil-water two-phase flow parameters, which could combine other algorithms to obtain the oil droplet velocity and the water holdup of oil water two-phase flow. Appropriate target representation features can improve the recognition effect of multiple oil droplets. However, due to shooting environment differences and quality differences of oil-water two-phase flow images, existing target representation features do not perform well in low-quality oil-water two-phase flow images. To improve the precision of multi-oil droplet target recognition in oil-water two-phase flow and reduce the miss rate, this paper constructs an integrated feature on the basis of aggregate channel features (ACF). The integrated feature named aggregate channel features with histogram of local gravitational feature（ACFHG） contains the color feature channels reflecting the overall color features of the oil droplet sample, the gradient amplitude channel reflecting the overall gradient of the oil droplet sample image, the gradient direction histogram feature channels reflecting the local gradient of the oil droplet sample image, and the local gravitational feature channels that ensure oil droplet target recognition in low quality photos and photos taken in complex shooting environments. Moreover, the rotation invariance is obtained by taking the oriented gradient histogram of the local gravitational feature to further improve the multi-oil droplet target recognition effect. Experiment results show that the average precision of multi-oil droplet target recognition using the integrated features is 83.38%, which is 9.93% higher than that with using ACF, and the miss rate is 9.13%, which is 57.18% lower than that with using ACF. Compared with other existing target detection methods, the method proposed in this paper still has an advantage in the rate of missed detection.     

Real-time cutting tool state recognition approach based on machining features in NC machining process of complex structural parts

Cutting tool state recognition plays an important role in ensuring the quality and efficiency of NC machining of complex structural parts, and it is quite especial and challengeable for complex structural parts with single-piece or small-batch production. In order to address this issue, this paper presents a real-time recognition approach of cutting tool state based on machining features. The sensitive parameters of monitored cutting force signals for different machining features are automatically extracted, and are associated with machining features in real time. A K-Means clustering algorithm is used to automatically classify the cutting tool states based on machining features, where the sensitive parameters of the monitoring signals together with the geometric and process information of machining features are used to construct the input vector of the K-Means clustering model. The experiment results show that the accuracy of the approach is above 95% and the approach can solve the real-time recognition of cutting tool states for complex structural parts with single-piece and small-batch production.     

基于纹理特征的道路行人识别研究

道路行人识别已经成为智能车辆与车辆辅助驾驶系统的关键技术。研究一种基于纹理特征的行人特征提取和识别方法。纹理特征作为图像的重要特征在图像分析与识别有着广泛的应用。做出道路行人与非行人样本的纹理频谱,得出它们存在差异性的结论。首先用统计方法来计算样本图像的纹理特征,然后将支持向量机方法应用于道路行人的识别试验。试验结果表明,选择纹理特征作为道路行人特征具有很好的道路行人识别效果。     

基于模糊理论的仪表数字识别研究

提出了一种基于模糊理论的仪表数字快速识别方法。确定的典型特征具有较高的区分度，且计算简单，无需进行数字细线化和大小归一化处理。构造了一种基于模糊识别最大隶属原则的数字识别器，并且采用BP神经网络解决了确定最优权矩阵的难点问题。试验表明：对于常规测量环境中的数字仪表，该方法的识别率高达99％，对7位数字的识别时间不超过30ms，达到了仪表数字识别的速度和准确率要求。     

Automatic recognition of intersecting features for side core design in two-piece permanent molds

The automatic recognition of molding features (protrusions, depressions, and their intersections), core, and cavity surfaces plays an important role in shortening the lead time in mold design and manufacturing as well as aiding the side core design. Consequently, in this paper, an automatic mold feature recognition system to recognize protrusion, depression as well as intersecting depression features is proposed and implemented. The recognition of various types of intersecting features is a significant contribution to the literature. The output generated by the accessibility analysis (without discretizing the part) is used as the input to the feature recognition module. The newly developed system is assessed by comparing its results with those of earlier systems. A comprehensive case study is presented that can demonstrate the additional capabilities of the proposed system to those of the present in the published literature.     

