Query:
学者姓名:林珊玲
Refining:
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract :
针对多模态工业检测中高维特征之间存在干扰,导致检测率不理想的问题,提出了一种基于标准化流的多模态工业异常检测方法.首先提取图像的3D点云的深度信息将其作为第4个通道添加到RGB图像中,生成融合后的RGBD图像,然后使用预训练的特征提取网络提取融合后的图像特征,最后使用特征训练得到一个用于异常检测的标准化流模型.实验结果表明,异常检测模型在MVTec 3D-AD数据集的平均Pixel AUROC达到95.8%,平均AU-PRO达到86.2%.相较于其他模型分别提升了 2.6%和9.1%.
Keyword :
多模态 多模态 工业异常检测 工业异常检测 标准化流 标准化流 点云 点云
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 谢宏兴 , 林珊玲 , 林志贤 et al. 点云与图像融合的无监督异常检测算法研究 [J]. | 激光与红外 , 2024 , 54 (10) : 1642-1648 . |
MLA | 谢宏兴 et al. "点云与图像融合的无监督异常检测算法研究" . | 激光与红外 54 . 10 (2024) : 1642-1648 . |
APA | 谢宏兴 , 林珊玲 , 林志贤 , 郭太良 , 林坚普 , 吕珊红 . 点云与图像融合的无监督异常检测算法研究 . | 激光与红外 , 2024 , 54 (10) , 1642-1648 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
Due to the hysteresis characteristics of electrowetting display, the luminance of the same driving voltage is different in the voltage rising stage and the voltage falling stage. In this paper, a gray distortion correction method for hysteresis characteristics of electrowetting display is proposed. Firstly, by measuring the influence of hysteresis characteristics on the photoelectric curve under different voltage ranges, the hysteresis curve model of electrowetting display was established by fitting the measured data. Based on this, the driving voltage mapping relationship of the same gray scale in different scenes is constructed, and finally the effect of reducing the luminance difference is achieved to reduce the gray distortion. Experimental results show that the proposed scheme can effectively reduce the degree of distortion, and the maximum gray‐scale relative luminance difference is reduced from 20.07% to 0.01%, and the reduction ratio is 99.93%. The relative luminance difference was reduced by 10.84% on average, and the reduction ratio was 80.98%. The oil aperture ratio distortion is reduced from 5.67% to 0.13%, and the reduction ratio is 97.7%.
Keyword :
Driving mode Driving mode Electrowetting display Electrowetting display Gray scale Gray scale Hysteresis phenomenon Hysteresis phenomenon Voltage modulation Voltage modulation
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Ting Mei , Ziyu Xie , Shanling Lin et al. P‐10.6: Research on gray scale distortion correction method for hysteresis characteristics of electrowetting diaplay [J]. | SID Symposium Digest of Technical Papers , 2024 , 55 : 1249-1257 . |
MLA | Ting Mei et al. "P‐10.6: Research on gray scale distortion correction method for hysteresis characteristics of electrowetting diaplay" . | SID Symposium Digest of Technical Papers 55 (2024) : 1249-1257 . |
APA | Ting Mei , Ziyu Xie , Shanling Lin , Bipeng Cai , Zhixian Lin . P‐10.6: Research on gray scale distortion correction method for hysteresis characteristics of electrowetting diaplay . | SID Symposium Digest of Technical Papers , 2024 , 55 , 1249-1257 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
针对语义分割网络参数量过大导致其难以部署在内存受限的边缘设备等问题,本文提出一种基于BiLevelNet的轻量级实时语义分割算法。首先,利用空洞卷积扩大感受野,并结合特征复用策略增强网络的区域感知能力。接着,嵌入两阶段的PBRA注意力机制,建立远距离相关物体之间的依赖关系以增强网络的全局感知能力。最后,引入结合浅层特征的FADE算子以改善图像上采样效果。实验结果表明,在输入图像分辨率为512×1024的情况下,本文网络在Cityscapes数据集上以121 f/s的速率获得了75.1%的平均交并比,模型大小仅为0.7 M。同时在输入图像分辨率为360×480的情况下,在Camvid数据集上取得68.2%的平均交并比。同当前其他实时语义分割方法相比,该网络性能取得速度与精度的均衡,符合自动驾驶应用场景对实时性的要求。
Keyword :
上采样 上采样 实时语义分割 实时语义分割 深度学习 深度学习 自动驾驶 自动驾驶 自注意力 自注意力
