A sub-region one-to-one mapping (SOM) detection algorithm for glass passivation parts wafer surface low-contrast texture defects

Glass Passivation Parts (GPP) wafer texture defects are one of the most important factors affecting the accuracy of wafer defect detection. Template matching has local errors and low efficiency, and deep learning requires many training samples. In the early stage, defect training sample sets cannot be provided. This paper discusses the design of an effective GPP wafer grain region texture defect detection algorithm using a sub-region one-to-one mapping. A set of standard wafer datum is selected as the reference of grain region segmentation detection, and then the standard wafer images and test GPP wafer images are automatically calibrated and segmented, respectively. Then, a series of pre-processes were performed to equalize the sizes of the two grain-region images. Then the grain region was divided into an equal number of rectangular sub-regions of the same size according to the measurement precision requirement. The correlation degree of each test sub-region is judged by the designed three-channel RGB gray-scale similarity decision functions. Experiments show that the algorithm successfully achieved the necessary calibration and segmentation for the grain region. Compared with the template and histogram matching algorithms, the proposed method does not require a training set, the detection accuracy is significantly improved and the detection efficiency is up to 29.74 times better on average using the proposed algorithm.

     

Delay‐dependent stability of nonlinear hybrid neutral stochastic differential equations with multiple delays

In this article, we study the delay‐dependent stability of a class of hybrid neutral stochastic differential equations (NSDEs) with multiple delays which is highly nonlinear. Some novel stability criteria are investigated according to Lyapunov functions and generalized Itô's formula. In particular, we generalize and improve the results in Shen et al, Systems & Control Letters (2018) from a single delay to multiple delays.     

Supervised discrete hashing through similarity learning

Multimedia Tools and Applications - Supervised hashing has achieved better accuracy than unsupervised hashing in many practical applications owing to its use of semantic label information. However,...     

Augmented Online Sequential Quaternion Extreme Learning Machine

Neural Processing Letters - Online sequential extreme learning machine (OS-ELM) is one of the most popular real-time learning strategy for feedforward neural networks with single hidden layer due...     

Finite Time Synchronization of Delayed Quaternion Valued Neural Networks with Fractional Order

Neural Processing Letters - In this article, the finite time (FT) synchronization problem of fractional order quaternion valued neural networks with time delay is investigated. Without separating...     

An SVD-based adaptive robust speech steganography using MDCT coefficient

Multimedia Tools and Applications - Speech is one of the essential ways of communication. The study of speech steganography provides great value in information security. To improve imperceptibility...     

Study of UAV tracking based on CNN in noisy environment

Multimedia Tools and Applications - Recently, there are lots of tracking methods proposed to improve the performance of visual tracking in videos with challenging situations, such as background...     

面向可重构扫描网络的锁定隔离安全结构

为使可重构扫描网络免受未经授权的访问、恶意仪器对传输数据的窜改和嗅探3种安全攻击的影响,提出了锁定隔离安全结构.该结构首先把彼此不具有安全威胁的仪器分成一组,通过控制隔离信号实现组与组之间的单独访问,以防止恶意仪器对传输数据的窜改和嗅探.然后通过使用锁段插入位保护关键的仪器,只有扫描网络中处于特定位置的多个键值被设置成特定值(0,1序列)时锁段插入位才能打开,能加大未经授权访问的难度.此外,为解决仪器分组多导致硬件开销大和布线困难的问题,提出了仪器分组算法,根据仪器间的安全关系构建无向图,然后对无向图求极大独立集,能有效地减少仪器分组数.在ITC 02基准电路上的实验结果表明,与国际上同类方法相比,所提的安全结构打开锁段插入位所需要的时间增大了7倍,在面积、功耗和布线上的平均减少百分比分别为3.81%,9.02%和4.55%.     

可见光-远红外图像的多模态能见度深度学习模型

为了增强能见度深度学习模型在小样本条件下的准确率和鲁棒性,提出一种基于可见光-远红外图像的多模态能见度深度学习方法.首先,利用图像配准获取视野范围与分辨率均相同的可见光-远红外输入图像对;然后,构造三分支并行结构的多模态特征融合网络;分别在可见光图像、远红外图像及其累加特征图中提取不同性质的大气特征,各分支的特征信息通过网络结构实现模态互补与融合;最后在网络末端输出图像场景所对应的能见度的等级.采用双目摄像机收集不同天气情况下的室外真实可见光-远红外图像作为实验数据,在不同性能指标、多角度下的实验结果表明,与传统单模态能见度深度学习模型相比,多模态能见度模型可显著提高小样本条件下能见度检测的准确率和鲁棒性.     

注意力机制在自然场景文字检测中的应用

针对目前主流的基于分割的文字检测方法中由于需要复杂的后处理过程保证检测精度,通常难以实现高检测速度的问题,提出一种应用位置注意力模块和金字塔注意力网络2种注意力机制的方法.首先用金字塔注意力网络对图像进行特征提取及语义分割;同时将位置注意力模块应用于高层特征,通过加强图像中相似物体的权重加强对文字的检测效果;最后进行简单有效的后处理,在实现较高检测准确度的前提下提高检测速度.实验结果表明,在Total-text数据集中,采用更轻量化的骨干网络时,所提方法在检测速度上优势明显;采用更深层的骨干网络时,所提方法的检测准确度领先2.0％.