A Standardized PMML Format for Representing Convolutional Neural Networks with Application to Defect Detection

Published

December 11, 2019

Author(s)

Max K. Ferguson, Yung-Tsun Lee, Anantha Narayanan, Kincho H. Law

Abstract

Convolutional neural networks are becoming a popular tool for image processing in the engineering and manufacturing sectors. However, managing the storage and distribution of trained models is still a difficult task, partially due to the lack of standardized methods for deep neural network representation. Additionally, the interoperability between different machine learning frameworks remains poor. This paper seeks to address this issue by proposing a standardized format, for convolutional neural networks, based on the Predictive Model Markup Language (PMML). A new standardized schema is proposed to represent a range of convolutional neural networks, including classification, regression and semantic segmentation systems. To demonstrate the practical application of this standard, a semantic segmentation model, which is trained to detect casting defects in Xray images, is represented in the proposed PMML format. A high-performance scoring engine is developed to evaluate images and videos against the PMML model. The utility of the proposed format and the scoring engine is evaluated by benchmarking the performance of the defect detection models on a range of different computation platforms.

Citation

Smart and Sustainable Manufacturing Systems

Volume

3

Pub Type

Journals

Download Paper

https://doi.org/10.1520/SSMS20190032

Local Download

Keywords

Smart Manufacturing, Predictive Model Markup Language, Machine Learning Models, Defect Detection, Automated Surface Inspection, Convolutional Neural Networks, Standard, Image Processing

Citation

Ferguson, M. , Lee, Y. , Narayanan, A. and Law, K. (2019), A Standardized PMML Format for Representing Convolutional Neural Networks with Application to Defect Detection, Smart and Sustainable Manufacturing Systems, [online], https://doi.org/10.1520/SSMS20190032, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=928776 (Accessed April 19, 2024)