FEATURE Machine vision
An incredible volume of goods crosses international borders every day. Hans Jongebloed, Innovation Manager at Prime Vision, looks at how artificial intelligence can help ensure cross-border efficiency
I
nternational trade presents an enormous security issue. With such high volumes of parcels entering a
scan or search them for prohibited items. Holding up every international order to conduct these checks is not feasible, so many nations are switching to a pre-arrival model. To this end, the European Union (EU) is implementing its Import Control System 2 (ICS2), which requires traders to send data to customs before a parcel arrives in the EU. The new regulations aim to adequately
of goods between countries. If a parcel is sent to the EU without data submitted beforehand, it will be returned to the sender.
Sellers submitting data Putting data on parcels via labels and tables is nothing new to international sellers, but submitting it to the right place prior to arrival is though. Traders must provide data regarding the receiver and sender of the parcel, including name and contact details and a short description of what the package contains, along with a Harmonised
every product and the material it is made of. This is particularly useful for labelling potentially hazardous items, like those with lithium-ion batteries. The weight, number of objects and the price per item are also needed, as well as the country of origin. For larger parcels even more data is required. Clearly this is a lot to process, even for a smaller business. Submitting this information manually via data entry can be extremely time consuming and costly.
An intelligent approach Ultimately, the optimal approach is to digitise data gathered from parcel labels as they pass through the sorting process. A camera placed above a conveyor or tabletop, equipped with optical character reading (OCR) technology can scan each label, collecting individual parcel data and
12 May 2024 | Automation
automatically transforming it into a pre- arrival submission, ready to be forwarded to postal services or customs. However, before implementation, OCR and parcels to train the AI models that power it. With enough examples, AI can not only decipher parcel information, but reconstruct damaged labels and reduce no reads. This doesn’t just apply to machine printed labels – AI can also read handwriting and turn it into digital data. In all cases, the OCR system is directly integrated with the customer’s existing IT or warehouse management system, providing seamless sharing of information and easy generation of pre-arrival submissions.
For high-volume operations, companies with small administration capacity or those handling parcels coming from varied departments and suppliers, this is a highly manual data entry.
A standardised solution Until recently, OCR systems were the preserve of businesses dealing with high parcel volumes. In fact, many early implementations were more akin to research and development projects, with
large investment required to train the AI and achieve a suitable solution. out-the-box OCR system at a competitive support global e-commerce companies and national postal services, standardised highly-trained AI models that can quickly of customer operations. Consequently, very little development work is required, speeding up implementation and reducing costs. Rather than remaining the preserve of the big players, OCR is now accessible and economic for logistics operations of all shapes and sizes.
Abreast of regulation Managing the risks of free trade is an ongoing process for nations and their customs authorities. Measures similar such as the US, and global adoption is set to grow. However, by harnessing OCR technology with the expert guidance of sellers can seamlessly meet the latest customs data requirements and ensure that everything is properly declared.
automationmagazine.co.uk
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 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102
