相关实验视频

Updated: May 5, 2026

Lensless Fluorescent Microscopy on a Chip

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

LDDP-Net:一种轻量级的神经网络,具有双解码路径,用于LED芯片的缺陷细分

Jie Zhang¹, Ning Chen¹, Mengyuan Li¹

¹Mechnical and Vehicle Engineering, Hunan University, Changsha 411082, China.

Sensors (Basel, Switzerland)

|January 25, 2025

概括

本研究介绍了LDDP-Net,这是一种用于LED芯片缺陷检测的轻量级神经网络. 它在芯片细分方面实现了高精度,提高了半导体制造质量.

科学领域:

半导体制造业半导体制造业
计算机视觉计算机视觉
人工智能的人工智能

背景情况:

芯片缺陷检测对于半导体生产质量和芯片性能至关重要.
现有的方法可能会因信息丢失和细粒度细分而扎.

研究的目的:

提出LDDP-Net,一种轻量级的神经网络,用于高效准确的LED芯片细分.
为了提高半导体制造中的缺陷检测能力.

主要方法:

开发了LDDP-Net与修改的MobileNetv3骨干,以减少信息丢失.
实现了用于并行处理的双解码路径 (粗粒和细粒).
集成的中间层特征,以提高边界细分的准确性.

主要成果:

在芯片数据集上,LDDP-Net实现了平均90.29%的跨欧交叉点 (mIoU).
该网络轻量级,有298万个参数和2.24千兆浮点操作 (FLOP).
与现有的先进方法相比,证明了显著的改进.

结论:

LDDP-Net为LED芯片细分提供了有效和高效的解决方案.
拟议的架构增强了半导体制造中的缺陷检测精度和边界细分.

关键词:

深度学习是一种深度学习.发现缺陷检测检测缺陷检测数字图像数字图像数字图像功能融合功能融合功能轻量级网络轻量级的网络.语义细分语义细分语义细分语义细分的空间分辨率.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

相关概念视频

Reducing Line Loss

Reducing Line Loss

In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...