A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Machine vision based surface roughness assessment system based on the Internet of Things and contourlet transforms
https://orcid.org/https://orcid.org/0009-0007-9577-4429
https://orcid.org/https://orcid.org/0000-0002-5079-9952
https://orcid.org/http://orcid.org/0000-0003-3894-9695
The contemporary progress in the automatic evaluation of surface roughness is based on machine vision systems. The human faults and struggles tangled in measuring surface roughness by means of physical tactile methods are diminished by technologies developed based on machine vision system. In this work, a machine vision system is developed based on two different types of image processing techniques namely curvelet and contourlet transforms for assessment of surface roughness. Contourlet transforms and artificial neural networks-teaching learning based optimization (ANN-TLBO) hybrid model forms the uniqueness of this work. Two different hybrid models are developed, Model-1 curvelet transforms based and Model-2 is based on contourlet tranforms texture feature data and a comparison is made between them. Compared to the hybrid model-1, the hybrid model-2 accurately predicted the surface roughness. Hybrid model-2 scored 98.89% prediction accuracy, outperforming the other model in terms of effectiveness. In order to forecast the surface roughness from provided texture characteristics, an equation is derived from the model-2 based on the weights and bias. An internet of things (IoT)-based system for surface roughness prediction from the captured image texture feature data is created based on the equation. The human measurement of surface roughness can be replaced by an IoT system created with such precision.
Machine vision based surface roughness assessment system based on the Internet of Things and contourlet transforms
https://orcid.org/https://orcid.org/0009-0007-9577-4429
https://orcid.org/https://orcid.org/0000-0002-5079-9952
https://orcid.org/http://orcid.org/0000-0003-3894-9695
The contemporary progress in the automatic evaluation of surface roughness is based on machine vision systems. The human faults and struggles tangled in measuring surface roughness by means of physical tactile methods are diminished by technologies developed based on machine vision system. In this work, a machine vision system is developed based on two different types of image processing techniques namely curvelet and contourlet transforms for assessment of surface roughness. Contourlet transforms and artificial neural networks-teaching learning based optimization (ANN-TLBO) hybrid model forms the uniqueness of this work. Two different hybrid models are developed, Model-1 curvelet transforms based and Model-2 is based on contourlet tranforms texture feature data and a comparison is made between them. Compared to the hybrid model-1, the hybrid model-2 accurately predicted the surface roughness. Hybrid model-2 scored 98.89% prediction accuracy, outperforming the other model in terms of effectiveness. In order to forecast the surface roughness from provided texture characteristics, an equation is derived from the model-2 based on the weights and bias. An internet of things (IoT)-based system for surface roughness prediction from the captured image texture feature data is created based on the equation. The human measurement of surface roughness can be replaced by an IoT system created with such precision.
Machine vision based surface roughness assessment system based on the Internet of Things and contourlet transforms
https://orcid.org/https://orcid.org/0009-0007-9577-4429
https://orcid.org/https://orcid.org/0000-0002-5079-9952
https://orcid.org/http://orcid.org/0000-0003-3894-9695
The contemporary progress in the automatic evaluation of surface roughness is based on machine vision systems. The human faults and struggles tangled in measuring surface roughness by means of physical tactile methods are diminished by technologies developed based on machine vision system. In this work, a machine vision system is developed based on two different types of image processing techniques namely curvelet and contourlet transforms for assessment of surface roughness. Contourlet transforms and artificial neural networks-teaching learning based optimization (ANN-TLBO) hybrid model forms the uniqueness of this work. Two different hybrid models are developed, Model-1 curvelet transforms based and Model-2 is based on contourlet tranforms texture feature data and a comparison is made between them. Compared to the hybrid model-1, the hybrid model-2 accurately predicted the surface roughness. Hybrid model-2 scored 98.89% prediction accuracy, outperforming the other model in terms of effectiveness. In order to forecast the surface roughness from provided texture characteristics, an equation is derived from the model-2 based on the weights and bias. An internet of things (IoT)-based system for surface roughness prediction from the captured image texture feature data is created based on the equation. The human measurement of surface roughness can be replaced by an IoT system created with such precision.
Machine vision based surface roughness assessment system based on the Internet of Things and contourlet transforms
Int J Interact Des Manuf
Chebrolu, Varun (author) / Koona, Ramji (author) / Raju, R. S. Umamaheswara (author)
2025-01-01
16 pages
Article (Journal)
Electronic Resource
English
Machine vision system , Surface roughness , Curvelet-transform , Contourlet-transforms , ANN-TLBO hybrid model , IoT Information and Computing Sciences , Artificial Intelligence and Image Processing , Engineering , Engineering, general , Engineering Design , Mechanical Engineering , Computer-Aided Engineering (CAD, CAE) and Design , Electronics and Microelectronics, Instrumentation , Industrial Design
Machine Vision for Surface Roughness Assessment of Inclined Components
| British Library Online Contents | 2010
Machine Vision-Based Concrete Surface Quality Assessment
| Online Contents | 2010
Machine Vision-Based Concrete Surface Quality Assessment
| British Library Online Contents | 2010
Aircraft-Based Pavement Surface Roughness Assessment
| British Library Online Contents | 2007