Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images

Abstract

Efficient quality control is inevitable in the manufacturing of light-emitting diodes (LEDs). Because defective LED chips may be traced back to different causes, a time and cost-intensive electrical and optical contact measurement is employed. Fast photoluminescence measurements, on the other hand, are commonly used to detect wafer separation damages but also hold the potential to enable an efficient detection of all kinds of defective LED chips. On a photoluminescence image, every pixel corresponds to an LED chip's brightness after photoexcitation, revealing performance information. But due to unevenly distributed brightness values and varying defect patterns, photoluminescence images are not yet employed for a comprehensive defect detection. In this work, we show that fully convolutional networks can be used for chip-wise defect detection, trained on a small data-set of photoluminescence images. Pixel-wise labels allow us to classify each and every chip as defective or not. Being measurement-based, labels are easy to procure and our experiments show that existing discrepancies between training images and labels do not hinder network training. Using weighted loss calculation, we were able to equalize our highly unbalanced class categories. Due to the consistent use of skip connections and residual shortcuts, our network is able to predict a variety of structures, from extensive defect clusters up to single defective LED chips.

arXiv comment14 pages, 12 figures

References in corpus (25)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Fully Convolutional Networks for Semantic Segmentation
• Multi-Scale Context Aggregation by Dilated Convolutions
• Understanding Neural Networks Through Deep Visualization
• Going Deeper with Convolutions
• Segmentation-Based Deep-Learning Approach for Surface-Defect Detection
• Fully Convolutional Networks for Semantic Segmentation
• YOLO9000: Better, Faster, Stronger
• Visualizing and Understanding Convolutional Networks
• A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRI
• Pyramid Scene Parsing Network
• Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
• RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
• Fully Convolutional Instance-aware Semantic Segmentation
• Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling
• DeepUNet: A Deep Fully Convolutional Network for Pixel-level Sea-Land Segmentation
• Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
• Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation
• PCA-aided Fully Convolutional Networks for Semantic Segmentation of Multi-channel fMRI

Cited by in corpus (1)

• Rethinking Fully Convolutional Networks for the Analysis of Photoluminescence Wafer Images