Real-time Machine Vision System Research Articles

Monitoring mineral wool production using real-time machine vision

Abstract This paper describes the development and use of a real-time machine vision system in the industrial production of mineral wool. Because of specific operating requirements and the very hostile environment the system employs unique hardware and software features. The main requirement is for real-time detection and control of the trajectory of molten rock as it falls onto a system of spinning wheels. The jet exhibits significant variation of its position with time, as a consequence of complex thermodynamic and hydrodynamic processes, resulting in a wide variation of quality and quantity of final product. Algorithms were developed to detect variations in the jet trajectory with time and this information is used to generate suitable control data.

The monitoring of froth surfaces on industrial flotation plants using connectionist image processing techniques

The rapid development of computer vision, computational resources, artificial intelligence and the integration of these technologies are creating new possibilities in the design and implementation of commercial machine vision systems. In minerals engineering numerous opportunities for the application of these systems exist, such as the characterization of flotation froth structures which is discussed in this paper by way of example. A general model for the development of feasible, real-time machine vision systems is proposed, which is based on an analogy with biological visual perception made possible by a connectionist approach and the ability of neural networks to solve ill-posed problems. It is shown that both supervised and unsupervised neural nets can be used in different ways to analyze froth structures of industrial flotation cells. Unsupervised (self-organizing) neural nets can monitor process behaviour on a continuous rather than on a discrete basis, which makes the early detection of erratic process control possible. Since some losses in information are incurred with the use of self-organizing systems, intelligent monitoring and control systems would in practice probably be comprised of both types of neural nets.

Switched capacitor networks for focal plane image processing systems

The use of switched capacitor (SC) networks as an alternative to large resistor networks for performing computations in VLSI circuits for real-time machine vision and image processing systems is investigated. A mapping can be made from any resistor network to an equivalent SC network that has the same node voltage solution in steady state. However, it takes several switching cycles for a charge to be distributed in the SC network before steady state is reached. Results indicate that SC networks can be used in moderate resolution systems (250*250 pixels) operating at video rate. A chip that implemented several switched capacitor networks for spatial smoothing of images in one dimension was fabricated and tested. The amount of spatial smoothing can be adjusted when the clocking scheme applied to the network is varied. >

Morphologic edge detection

Edge operators based on gray-scale morphologic operations are introduced. These operators can be efficiently implemented in near real time machine vision systems which have special hardware support for gray-scale morphologic operations. The simplest morphologic edge detectors are the dilation residue and erosion residue operators. The underlying motivation for these and some of their combinations are discussed and justified. Finally, the blur-minimum morphologic edge operator is defined. Its inherent noise sensitivity is less than the dilation or the erosion residue operators. Some experimental results are provided to show the validity of these morphologic operators. When compared with the enhancement/thresholding edge detectors and the cubic facet second derivative zero-crossing edge operator, the results show that all the edge operators have similar performance when the noise is small. However, as the noise increases, the second derivative zero-crossing edge operator and the blur-minimum morphologic edge operator have much better performance than the rest of the operators. The advantage of the blur-minimum edge operator is that it is less computationally complex than the facet edge operator.

Morphologic Edge Detection

Edge operators based on grayscale morphologic operations are introduced. These operators can be efficiently implemented in near real time machine vision systems which have special hardware support for grayscale morphologic operations. The simplest morphologic edge detectors are the dilation residue and erosion residue operators. The underlying motivation for these is discussed. Finally, the blur minimum morphologic edge operator is defined. Its inherent noise sensitivity is less than the dilation or the erosion residue operators. Some experimental results are provided to show the validity of the blur minimum morphologic operator. When compared with the cubic facet second derivative zero-crossing edge operator, the results show that they have similar performance. The advantage of the blur-minimum edge operator is that it is less computationally complex than the facet edge operator.