LDDP-Net: A Lightweight Neural Network with Dual Decoding Paths for Defect Segmentation of LED Chips
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 fiel...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/425 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587519186698240 |
|---|---|
| author | Jie Zhang Ning Chen Mengyuan Li Yifan Zhang Xinyu Suo Rong Li Jian Liu |
| author_facet | Jie Zhang Ning Chen Mengyuan Li Yifan Zhang Xinyu Suo Rong Li Jian Liu |
| author_sort | Jie Zhang |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-ad49b2de33924d4ca88d25270b9a225b |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-ad49b2de33924d4ca88d25270b9a225b2025-01-24T13:48:53ZengMDPI AGSensors1424-82202025-01-0125242510.3390/s25020425LDDP-Net: A Lightweight Neural Network with Dual Decoding Paths for Defect Segmentation of LED ChipsJie Zhang0Ning Chen1Mengyuan Li2Yifan Zhang3Xinyu Suo4Rong Li5Jian Liu6Mechnical and Vehicle Engineering, Hunan University, Changsha 411082, ChinaMechnical and Vehicle Engineering, Hunan University, Changsha 411082, ChinaMechnical and Vehicle Engineering, Hunan University, Changsha 411082, ChinaMechnical and Vehicle Engineering, Hunan University, Changsha 411082, ChinaMechnical and Vehicle Engineering, Hunan University, Changsha 411082, ChinaMechnical and Vehicle Engineering, Hunan University, Changsha 411082, ChinaMechnical and Vehicle Engineering, Hunan University, Changsha 411082, ChinaChip 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.https://www.mdpi.com/1424-8220/25/2/425deep learningdefect detectionfeature fusionlightweight networksemantic segmentationdigital images |
| spellingShingle | Jie Zhang Ning Chen Mengyuan Li Yifan Zhang Xinyu Suo Rong Li Jian Liu LDDP-Net: A Lightweight Neural Network with Dual Decoding Paths for Defect Segmentation of LED Chips Sensors deep learning defect detection feature fusion lightweight network semantic segmentation digital images |
| title | LDDP-Net: A Lightweight Neural Network with Dual Decoding Paths for Defect Segmentation of LED Chips |
| title_full | LDDP-Net: A Lightweight Neural Network with Dual Decoding Paths for Defect Segmentation of LED Chips |
| title_fullStr | LDDP-Net: A Lightweight Neural Network with Dual Decoding Paths for Defect Segmentation of LED Chips |
| title_full_unstemmed | LDDP-Net: A Lightweight Neural Network with Dual Decoding Paths for Defect Segmentation of LED Chips |
| title_short | LDDP-Net: A Lightweight Neural Network with Dual Decoding Paths for Defect Segmentation of LED Chips |
| title_sort | lddp net a lightweight neural network with dual decoding paths for defect segmentation of led chips |
| topic | deep learning defect detection feature fusion lightweight network semantic segmentation digital images |
| url | https://www.mdpi.com/1424-8220/25/2/425 |
| work_keys_str_mv | AT jiezhang lddpnetalightweightneuralnetworkwithdualdecodingpathsfordefectsegmentationofledchips AT ningchen lddpnetalightweightneuralnetworkwithdualdecodingpathsfordefectsegmentationofledchips AT mengyuanli lddpnetalightweightneuralnetworkwithdualdecodingpathsfordefectsegmentationofledchips AT yifanzhang lddpnetalightweightneuralnetworkwithdualdecodingpathsfordefectsegmentationofledchips AT xinyusuo lddpnetalightweightneuralnetworkwithdualdecodingpathsfordefectsegmentationofledchips AT rongli lddpnetalightweightneuralnetworkwithdualdecodingpathsfordefectsegmentationofledchips AT jianliu lddpnetalightweightneuralnetworkwithdualdecodingpathsfordefectsegmentationofledchips |