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 吴马靖 , 张永爱 , 林珊玲 et al. 基于BiLevelNet的实时语义分割算法 [J]. | 光电工程 , 2024 , 51 (05) : 25-38 . |
MLA | 吴马靖 et al. "基于BiLevelNet的实时语义分割算法" . | 光电工程 51 . 05 (2024) : 25-38 . |
APA | 吴马靖 , 张永爱 , 林珊玲 , 林志贤 , 林坚普 . 基于BiLevelNet的实时语义分割算法 . | 光电工程 , 2024 , 51 (05) , 25-38 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
Micro-LED拥有出色的亮度、高发光效率、低能耗、高反应速度、超高解析度与色彩饱和度等优势,且具备自发光和感测能力,是一项十分理想的显示技术。传统的直流灰度调控方法不再适用于驱动单端载流子注入结构的交流型LED,本文根据单端注入型LED器件在不同频率、幅度、占空比以及交流驱动模式下的光电特性,提出一种基于人眼视觉特性的相对占空比混合式灰度调制方案。结果表明,正负方波驱动模式下的器件在相同电压和频率下表现出更强的发光亮度,并且器件随着驱动频率的增加,发光亮度逐渐提升。最后,结合人眼视觉特性,验证了发光器件在不同相对占空比、幅度、频率的混合式调制方法下实现了由2个灰度到8个灰度等级的提升,为未来新型发光器件灰度调制提供新思路。
Keyword :
LED LED 交流电 交流电 光电性能 光电性能 单端载流子注入 单端载流子注入 灰度调制 灰度调制
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 林珊玲 , 卢杰 , 吴朝兴 et al. 单端注入型LED的光电特性与灰度调制技术研究 [J]. | 电子元件与材料 , 2024 , 43 (05) : 521-527 . |
MLA | 林珊玲 et al. "单端注入型LED的光电特性与灰度调制技术研究" . | 电子元件与材料 43 . 05 (2024) : 521-527 . |
APA | 林珊玲 , 卢杰 , 吴朝兴 , 林志贤 , 郭太良 . 单端注入型LED的光电特性与灰度调制技术研究 . | 电子元件与材料 , 2024 , 43 (05) , 521-527 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
为改善暗环境下图像的成像效果,本文提出了一种无监督双路低光照图像增强算法,结合了色彩校正和结构信息.该算法基于生成对抗网络,其中生成器采用双分支结构同时处理图像的色彩与结构细节,以实现更自然的颜色恢复和更清晰的纹理细节.判别器引入空间辨别模块(spatial-discriminative block,SDB),以增强其判别能力,推动生成器生成更真实的图像.图像色彩校正模块(Illumination-guided color correction block,IGCB)利用光照特征引导,减少低光照环境下噪声和伪影的影响.通过多尺度通道融合模块(selective kernel channel fusion,SKCF)和优化的注意力卷积模块(convolution attention block,CAB),增强了图像的语义信息和局部细节.实验结果表明,该算法在LOL和LSRW数据集上表现优于经典方法,在LOLv1和LOLv2数据集上,PSNR和SSIM指标分别达到19.89与0.672,以及20.08与0.693,整体性能优于现有无监督算法.实际应用验证了该算法在恢复低光照图像的亮度、对比度和色彩方面的有效性.
Keyword :
低光照图像增强 低光照图像增强 多尺度特征融合 多尺度特征融合 注意力卷积 注意力卷积 色彩校正 色彩校正
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 林珊玲 , 陈燕 , 张雪 et al. 结合色彩校正和结构信息的双路低光照图像增强 [J]. | 光电工程 , 2024 , 51 (9) : 80-94 . |
MLA | 林珊玲 et al. "结合色彩校正和结构信息的双路低光照图像增强" . | 光电工程 51 . 9 (2024) : 80-94 . |
APA | 林珊玲 , 陈燕 , 张雪 , 林志贤 , 林坚普 , 吕珊红 et al. 结合色彩校正和结构信息的双路低光照图像增强 . | 光电工程 , 2024 , 51 (9) , 80-94 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
In order to solve the problem that the color of the reflective display color electrowetting display is inconsistent under ambient light with different color temperatures, which affects the color reproduction of the displayed picture, a color correction method based on the spectral reflectance characteristics of color electrowetting display is proposed. The spectral correspondence of the display color under ambient light with different color temperatures is obtained through the spectral reflectance characteristics of color electrowetting display, so as to establish the mapping relationship of the display color of color electrowetting display under ambient light with different color temperatures. According to the mapping relationship, the input color data is corrected to reduce the color difference of the displayed colors under ambient light with different color temperatures. The experimental results show that the chromaticity data of 100 test color blocks before and after the correction by the method in the two experimental light sources are reduced by 55% and 35% respectively with the average color difference of the standard light source, and the average subjective evaluation Z-scores of the corrected display images are 0.45 and 0. 25.
