18195190. DEFECT DETECTION DEVICE AND METHOD THEREOF simplified abstract (Samsung Electronics Co., Ltd.)
Contents
- 1 DEFECT DETECTION DEVICE AND METHOD THEREOF
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DEFECT DETECTION DEVICE AND METHOD THEREOF - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
DEFECT DETECTION DEVICE AND METHOD THEREOF
Organization Name
Inventor(s)
Sungwook Hwang of Suwon-si (KR)
DEFECT DETECTION DEVICE AND METHOD THEREOF - A simplified explanation of the abstract
This abstract first appeared for US patent application 18195190 titled 'DEFECT DETECTION DEVICE AND METHOD THEREOF
Simplified Explanation
The abstract describes a defect detection device that uses an artificial neural network to determine the type and location of defects on a wafer by analyzing layout and inspection images.
- Memory stores layout image with circuit and dummy patterns
- Controller includes artificial neural network to learn layout image
- Controller analyzes inspection image to determine if defect is in circuit or dummy pattern area
- Type of defect is determined based on location in circuit or dummy pattern area
Potential Applications
This technology can be applied in the semiconductor industry for quality control and defect detection in wafer manufacturing processes.
Problems Solved
1. Efficient defect detection in semiconductor wafers 2. Accurate classification of defects based on their location in the circuit pattern
Benefits
1. Improved quality control in wafer manufacturing 2. Faster identification and classification of defects 3. Reduction in production costs due to early defect detection
Potential Commercial Applications
Optimizing Semiconductor Manufacturing Processes with Artificial Neural Networks
Possible Prior Art
One possible prior art in this field is the use of machine learning algorithms for defect detection in semiconductor manufacturing processes. However, the specific application of an artificial neural network to determine defect type based on location in circuit or dummy pattern areas may be a novel approach.
Unanswered Questions
How does the artificial neural network learn and adapt to different types of defects?
The abstract does not provide details on the training process of the artificial neural network and how it can effectively classify various types of defects.
What is the accuracy rate of defect classification using this technology compared to traditional methods?
The abstract does not mention the performance metrics or comparative analysis of the defect detection device with existing techniques.
Original Abstract Submitted
A defect detection device includes: a memory configured to store a layout image indicating a circuit pattern and indicating a dummy pattern; and a controller comprising an artificial neural network configured to learn the layout image, the controller being configured to: determine, based on an inspection image obtained by photographing an area including a defect on a wafer, whether the defect is in a first area in which the circuit pattern is positioned or in a second area in which the dummy pattern is positioned, by using the artificial neural network, and determine a type of the defect based on whether the defect is positioned is in the first area or in the second area.