基于多特征融合和BP-AdaBoost算法的列车关键零件故障自动识别

针对列车集尘器和安全链锁紧螺栓的故障检测,提出了一种基于多特征融合和BP-AdaBoost的故障自动识别算法。首先提取故障区域与非故障区域的局部二进制模式（LBP）、方向梯度直方图（HOG）和Haar-like三类特征;其次利用主成分分析（PCA）定义不同特征对故障识别准确率的贡献值,并据此对这三种特征进行降维和融合;再次利用融合特征来训练BP-AdaBoost分类器;最后用训练好的分类器结合不同的识别算法,对集尘器和安全链锁紧螺栓的故障进行定位和识别。实验结果表明,该算法能较好地识别两种不同故障,故障识别率高,误检率和漏检率低,对于光照不均和遮挡情况有一定的鲁棒性。     

基于铁谱图像异类特征融合的磨损类型识别方法

针对铁谱磨粒图像识别中存在特征单一、异类特征的综合利用率低等问题,提出一种磨粒图像多特征的异类信息融合识别方法。首先,对在线铁谱图像预处理基础上提取磨粒纹理(ASM、熵、相关、对比度)、颜色(均值、方差、斜度)、几何(7个不变矩)3种统计特征;其次,对提取特征数据进行[0,1]归一化处理,采用超球心间距法确定核参数,运用超球多类SVM实现基于单种特征的多类磨损识别;最后,在单种特征识别基础上通过后验概率构造3种特征所需的软判决基本概率赋值(BPA)函数,运用超球多类SVM与D-S证据理论结合法实现异类特征融合的铁谱图像识别。特征融合方法识别最高识别率达到了96.1%,与单一特征识别结果相比,识别准确度更高,且实现了不同特征的互补。     

全局注意力关系网络的小样本船舶识别

实际场景中采集的船舶目标类别样本数量不均衡,模型训练易导致过拟合。 传统迁移学习的数据集划分存在类别交 叉,造成未标注新类别识别精度低。 为解决上述问题,提出了一种跨目标通用全局注意力机制与关系度量网络融合的小样本船 舶识别算法。 该方法通过在关系网络中引入全局注意力机制,利用关系网络提取到的原始特征,经过全局注意力机制平滑不均 衡类别间的目标特征,并与关系网络提取的原始特征融合后进行特征距离度量。 该方法增强了全局特征之间的一致性,有利于 学习不变的目标特征,提升少样本少标签的船舶目标识别性能,解决了训练过程中类别不均衡导致的过拟合问题。 利用自己采 集制作的船舶数据集对本文方法进行测试实验,识别精度提高了 5. 6% (5-shot)、3. 2% (1-shot),减小了不均衡类别对模型目标 识别造成的影响,增强了模型的鲁棒性。     

Decomposition of interacting machining features based on the reasoning on the design features

Currently, design and machining features diverge in meaning, even when they are interpreting the same object. This divergence of feature interpretation provides a venue for research work to reduce the complexity that arises in recognizing interacting machining features. Therefore, this paper demonstrates the recognition of design features with the aim to eventually decompose the interacting machining features. Loop driving recognition links the CAD data directly to the features to be recognized. The first step is to recognize the design features from B-Reps part. Then geometrical reasoning on these design features is employed to convert the design features to its respective machining features. The process of conversion is in fact the process of decomposing the interacting machining features without having to visit the B-Reps data again. The system takes into account the nesting of the design features that causes more interacting machining features to be decomposed. Finally, output data of both design and machining features are then displayed.     

