Search results

The recent introduction of low‐cost vision sensors has greatly increased the range of applications for vision. Within the arena of automated assembly there are a number of tasks that vision is suited to and these are outlined. Also the idea of distributing vision throughout the assembly process together with networking via Ethernet is examined.

Outlines some of the areas in machine vision system solution which have seen the most significant advances as a result of technology enhancement and particularly the rapid development in semiconductor technology. Looks at the background of machine vision development and improvements brought about by modern technology, covering advances in vision algorithms, “warp engines” used in combination with an application specific integrated circuit [ASIC], improvements in human interface; and optical character recognition. Concludes that the trend now is for general purpose vision processing systems to provide greater capability, at greater throughput speed, without significantly increasing the cost of the system which means that they are now part of the original process design to inspect critical stages of manufacture.

This paper aims to propose a non-contact method using machine vision for measuring the surface roughness of a rotating workpiece at speeds of up to 4,000 rpm.

A commercial digital single-lens-reflex camera with high shutter speed and backlight was used to capture a silhouette of the rotating workpiece profile. The roughness profile was extracted at sub-pixel accuracy from the captured images using the moment invariant method of edge detection. The average (Ra), root-mean square (Rq) and peak-to-valley (Rt) roughness parameters were measured for ten different specimens at spindle speeds of up to 4,000 rpm. The roughness values measured using the proposed machine vision system were verified using the stylus profilometer.

The roughness values measured using the proposed method show high correlation (up to 0.997 for Ra) with those determined using the profilometer. The mean differences in Ra, Rq and Rt between the two methods were only 4.66, 3.29 and 3.70 per cent, respectively.

The proposed method has significant potential for application in the in-process roughness measurement and tool condition monitoring from workpiece profile signature during turning, thus, obviating the need to stop the machine.

The machine vision method combined with sub-pixel edge detection has not been applied to measure the roughness of a rotating workpiece.

Outlines the factors causing the automotive industry to increase machine vision application, reviews new developments in vision technology that are targeted at expanding and improving it use in the automotive industry, reports on an innovative application of vision guided robotics at DaimlerChrysler

Advances in the design of image processing software and in the development of cameras with on‐board processing are changing the face of machine vision. A group of suppliers is now producing vision systems targeted directly at end‐users in the assembly plant.

Manufacturers faced with small production runs often require multiple machine changeovers per shift. Vision control of machinery offers a cost‐effective solution to this problem. Manufacturers are able to introduce diverse products, randomly, to a process line during the same production run, using reasonably priced industrial electronic equipment incorporating vision technology. A vision controlled polyurethane dispensing machine has been designed, manufactured and commissioned to substantiate this theory. An image of a moat, recessed into a mould, is captured by means of a CCD camera, resulting in a dispensing path being transferred to a microprocessor. The analogue signal is converted to a digital signal that pre‐sets a path for the two‐axis motion controller, capable of performing interpolation, to follow. A polyurethane mixing machine receives the same digital signal which sets the dispensing rate and shot size. Polyurethane is dispensed into the moat to form a seal between the filter media and the air‐filter housing. A summary of the design, implementation and results of the project is outlined and described.

Based on the highlights of The Metropolitan Museum of Art's collection, the purpose of this paper is to examine the similarities and differences between the subject keywords tags assigned by the museum and those produced by three computer vision systems.

This paper uses computer vision tools to generate the data and the Getty Research Institute's Art and Architecture Thesaurus (AAT) to compare the subject keyword tags.

This paper finds that there are clear opportunities to use computer vision technologies to automatically generate tags that expand the terms used by the museum. This brings a new perspective to the collection that is different from the traditional art historical one. However, the study also surfaces challenges about the accuracy and lack of context within the computer vision results.

This finding has important implications on how these machine-generated tags complement the current taxonomies and vocabularies inputted in the collection database. In consequence, the museum needs to consider the selection process for choosing which computer vision system to apply to their collection. Furthermore, they also need to think critically about the kind of tags they wish to use, such as colors, materials or objects.

The study results add to the rapidly evolving field of computer vision within the art information context and provide recommendations of aspects to consider before selecting and implementing these technologies.