This page contains a Flash digital edition of a book.
Exclusive Int

Atten ontodetail: AutomaAut

Attent efficiency,


ndustry4.0.0, revo

morean year

years.Aſte cam

0, thefo volution,has

andmoreove ſtercomp

mputersandrob signal arege format

forhu anint position; at

ar getting efficient

fo human nterac human

utomated inspection softwar ut

ally st al

asbeentalalke abou ver thelast few obo


productionbecamemoreefficient,but noweve yoneis talkingabngabo conne

amealonginthe20thcentcenturyfa ow veryo

co nectingandcommunicatingat ngwith eac

achotherviatheInternet, sending alsandinfo

anroletoamoresupervisory at thesame me


ngusedtoqu ke andmore ntproductionspeeds.

metime,manufac quickeran

Throughout the printing and packaging industry,machine vision and inspection cameras are used to spot inaccuracies, defefects and poor quality print. OCR (Optical Character Recognition) technology from ABBYY can be implemented intomachine vision systems; it extracts text fromprinted

factory bu

boutmachines ng

ationwithout theneed action.This reduces the


kedabout fe

ntiion to detail: atedinspectionsoftware canincrease

y,but is itit reallyas cleveras it sounds? fourthindustrial


producer wants tomake sure the right label is on the right product and the text is readable and correct. You have standard product infoformation but there’s also individual infoformation, such as the batch number or expiry date, whichmight be unique. If something is wrong this could be damaging to the brand.”


Machine vision and quality assurance has immense value in the production industry and it is important to help improve

efficiency. Some systems can complete up to several thousand inspections everyminute. ABBYY works directly with system

manufafacturers to foformpartnerships and incorporate its OCR technology at the last n the line fofor final checking aftfter inspection has taken place.

camera point o


The printed product passes in front of the camera and an image is taken; this is sent

nterview-M achine Vi


WebInspection eb

process happens fafaster an “Printing and OCR tech

nology go hand-in- d ismore accurate.

hand,”Weber continues. “An excellent OCR systemhas to be able to recognise not only ‘easy’but, ‘difficult texts’ too. ‘Easy texts’are simply black text on white background, but when colours, images or objects are included it becomes slightlymore difficult to interpret it. Labels and packaging come under ‘difficult texts’. The systemneeds to decide what is important to read and what is not. Image are needed to get

good results and we offe pre-processing functions

ffer a broad set of

processing options; it’s better to prepare the image befofore the text is read, and therefofore you’ll end up with a higher quality result. “It’s not only the print and packaging and checking but you can actually acquire infoformation and send it to anothermachine; today’smachines equipped with highly complex computer programmes can act like humans, they can read text, interpret it and apply actions on how to proceed.”

LESS NEED FOR HUMAN OPER TION Weber also says that productionwill only get quicker in the future, and that human interventionwill not be required asmuch. However,r, she notes that softftware has to be programmedwith the correct data in the first place in order fofor it to operate on its own.



September 2016

Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40