Full Wafer Process Control Through Object Detection Using Region-Based Convolutional Neural Networks

Thomas Alcaire (1) , Delphine Le Cunff (1) , Jean-Herve Tortai (2) , Sebastien Soulan (2) , Virginie Brouzet (1) , Romain Duru (1) , Christophe Euvrard (1)

1 ST-CROLLES - STMicroelectronics [Crolles]
2 LTM - Laboratoire des technologies de la microélectronique

Full wafer measurement techniques are used in the semiconductor industry to acquire information at a large scale to control process variation or detect potential defects. This process usually results in the generation of full wafer images, containing various objects that need to be identified to evaluate their impact on the final product performance. Artificial intelligence is very powerful to automate this identification routine. In this paper, we present the application of Region-based Convolutional Neural Networks (RCNN) for enhanced process control from full wafer images gathered by two industrial metrology equipments.

Mots clés: Full wafer; Process control; Photoluminescence imaging; Scanning Acoustic Microscopy; RCNN

Domaines: Sciences de l'ingénieur [physics]

Thomas Alcaire, Delphine Le Cunff, Jean-Herve Tortai, Sebastien Soulan, Virginie Brouzet, et al.. Full Wafer Process Control Through Object Detection Using Region-Based Convolutional Neural Networks. 2022 33rd Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC), May 2022, Saratoga Springs, France. pp.1-5, ⟨10.1109/ASMC54647.2022.9792479⟩. ⟨hal-03746567⟩