Automatic Defect Classification Without Sampling and Feature Selection

摘要

Systems and methods for defection classification in a semiconductor process are provided. The system includes a communication line configured to receive a defect image of a wafer from the semiconductor process and a deep-architecture neural network in electronic communication with the communication line. The neural network has a first convolution layer of neurons configured to convolve pixels from the defect image with a filter to generate a first feature map. The neural network also includes a first subsampling layer configured to reduce the size and variation of the first feature map. A classifier is provided for determining a defect classification based on the feature map. The system may include more than one convolution layers and/or subsampling layers. A method includes extracting one or more features from a defect image using a deep-architecture neural network, for example a convolutional neural network.

主权项

1. A system for defect classification in a semiconductor process, comprising:
a communication line configured to receive a defect image of a wafer from the semiconductor process; a deep architecture neural network in electronic communication with the communication line, comprising:
a first convolution layer of neurons, each neuron configured to convolve a corresponding receptive field of pixels from the defect image with a filter to generate a first feature map;a first subsampling layer configured to reduce the size and variation of the first feature map; anda classifier for determining a defect classification based on the feature map.