文献类型：期刊文献

英文题名：Merged-Sampling Mask R-CNN With Random Proposal Expansion for Particle Measurement of SEM Images of Molecular Sieve Catalysts

作者：Xin, Jiade[1];Wei, Zhangpeng[1];Yang, Minglei[1];Peng, Xin[1];Du, Wenli[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2021

卷号：70

外文期刊名：IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT

收录：;EI(收录号：20214511139417);WOS:【SCI-EXPANDED(收录号:WOS:000719563600005)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61988101, Grant 61725301, and Grant 61803157; in part by the International (Regional) Cooperation and Exchange Project under Grant 61720106008; and in part by the Shanghai Pujiang Program under Grant 21PJ1402200.

语种：英文

外文关键词：Proposals; Image segmentation; Training; Scanning electron microscopy; Molecular sieves; Feature extraction; Transfer learning; Data augmentation; instance segmentation; Mask R-CNN; molecule sieve catalysts; overfitting

摘要：Scanning electron microscope (SEM) images of molecular sieve catalysts contain information about the shapes and sizes of these particles. SEM image measurement is a crucial step in the evaluation of the catalytic performances. Instance segmentation methods, such as Mask R-CNN, are effective in automatically analyzing SEM images. However, their performance is limited in small datasets. Although overfitting caused by small datasets can be addressed through data augmentation at the image level, the application of Mask R-CNN still needs further improvement for generalization enhancement. In this article, two techniques for Mask R-CNN are proposed to alleviate overfitting during the training on small datasets. First, merged sampling on the region proposal network simultaneously samples proposals with high and low scores in order that the head networks can be exposed to more diverse proposal samples. Second, random proposal expansion enhances the diversity of samples provided to the mask branch of Mask R-CNN. These two techniques can be viewed as data augmentation at the instance level. Experiments on a small SEM image dataset showed that merged-sampling Mask R-CNN with random proposal expansion improved about the average precision (AP) by 5%, compared with the original Mask R-CNN. Overfitting on the small dataset is effectively controlled using the proposed methods. Hence, the results of the particle measurements of the industrial SEM images improved.