Recognizing shipbuilding parts using artificial neural networks and Fourier descriptors

Sanders, David

doi:10.1243/09544054jem1382

Cited by 47 publications

(73 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results were compared with those achieved by the most recently published system for identifying ships' parts [2], using the same shapes for the comparison. The most recently published system used Fourier descriptors on edgedetected shapes without considering corner identification.…”

Section: Testing and Results For The Improved Systemmentioning

confidence: 99%

“…These lines were then overlaid onto the filtered greyscale image for viewing. Later systems used Fourier descriptors [1,2] and artificial neural networks (ANNs) [6][7][8], and in the most recent systems described herein new corner-finding algorithms to effectively reduce noise were also introduced.…”

Section: Proposed Systemmentioning

confidence: 99%

“…Thus, the coefficients B n represent the shape (or form). These Fourier coefficients are invariant under translation, rotation and dilation and just represent the shape [2]. ANNs were trained using backpropagation algorithms.…”

Section: Extracting Fourier Descriptorsmentioning

confidence: 99%

“…Although some shipyards have used robots for welding steel for 20 years [1,2], integration of robotic welding presents problems [3]. The low level of repeatable welds within some ships means that, although the quality and speed of robotic welding are acceptable, generation of programs capable of carrying out welding has proved difficult.…”

Section: Introductionmentioning

confidence: 99%

“…New sub-systems have successfully distinguished between various ships' parts by processing shape information so that Fourier descriptors [4] can be extracted and formed into sets for association with training sets so that decisions can be made. This work was described previously [2]. In that work, images were broken into equal segments, which were then represented as complex numbers by referring coordinate points to a random starting point.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Improving automatic robotic welding in shipbuilding through the introduction of a corner-finding algorithm to help recognise shipbuilding parts

et al. 2011

View full text Add to dashboard Cite

A system that uses a combination of techniques to suggest weld requirements for ships' parts is proposed. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator. New image capture methods are being combined with a decision-making system that uses multiple parallel artificial intelligence (AI) techniques. A pattern recognition system recognises shipbuilding parts using shape contour information. Fourier descriptors provide information and neural networks make decisions about shapes. The system has distinguished between various parts, and programs have been generated to validate the approaches used. The system has recently been improved by pre-processing using a simple and accurate corner finder in an edge-detected image.

show abstract

Section: Testing and Results For The Improved Systemmentioning

confidence: 99%

Section: Proposed Systemmentioning

confidence: 99%

Section: Extracting Fourier Descriptorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving automatic robotic welding in shipbuilding through the introduction of a corner-finding algorithm to help recognise shipbuilding parts

et al. 2011

View full text Add to dashboard Cite

show abstract

A Method to Produce Minimal Real Time Geometric Representations of Moving Obstacles

Sanders

Wang

Bausch

et al. 2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Real time modelling methods are compared for use with a robot manufacturing work-cell and a simple image processing system. The static parts of a robotic manufacturing work-cell are modelled as a number of solid polyhedra. The robot is modelled as a number of connected spheres and cylinders. The static model is renewed when an object enters or leaves the static workplace. Simple polyhedra, spheres and similar 2-D slices in actuator space are compared with other models as representations of objects move in and out of the reach of the robot. Models are compared for their efficiency in accessing data and ability to update as information about moving objects changes. Geometric models of the robot and the robot work-cell are loaded into a path planner to compare the models for efficiency on planning paths around moving objects

show abstract

Making Decisions About Saving Energy in Compressed Air Systems Using Ambient Intelligence and Artificial Intelligence

Sanders

Robinson

Hassan

et al. 2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Compressed air systems are often the most expensive and inefficient industrial systems. For every 10 units of energy, less than 1 unit turns into useful compressed air. Air compressors tend to be kept fully on even if they are not (all) needed. The research proposed in this short paper will combine real time ambient sensing with Artificial Intelligence and Knowledge Management to automatically improve efficiency in energy intensive manufacturing. The research will minimise energy use for air compressors based on real-time manufacturing conditions (and anticipated future requirements). Ambient data will provide detailed information on performance. Artificial Intelligence will make sense of that data and automatically act. Knowledge Management will facilitate the processing of information to advise human operators on actions to reduce energy use and maintain productivity. The aim is to create new intelligent techniques to save energy in compressed air systems.

show abstract

Recognizing shipbuilding parts using artificial neural networks and Fourier descriptors

Cited by 47 publications

References 33 publications

Improving automatic robotic welding in shipbuilding through the introduction of a corner-finding algorithm to help recognise shipbuilding parts

Improving automatic robotic welding in shipbuilding through the introduction of a corner-finding algorithm to help recognise shipbuilding parts

A Method to Produce Minimal Real Time Geometric Representations of Moving Obstacles

Making Decisions About Saving Energy in Compressed Air Systems Using Ambient Intelligence and Artificial Intelligence

Contact Info

Product

Resources

About