Keyword :
ambient light ambient light color correction color correction color difference color difference electrowetting display electrowetting display spectral properties spectral properties
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Liu, Yumin , Lin, Shanling , Lin, Zhixian et al. Color correction of color electrowetting display under ambient light with different color temperatures [J]. | CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS , 2024 , 39 (1) : 32-39 . |
MLA | Liu, Yumin et al. "Color correction of color electrowetting display under ambient light with different color temperatures" . | CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS 39 . 1 (2024) : 32-39 . |
APA | Liu, Yumin , Lin, Shanling , Lin, Zhixian , Guo, Tailiang . Color correction of color electrowetting display under ambient light with different color temperatures . | CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS , 2024 , 39 (1) , 32-39 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
针对太阳能电池片缺陷检测方法存在精度低的问题,提出一种基于改进的YOLOv5s太阳能电池片表面缺陷检测算法.首先,为了解决电池片小目标缺陷检测问题,提出了上下文Transformer网络(CoT),可以为小目标提供全局上下文信息,帮助模型更好地预测小目标.其次,将CBAM注意力加入到Head部分的C3模块,能够更好地捕捉输入特征图的重要通道和空间位置,提高模型的性能和鲁棒性.接着,使用轻量级的通用上采样算子CARAFE减少上采样过程中特征信息的损失,保证了特征信息的完整性.最后,使用WIoU作为边界框损失函数,大幅提升了回归的准确性,并且有助于快速实现模型的收敛.实验结果显示,改进后的YOLOv5s相较于原始算法在Precision、Recall、mAP@0.5三个指标上分别提高了5.5%、4.1%、3.3%,检测速度达到了76 FPS,满足太阳能电池片缺陷检测要求.
Keyword :
CARAFE CARAFE YOLOv5s YOLOv5s 上下文Transformer网络 上下文Transformer网络 太阳能电池片 太阳能电池片 损失函数 损失函数
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 彭雪玲 , 林珊玲 , 林志贤 et al. 改进的YOLOv5s太阳能电池片缺陷检测算法 [J]. | 液晶与显示 , 2024 , 39 (2) : 237-247 . |
MLA | 彭雪玲 et al. "改进的YOLOv5s太阳能电池片缺陷检测算法" . | 液晶与显示 39 . 2 (2024) : 237-247 . |
APA | 彭雪玲 , 林珊玲 , 林志贤 , 郭太良 . 改进的YOLOv5s太阳能电池片缺陷检测算法 . | 液晶与显示 , 2024 , 39 (2) , 237-247 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
针对反射式显示器彩色电润湿电子纸在不同色温环境光下显示颜色不一致,影响显示图片色彩还原度的问题,提出一种基于彩色电润湿电子纸光谱反射率特性的色彩校正方法.通过彩色电润湿电子纸的光谱反射率特性,得到不同色温环境光下显示颜色的光谱对应关系,以此建立不同色温环境光下彩色电润湿电子纸显示颜色的映射关系,并根据该映射关系对输入颜色数据进行校正,从而减小不同色温环境光下显示颜色的色差.设置标准光源A(5000 K)、实验光源B(3500 K)和实验光源C(6500 K)对样品进行测试.在两个实验光源下,测量100个测试色块在经过本文方法校正前后的色度数据.实验结果表明,校正前后显示颜色与标准光源下显示颜色的平均色差分别减小了55%和35%,校正后的显示图像平均主观评价Z得分分别为0.45和0.25.
