基于图像处理的服装商标剪切缝检测算法

目前国内对于服装商标的剪切主要采用手工方式进行，不仅生产效率低下，且成本较高。提出了一种利用垂直边缘检测确定剪切缝具体位置的算法，并基于特征提出距离滤波方法以消除剪切缝识别过程中的噪声干扰。实验结果表明该算法能对服装商标剪切缝进行精确识别定位，可应用于服装商标自动剪切系统。     

浅谈企业开展质量体系认证的几个问题

ISO9000是建立质量管理和质量保证模式的系列标准，是产品生产企业开展质量管理、质量保证和质量体系认证的依据．本文从质量体系认证与全面质量管理；质量体系认证与创优评奖；质量体系认证与产品质量认证．国内认证、国外认证与国际认证；、质量体系与经济效益等几个方面论述了企业开展质量体系认证需要明确和处理好的几个问题．     

铣削力建模与计算机仿真

本文综合分析了切削过程中刀具几何参数对端铣铣削力的影响，对铣削力模型进行了修正，建立了适合端铣铣削力计算机仿真的铣削力模型。并对仿真结果与实际测试曲线进行了比较。     

单圆弧齿廓面齿轮齿面的生成

旨在解决单圆弧齿廓面齿轮造型难的问题,提出一种高效精确的建模方法。以范成加工原理为理论依据,布尔运算为主要实现方法,精确建立刀具齿轮模型,再运用三维建模CATIA软件二次开发技术,编写VBA宏程序完成刀具齿轮包络运动过程中切割面齿轮毛坯,生成单圆弧齿廓面齿轮齿面。该方法类似插齿加工面齿轮,不同在于刀具只做公转和自转的包络成形运动,成形的齿面精度可控且可靠。在理论模型上再现了刀具迹线,为单圆弧齿廓面齿轮的加工和研究提供了模型参照。     

High Speed Face Milling of a Aluminium Silicon Alloy Casting

High speed machining of aluminium silicon alloy castings has gained significant interest from automotive industry involved in the development of the new generation of lightweight vehicles. This paper investigates the influence of workpiece microstructure, namely the secondary dendritic arm spacing (SDAS), tool material and geometry on tool wear mechanisms, cutting forces and surface integrity when face milling at cutting speeds of 5,000 m min⁻¹. It was found that the SDAS is the parameter with the main influence on tool wear rate; higher SDAS values require polycrystalline diamond (PCD) tooling due to the lower wear rates when compared with carbide tools. Finite Element Analysis (FEA) was employed to study the influence of tool wear on temperature and shear stress distribution in the workpiece material.     

井冈山仙口水电站面板堆石坝设计

简要介绍了江西省井冈山仙口电站面板堆石坝的设计和施工运行中遇到的问题及处理方法，并总结了在面板堆石坝设计中的经验和体会．     

基于秩统计量枯水径流分布变点的非参数识别

本文提出了枯水径流时序分布变点的识别原理和基于秩统计量的非参数识别方法，并以东江流域为例，对其干流的枯期径流量年系列（1957-2000年）进行了变点识别，结果显示1974年为东流域枯期径流的显著性分布变点。通过对比分析变点前后的统计参数，1974年后的东江流域枯水径流量年均值明显增加，年际变化的离散程度增大。     

Human face recognition by adaptive processing of tree structures representation

This paper describes a novel method of facial representation and recognition based upon adaptive processing of tree structures. Instead of the conventional flat vector representation for a face, a neural network approach-based technique is proposed to transform the Localised Gabor Feature (LGF) vectors extracted from human facial components into Human Face Tree Structure (HFTS) to represent a human face. A structural training algorithm is assigned to train and recognize the face identity in this HFTS representation with the corresponding LGF vectors. By benchmarking using the tested public face databases presented in this paper, our approach is able to achieve accuracy up to 90% under different scenarios of lighting conditions and posture orientations. This work is supported by the NTU SCE start-up grant (CE-SUG 10/03).     

Confidence modeling for handwriting recognition: algorithms and applications

Confidence scoring can assist in determining how to use imperfect handwriting-recognition output. We explore a confidence-scoring framework for post-processing recognition for two purposes: deciding when to reject the recognizer's output, and detecting when to change recognition parameters e.g., to relax a word-set constraint. Varied confidence scores, including likelihood ratios and posterior probabilities, are applied to an Hidden-Markov-Model (HMM) based on-line recognizer. Receiver-operating characteristic curves reveal that we successfully reject 90% of word recognition errors while rejecting only 33% of correctly-recognized words. For isolated digit recognition, we achieve 90% correct rejection while limiting false rejection to 13%.     

基于特征步态的身份识别方法

本文提出了一种有效实用的基于步态的身份识别方法。通过提取目标行走的差分步态图像,将目标运动过程的动态信息转化为二维平面中的静态信息,利用K-L变换进行特征提取,使用标准的分类器进行分类。在中科院自动化所提供的NLPR数据库上做了大量的仿真实验,验证识别性能。