Zhang Jie, Chen Ning, Li Mengyuan, Zhang Yifan, Suo Xinyu, Li Rong, Liu Jian
Mechnical and Vehicle Engineering, Hunan University, Changsha 411082, China.
Sensors (Basel). 2025 Jan 13;25(2):425. doi: 10.3390/s25020425.
Chip defect detection is a crucial aspect of the semiconductor production industry, given its significant impact on chip performance. This paper proposes a lightweight neural network with dual decoding paths for LED chip segmentation, named LDDP-Net. Within the LDDP-Net framework, the receptive field of the MobileNetv3 backbone is modified to mitigate information loss. In addition, dual decoding paths consisting of a coarse decoding path and a fine-grained decoding path in parallel are developed. Specifically, the former employs a straightforward upsampling approach, emphasizing macro information. The latter is more detail-oriented, using multiple pooling and convolution techniques to focus on fine-grained information after deconvolution. Moreover, the integration of intermediate-layer features into the upsampling operation enhances boundary segmentation. Experimental results demonstrate that LDDP-Net achieves an mIoU (mean Intersection over Union) of 90.29% on the chip dataset, with parameter numbers and FLOPs (Floating Point Operations) of 2.98 M and 2.24 G, respectively. Comparative analyses with advanced methods reveal varying degrees of improvement, affirming the effectiveness of the proposed method.
芯片缺陷检测是半导体生产行业的一个关键方面，因为它对芯片性能有重大影响。本文提出了一种用于LED芯片分割的具有双解码路径的轻量级神经网络，名为LDDP-Net。在LDDP-Net框架内，对MobileNetv3主干的感受野进行了修改，以减少信息损失。此外，还开发了由粗解码路径和细粒度解码路径并行组成的双解码路径。具体来说，前者采用直接的上采样方法，强调宏观信息。后者更注重细节，使用多个池化和卷积技术，在反卷积后专注于细粒度信息。此外，将中间层特征集成到上采样操作中可增强边界分割。实验结果表明，LDDP-Net在芯片数据集上的mIoU（平均交并比）达到90.29%，参数数量和FLOPs（浮点运算）分别为2.98M和2.24G。与先进方法的对比分析显示出不同程度的改进，证实了所提方法的有效性。
