Abb Schweiz Ag

Abb Oy

Abb Inc.

Tommi Huotilainen

Ake Arvid Hellstrom

Antti Saarela

Seppo Riikonen

Myron Laster

A real-time, full web image processing method for analyzing formation in a web is described, the web is transported in a moving direction during a web manufacturing process, the method including the steps of acquiring a two-dimensional original image Pof the web, the image being representable as a digital image representable by a plurality of pixel values Pwith i&#x2208;{1; . . . ; I}, j&#x2208;{1; . . . ; J}; and producing a plurality of P processed images Pwith p&#x2208;{1; . . . ; P}, each of the processed images being representable by pixel values Pwith m&#x2208;{1; . . . ; M}, n&#x2208;{1; . . . ; N}, the processed images being obtained by spatial bandpass filtering of the original image, wherein a spatial different bandpass filter is used for obtaining each of the processed.

Real-time, full web image processing method and system for web manufacturing supervision

A method for detection of distinctive features in a web being transported in a moving direction during a web manufacturing process including the steps of: a) acquiring an image of the web, including a plurality of pixels P i with i&#x3f5;{1; . . . ; p}, b) identifying a plurality of regions of interest each corresponding to a distinctive feature by processing the plurality of pixels P i by: c) selecting a local pixel unit including a subset P j with j&#x3f5;S&#x2282;{1; . . . ; p} of the plurality of pixels, the subset i) being representative of a subregion of the digital image, and ii) different from previously selected local pixel units, d) deciding whether the local pixel unit is of interest or not, i) if the local pixel unit is of interest, 1) identifying whether the local pixel unit is located within an impact area A k of a previously identified region of interest R k with k&#x3f5;A&#x2286;{1; . . . ; n}, 2) if the local pixel unit is not located within any impact area A k of any previously identified region of interest R k with k&#x3f5;A&#x2286;{1; . . . ; n}, or no regions of interest have previously been identified, (a) identifying the local pixel unit as a new region R n+1 of interest; (b) initializing an impact area A n+1 for the new region R n+1 of interest; (c) incrementing a counter n representative of the number of previously identified regions of interest; if the local pixel unit is located within an impact area A k 0 of a previously identified region of interest R k 0, (a) merging, depending on a merging condition, the local pixel unit with the previously identified region of interest R k 0, (b) if the merging condition is fulfilled, updating the impact area A k 0 of the region of interest R k 0; ii) preferably, if the local pixel unit is not of interest, identifying whether the local pixel unit is located within an impact area A k of a previously identified region of interest R k with k&#x3f5;{1; . . . ; n},if the local pixel unit is located within an impact area A k 0 of a previously identified region of interest R k 0, updating the impact area A k 0; e) repeating steps b) through d) until at least essentially all pixels of the image have been processed.

There is described a method and apparatus for tracking the location of web features through a converting process, one application of which can involve tracking paper defects from a paper machine as detected by a camera system, to a winder where the sheet is wound to rolls so that the web defects can be repaired in the winder before making the rolls. The method to track web features is based on pattern identification of inherent sheet variability or defects. The apparatus involves two or more sheet property or defect monitoring web sensors arranged at the same cross directional location at different stages of the converting operation, augmented by tachometers and/or roll diameter sensors. A full automation system for drive control on the winder based on this information is preferably added to make maximum advantage of this information.

Accurate tracking of web features through converting processes

A new method for processing image data in order to detect abnormalities in a web is provided. The web is monitored by at least one camera, whereby an image comprising of plurality of pixels is generated. The data of the image is stored in a memory. Image data is filtered by a processor by creating a filtered image data by weighting the image data and at least one of earlier image data and earlier filtered image data; and combining the weighted image data and at least one of the weighted earlier image data and the weighted earlier filtered image data; and controlling filtering by at least one nonlinear algorithm; and thresholding the created filtered image data.

Growing community of inventors

Helsinki, Finland

Tommi Huotilainen