Keyword :
光谱特性 光谱特性 彩色电润湿电子纸 彩色电润湿电子纸 环境光 环境光 色差 色差 色彩校正 色彩校正
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 刘予敏 , 林珊玲 , 林志贤 et al. 不同色温环境光下彩色电润湿电子纸的色彩校正 [J]. | 液晶与显示 , 2024 , 39 (1) : 32-39 . |
MLA | 刘予敏 et al. "不同色温环境光下彩色电润湿电子纸的色彩校正" . | 液晶与显示 39 . 1 (2024) : 32-39 . |
APA | 刘予敏 , 林珊玲 , 林志贤 , 郭太良 . 不同色温环境光下彩色电润湿电子纸的色彩校正 . | 液晶与显示 , 2024 , 39 (1) , 32-39 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
为解决彩色电泳电子纸因粘滞阻力等引起的显示颜色饱和度低、边缘模糊等问题,本文提出基于HSL空间的彩色电子纸边缘增强误差扩散算法,以提高图像显示质量。该算法首先将去噪图像利用边缘检测算子得到边缘增强图像,结合边缘增强图像像素邻域平均灰度、像素与邻域灰度差异和像素邻域相似度得到新RGB图像像素值。接着,新RGB图像通过阈值处理过程得到16色阶RGB图像。最后,16色阶RGB图像转换到HSL空间,建立HSL和RGB色彩空间的转换模型,根据像素点的亮度和饱和度计算出调整因子,从而增强RGB图像饱和度。该算法与传统的误差扩散算法相比,信噪比PSNR提高了3.9%~26.7%,UCIQE提高了10.1%~48.2%,相似度SSIM提高了13.2%~25.4%。主观评价参考ITU-R BT.500-1标准设计实验计算Z得分,最终本文算法处理后图像在彩色电子纸上显示的图像细节和颜色更加接近原图,整体视觉效果更好。
Keyword :
图像增强 图像增强 彩色电泳电子纸 彩色电泳电子纸 误差扩散 误差扩散 边缘检测 边缘检测 饱和度 饱和度
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 林珊玲 , 谢欣欣 , 林坚普 et al. 增强彩色电子纸饱和度的误差扩散优化 [J]. | 光电工程 , 2024 , 51 (01) : 122-132 . |
MLA | 林珊玲 et al. "增强彩色电子纸饱和度的误差扩散优化" . | 光电工程 51 . 01 (2024) : 122-132 . |
APA | 林珊玲 , 谢欣欣 , 林坚普 , 林志贤 , 郭太良 . 增强彩色电子纸饱和度的误差扩散优化 . | 光电工程 , 2024 , 51 (01) , 122-132 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
Aiming at the problem of low accuracy of the method for solar cell defect detection, a surface defect detection algorithm based on the improved YOLOv5s solar cell is proposed. First, in order to solve the problem of small target defect detection on the cell sheet, the Contextual Transformer Network (CoT) is proposed, which can provide global contextual information for small targets and the model better at predicting small targets. Secondly, by adding CBAM attention to the C3 module in the Head part, the important channels and spatial locations of the input feature maps can be better captured to improve the performance and robustness of the model. Next, the integrity of feature information is ensured by using CARAFE, a lightweight generalized up-sampling operator, to reduce the loss of feature information during up-sampling. Finally, by using WIoU as the bounding box loss function, the accuracy of the regression can be greatly improved and the convergence of model can be achieved quickly. The experimental results show that compared with the original algorithm, the improved YOLOv5s improves the three indicators of Precision, Recall, and mAP@0. 5 by 5. 5%, 4. 1%, and 3. 3% respectively, and the detection speed reaches 76 FPS, which meets the requirements of solar cell defect detection. © 2024, Science Press. All rights reserved.
Keyword :
CARAFE CARAFE contextual transformer network contextual transformer network loss function loss function solar cell solar cell YOLOv5s YOLOv5s
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Peng, X. , Lin, S. , Lin, Z. et al. Defect detection algorithm of improved YOLOv5s solar cell [J]. | Chinese Journal of Liquid Crystals and Displays , 2024 , 39 (2) : 237-247 . |
MLA | Peng, X. et al. "Defect detection algorithm of improved YOLOv5s solar cell" . | Chinese Journal of Liquid Crystals and Displays 39 . 2 (2024) : 237-247 . |
APA | Peng, X. , Lin, S. , Lin, Z. , Guo, T. . Defect detection algorithm of improved YOLOv5s solar cell . | Chinese Journal of Liquid Crystals and Displays , 2024 , 39 (2) , 237-247 . |
Export to | NoteExpress RIS BibTex |
Version :
Export
Results: |
Selected to |
Format: |