计算机视觉下的果实目标检测算法综述

基于计算机视觉的果实目标检测识别是目标检测、计算机视觉、农业机器人等多学科的重要交叉研究课题,在智慧农业、农业现代化、自动采摘机器人等领域,具有重要的理论研究意义和实际应用价值。随着深度学习在图像处理领域中广泛应用并取得良好效果,计算机视觉技术结合深度学习方法的果实目标检测识别算法逐渐成为主流。本文介绍基于计算机视觉的果实目标检测识别的任务、难点和发展现状,以及2类基于深度学习方法的果实目标检测识别算法,最后介绍用于算法模型训练学习的公开数据集与评价模型性能的评价指标,且对当前果实目标检测识别存在的问题和未来可能的发展方向进行讨论。     

Evaluating the performance of table processing algorithms

While techniques for evaluating the performance of lower-level document analysis tasks such as optical character recognition have gained acceptance in the literature, attempts to formalize the problem for higher-level algorithms, while receiving a fair amount of attention in terms of theory, have generally been less successful in practice, perhaps owing to their complexity. In this paper, we introduce intuitive, easy-to-implement evaluation schemes for the related problems of table detection and table structure recognition. We also present the results of several small experiments, demonstrating how well the methodologies work and the useful sorts of feedback they provide. We first consider the table detection problem. Here algorithms can yield various classes of errors, including non-table regions improperly labeled as tables (insertion errors), tables missed completely (deletion errors), larger tables broken into a number of smaller ones (splitting errors), and groups of smaller tables combined to form larger ones (merging errors). This leads naturally to the use of an edit distance approach for assessing the results of table detection. Next we address the problem of evaluating table structure recognition. Our model is based on a directed acyclic attribute graph, or table DAG. We describe a new paradigm, “graph probing,” for comparing the results returned by the recognition system and the representation created during ground-truthing. Probing is in fact a general concept that could be applied to other document recognition tasks as well. Received July 18, 2000 / Accepted October 4, 2001     

Empirical performance evaluation of graphics recognition systems

Presents a methodology for evaluating graphics recognition systems operating on images that contain straight lines, circles, circular arcs, and text blocks. It enables an empirical comparison of vectorization software packages and uses practical performance evaluation methods that can be applied to complete vectorization systems. The methodology includes a set of matching criteria for pairs of graphical entities, a set of performance evaluation metrics, and a benchmark for the evaluation of graphics recognition systems. The benchmark was tested on three systems. The results are reported and analyzed in the paper     

基于序列到序列模型的事件识别

事件识别是以事件为单位进行信息抽取的起点,对后续各个子任务都意义重大。针对事件识别任务,该文提出了一种融入文档信息的序列到序列方法,一方面借助神经网络减少了特征工程产生的人工依赖,另一方面借助注意力机制将局部的词、实体与全局的文档中事件的共现等信息统一建模。在LDC2017E02语料上实验结果表明,该方法能有效提高事件识别的性能。     

基于ROC分析的Canny算法在景象匹配中的应用

根据ROC分析方法能对分类识别算法进行多门限评估的特点,利用其改进Canny算法性能并应用于景象匹配。首先由不同参数组合的Canny算子计算图像的多个边缘提取图,并逐像素进行统计,得到边缘像素相关图;然后采用ROC曲线分析找到最佳的关联阈值,从而确定理论边缘图;最后将参考图与实时图所对应的理论边缘图进行景象匹配。实验结果表明,该方法在参考图和实时图存在一定几何畸变和灰度差异的情况下,能取得较高的平均匹配精度与正确匹配概率。此外,该方法克服了传统Canny算子采用固定参数的缺点,根据多参数自动进行筛选优化,有较强的工程实用性。     

A protocol for performance evaluation of line detection algorithms

Accurate and efficient vectorization of line drawings is essential for any higher level processing in document analysis and recognition systems. In spite of the prevalence of vectorization and line detection methods, no standard for their performance evaluation protocol exists. We propose a protocol for evaluating both straight and circular line extraction to help compare, select, improve, and even design line detection algorithms to be incorporated into line drawing recognition and understanding systems. The protocol involves both positive and negative sets of indices, at pixel and vector levels. Time efficiency is also included in the protocol. The protocol may be extended to handle lines of any shape as well as other classes of graphic objects.     

基于多层次特征集成的中文实体指代识别

实体指代识别(Entity Mention Detection, EMD)是识别文本中对实体的指代(Mention)的任务,包括专名、普通名词、代词指代的识别。本文提出一种基于多层次特征集成的中文实体指代识别方法,利用条件随机场模型的特征集成能力,综合使用字符、拼音、词及词性、各类专名列表、频次统计等各层次特征提高识别性能。本文利用流水线框架,分三个阶段标注实体指代的各项信息。基于本方法的指代识别系统参加了2007年自动内容抽取(ACE07)中文EMD评测,系统的ACE Value值名列第二。     

融合多跳关系标签与依存句法结构信息的事件检测模型

大部分基于依存句法分析的事件检测方法仅聚焦于依存句法结构上的单跳联系,忽视了词与词之间的多跳联系,造成事件触发词与部分相关实体间的语义缺失,从而影响了事件检测效率。因此,为了充分利用词语间的语义相关性提升事件触发词的识别能力,提出了融合多跳关系标签和依存句法结构信息的事件检测模型。构建了一种新型的依存句法多跳树以及多跳关系标签搜索算法,增强了核心词汇的事件表征能力,并结合图注意力网络聚合了词的多阶表示,提升了事件检测性能。在ACE2005数据集上的实验结果显示,提出的增加了多跳关系标签信息的事件检测方法比基准模型性能提升了近2%。     

基于模糊方法的综合评判入侵检测系统

在分析现有入侵检测技术的基础上，结合模糊数学和层次分析法，提出了一种综合评判入侵检测系统性能的新方法，把评估的主观冈素限制在很小的范围内，提高了评判结果的准确度和可信度。并已通过实验验证，表明该方法是有效的。     

角点检测技术研究及进展

角点是图像的重要局部特征,在图像配准、图像理解及模式识别等领域中,角点检测具有十分重要的意义。对角点检测的各种方法进行了分析、比较,给出了性能评价标准。最后,分析了该领域现存的问题、最新研究动态及发展方向。