采用鱼群算法进化极限学习机的假肢步态识别

为提高下肢假肢步态识别的准确性,提出一种基于鱼群(fish swarm,简称FA)算法优化极限学习机(extreme learning machine,简称ELM)的模式识别方法。首先,提取张量投影特征,分析了特征值选取的合理性;其次,采用主成分分析法降维;最后,利用鱼群算法进化极限学习机分类识别平地行走、上楼、下楼、上坡及下坡5种步态,识别准确率达到97.45%。通过实验比较了该算法与极限学习机等分类器在假肢步态分类上的识别准确率与识别时间,结果表明,FA-ELM方法识别准确率优于其他方法。     

基于属性邻接图的制造特征识别方法

制造特征的识别是实现CAD／CAPP／CAM集成的关键技术,既要将特征交互的区域合理分解,又要避免在识别过程中把单个特征不恰当地分解为两个或多个特征,本文使用辅助面、延伸面相结合的方法,对零件的属性邻接图表示进行扩展,同时引入了联合加工特征的概念及识别方法,使扩展后得到的图被分解后能够真实地表示零件的制造特征,从而使加工的推理胡切、更快捷。     

基于粒子群优化算法的水源微生物自动识别

水源微生物检测在水源生物安全监测等方面具有非常重要的意义，而传统的显微镜观测等方法存在效率低、需要专业人员操作等不足，为此提出了一种水源微生物自动识别方法。采集水样，并制作水源微生物图像集，编写全自动与半自动两种图像分割算法用于提取目标微生物区域，并提取6种图像特征。基于以上特征数据，研究水源微生物识别模型的优化问题：首先，优化部分特征参数；接着，融合所有特征，建立粒子群优化算法的支持向量机（support vector machine optimized by particle swarm optimization, PSO-SVM）微生物识别模型，并与其他识别算法进行比较。结果表明，相比于其他3种算法，PSO-SVM能更有效地识别各种微生物，其平均识别率达到97.08%。     

钣金零件特征识别方法的研究

从面向特征识别的角度，对钣金零件的特征进行了分类，并采用图结构描述分类特征。在此基础上，将特征识别的过程分解为模型有效性检查和基于图匹配的特征提取，所识别出的特征，可根据后续应用的需要重构出新的特征模型。     

Classification of stomach infections: A paradigm of convolutional neural network along with classical features fusion and selection

Automated detection and classification of gastric infections (i.e., ulcer, polyp, esophagitis, and bleeding) through wireless capsule endoscopy (WCE) is still a key challenge. Doctors can identify these endoscopic diseases by using the computer‐aided diagnostic (CAD) systems. In this article, a new fully automated system is proposed for the recognition of gastric infections through multi‐type features extraction, fusion, and robust features selection. Five key steps are performed—database creation, handcrafted and convolutional neural network (CNN) deep features extraction, a fusion of extracted features, selection of best features using a genetic algorithm (GA), and recognition. In the features extraction step, discrete cosine transform, discrete wavelet transform strong color feature, and VGG16‐based CNN features are extracted. Later, these features are fused by simple array concatenation and GA is performed through which best features are selected based on K‐Nearest Neighbor fitness function. In the last, best selected features are provided to Ensemble classifier for recognition of gastric diseases. A database is prepared using four datasets—Kvasir, CVC‐ClinicDB, Private, and ETIS‐LaribPolypDB with four types of gastric infections such as ulcer, polyp, esophagitis, and bleeding. Using this database, proposed technique performs better as compared to existing methods and achieves an accuracy of 96.5%.     

基于SURF算子的快速手背静脉识别

提出基于加速鲁棒性特征(speeded-up robustfeatures,SURF)的手背静脉识别算法.首先对手背静脉图像进行预处理,提取手背静脉感兴趣区域(ROI),然后提取手背静脉的局部SURF特征,基于欧式距离实现测试样本和注册样本特征点的匹配,并剔除错误匹配对,最后计算匹配率作为待识别样本和注册样本之间的相似度测试实现身份识别.利用TJU手背静脉图像数据库对算法性能进行测试,在认证模式下等错率为0.07%,平均识别时间0.153 s.实验结果证明该算法可以快速有效地实现手背静脉识别.