Academy Offers

AIChE members receive complimentary, unlimited access to live and on-demand AIChE webinars by purchasing them with their newly increased number of credits. See more resources.

Multivariate Image Analysis and Regression (MIA/MIR) in the Process Industries

Source: AIChE
  • Type:
    Conference Presentation
  • Conference Type:
    AIChE Annual Meeting
  • Presentation Date:
    November 3, 2013
  • Duration:
    30 minutes
  • Skill Level:
  • PDHs:

Share This Post:

Multivariate Image Analysis (MIA) was first introduced by Esbensen and Geladi in the mid-late 80’s [1] when they proposed to apply Principal Component Analysis (PCA) on multi-channel images. Most of the early MIA research works were made in the fields of remote sensing , analytical chemistry , and medical imaging where multivariate images were available. The history of MIA in the process industries is more recent , and its introduction in the chemical engineering field was pioneered by John MacGregor and his group. It began almost a decade later when Bharati and MacGregor [2] advocated the use of MIA for on-line process monitoring by applying the approach to time series of images. That is using the imaging system as an on-line PAT type sensor for real-time process monitoring (i.e. Multivariate Statistical Process Control). Today , important image-based problems are solved using multivariate approaches such as: 1) monitoring products for defects , 2) predicting overall product quality , 3) feedback control of product quality , 4) monitoring and control of process conditions. Key contributions from the MacGregor’s group that helped solving these important process problems include the development of Multivariate Image Regression (MIR) methods for predicting any product property or process condition of interest using spectral information [3] , textural information [4] or both , and the use of the image-based models for process control and optimization [5]. These papers led to many other developments and applications in the process engineering field which were recently reviewed in [6]. The objective of this presentation is to provide an overview of the history , methods and applications of MIA that have impacted the process industries. How John MacGregor has inspired further developments in the field , and particularly the work of the two co-authors , will be emphasized.   [1] K. Esbensen , P. Geladi , “Strategy of Multivariate Image Analysis (MIA)” , Chemometrics and Intelligent Laboratory Systems , 7 , 67-86 , 1989. [2] M.H. Bharati , J.F. MacGregor , “Multivariate image analysis for process monitoring and control” , Industrial & Engineering Chemistry Research , 37 , 4715-4724 , 1998. [3] H. Yu , J.F. MacGregor , Multivariate image analysis and regression for prediction of coating content and distribution in the production of snack foods , Chemometrics and Intelligent Laboratory Systems 67 (2003) 125–144. [4] M.H. Bharati , J.J. Liu , J.F. MacGregor , Image texture analysis: methods and comparisons , Chemometrics and Intelligent Laboratory Systems 72 (2004) 57–71. [5] J.J. Liu , J.F. MacGregor , Modeling and optimization of product appearance: application to injection-molded plastic models , Industrial and Engineering Chemistry Research 44 (2005) 4687–4696. [6] C. Duchesne , J.J. Liu , J.F. MacGregor , “Multivariate image analysis in the process industries: A review” , Chemometrics and Intelligent Laboratory Systems , 117 , 116-128 , 2012.

Once the content has been viewed and you have attested to it, you will be able to download and print a certificate for PDH credits. If you have already viewed this content, please click here to login.



Do you already own this?



AIChE Member Credits 0.5
AIChE Members $15.00
AIChE Graduate Student Members Free
AIChE Undergraduate Student Members Free
Non-Members $25.00