Focused and TSOM Images Two-Input Deep-Learning Method for Through-Focus Scanning Measuring
Through-focus scanning optical microscopy (TSOM) is one of the recommended measurement methods in semiconductor manufacturing industry in recent years because of its rapid and nondestructive properties. As a computational imaging method, TSOM takes full advantage of the information from defocused im...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/7/3430 |
| _version_ | 1797440476041707520 |
|---|---|
| author | Zhange Zhang Jiajun Ren Renju Peng Yufu Qu |
| author_facet | Zhange Zhang Jiajun Ren Renju Peng Yufu Qu |
| author_sort | Zhange Zhang |
| collection | DOAJ |
| description | Through-focus scanning optical microscopy (TSOM) is one of the recommended measurement methods in semiconductor manufacturing industry in recent years because of its rapid and nondestructive properties. As a computational imaging method, TSOM takes full advantage of the information from defocused images rather than only concentrating on focused images. In order to improve the accuracy of TSOM in nanoscale dimensional measurement, this paper proposes a two-input deep-learning TSOM method based on Convolutional Neural Network (CNN). The TSOM image and the focused image are taken as the two inputs of the network. The TSOM image is processed by three columns convolutional channels and the focused image is processed by a single convolution channel for feature extraction. Then, the features extracted from the two kinds of images are merged and mapped to the measuring parameters for output. Our method makes effective use of the image information collected by TSOM system, for which the measurement process is fast and convenient with high accuracy. The MSE of the method can reach 5.18 nm<sup>2</sup> in the measurement of gold lines with a linewidth range of 247–1010 nm and the measuring accuracy is much higher than other deep-learning TSOM methods. |
| first_indexed | 2024-03-09T12:07:45Z |
| format | Article |
| id | doaj.art-7d7029b3ad56487aae807b73e3d27857 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T12:07:45Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7d7029b3ad56487aae807b73e3d278572023-11-30T22:55:37ZengMDPI AGApplied Sciences2076-34172022-03-01127343010.3390/app12073430Focused and TSOM Images Two-Input Deep-Learning Method for Through-Focus Scanning MeasuringZhange Zhang0Jiajun Ren1Renju Peng2Yufu Qu3School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing 100191, ChinaZheku Technology (Shanghai) Co., Ltd., Shanghai 201210, ChinaSchool of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing 100191, ChinaSchool of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing 100191, ChinaThrough-focus scanning optical microscopy (TSOM) is one of the recommended measurement methods in semiconductor manufacturing industry in recent years because of its rapid and nondestructive properties. As a computational imaging method, TSOM takes full advantage of the information from defocused images rather than only concentrating on focused images. In order to improve the accuracy of TSOM in nanoscale dimensional measurement, this paper proposes a two-input deep-learning TSOM method based on Convolutional Neural Network (CNN). The TSOM image and the focused image are taken as the two inputs of the network. The TSOM image is processed by three columns convolutional channels and the focused image is processed by a single convolution channel for feature extraction. Then, the features extracted from the two kinds of images are merged and mapped to the measuring parameters for output. Our method makes effective use of the image information collected by TSOM system, for which the measurement process is fast and convenient with high accuracy. The MSE of the method can reach 5.18 nm<sup>2</sup> in the measurement of gold lines with a linewidth range of 247–1010 nm and the measuring accuracy is much higher than other deep-learning TSOM methods.https://www.mdpi.com/2076-3417/12/7/3430deep learningdimensional measurementcomputational imagingthrough-focus scanning optical microscopy |
| spellingShingle | Zhange Zhang Jiajun Ren Renju Peng Yufu Qu Focused and TSOM Images Two-Input Deep-Learning Method for Through-Focus Scanning Measuring Applied Sciences deep learning dimensional measurement computational imaging through-focus scanning optical microscopy |
| title | Focused and TSOM Images Two-Input Deep-Learning Method for Through-Focus Scanning Measuring |
| title_full | Focused and TSOM Images Two-Input Deep-Learning Method for Through-Focus Scanning Measuring |
| title_fullStr | Focused and TSOM Images Two-Input Deep-Learning Method for Through-Focus Scanning Measuring |
| title_full_unstemmed | Focused and TSOM Images Two-Input Deep-Learning Method for Through-Focus Scanning Measuring |
| title_short | Focused and TSOM Images Two-Input Deep-Learning Method for Through-Focus Scanning Measuring |
| title_sort | focused and tsom images two input deep learning method for through focus scanning measuring |
| topic | deep learning dimensional measurement computational imaging through-focus scanning optical microscopy |
| url | https://www.mdpi.com/2076-3417/12/7/3430 |
| work_keys_str_mv | AT zhangezhang focusedandtsomimagestwoinputdeeplearningmethodforthroughfocusscanningmeasuring AT jiajunren focusedandtsomimagestwoinputdeeplearningmethodforthroughfocusscanningmeasuring AT renjupeng focusedandtsomimagestwoinputdeeplearningmethodforthroughfocusscanningmeasuring AT yufuqu focusedandtsomimagestwoinputdeeplearningmethodforthroughfocusscanningmeasuring |