Matching, Recognition, Results

The Best-Performing Address Matching and Recognition Solutions for
Postal and Logistics Companies

Syslore DROIDI

Syslore DROIDI (Deep learning Region of Interest Detector Instrument) is the smartest Region of Interest block detector in the industry

Product Overview

In postal business, Region of Interest (ROI) is defined as an area in a mail piece image that contains or depicts some specific kind of information. Typically, the region of interest is the recipient address, but there are all kinds of interesting regions, such as stamps, logos, bar codes, special symbols, phone numbers and sender addresses etc., which may be interesting in terms of revenue protection, customs clearance or some special delivery options. Syslore DROIDI is capable of detecting unlimited number of different ROI areas from different mail pieces. 

DROIDI is a deep learning based system designed for detecting ROI areas automatically from an image in 40-100 milliseconds. The latest technological breakthrough in artificial intelligence research is deep learning. It is brain inspired artificial neural network and consists of multiple network layers, which allows to represent functions of increased complexity by combining learned concepts. Further, Convolutional Neural Networks (CNNs), a widespread deep learning model, are employed for image content interpretation for example to extract letters and digits.

Commercially Proven Technology

Syslore DROIDI is part of Syslore OCR and used in several high volume installations world wide, both in national and private postal companies. Cloud or on-premise, it is your choice. Syslore DROIDI can be implemented on-premises, on a third party hosting or in a cloud as a service.

Product Benefits

DROIDI is a system for Region-Of-Interest detection that is:

  • Data-driven: All modeling is based on generalizations of training data using applied machine learning techniques.
  • Effective: Depending on the dataset and image quality, the detection accuracy for multiple area can exceed 95%.
  • Efficient: Depending on the resolution of the images, a decision takes on average 20-40 milliseconds.
  • Versatile: Can deal with hand-written and machine printed data.
  • Flexible: All the algorithms and models are easily replaceable and tailorable.

DROIDI in a Nutshell

Resolving the address text in a mail-piece image has to be done in two phases. First, you must locate the area where the address block is, and then pass that area into an optical character recognition tool that converts the area to machine readable text. You cannot usually pass the whole of the mail-piece to optical character recognition as it usually takes too long, and, more importantly, you lose the important location information with which to distinguish the recipient's address from the sender's address. In mail sorting, confusing those two is counter-productive and thus expensive.

Candidate Areas

Finding the address block in a letter with a few simple rules is easy: apply some smart binarization that filters out non-relevant smears and logos, find clusters of connected components, i.e., blobs, of a suitable size, ignore the top x % of the mail-piece (unless dealing with a flat), in case of multiple areas favor the lower one or the one closest to the centre, etc. Depending on the mail-flow, a set of simple rules might recognize up to 70 percent of the address blocks, and tweaking it some more, you might get to 80 percent. However, for a mail-sorting system that is not good enough. Furthermore, the layout of mail-pieces varies from country to country, which means the manual rules have to be adjusted for each deployment. Manual work is expensive and it does not generalize very well.

Syslore approaches the problem of locating the address block, or region-of-interest in postal lingo, from deep learning angle. We train a deep learning system with a set of sample images. The system generalizes the training samples into a model. Syslore DROIDI (an acronym for Deep-learning Region-Of-Interest Detection Instrument) is fundamentally a probabilistic system. There are many phases and mechanisms in the process, but the essential decision boils down to this: given this kind of mail-piece, where is the desired field likeliest to be.

This parcel image depicts a mail-piece from the trial data set, where Syslore DROIDI has found several ROI areas. Real life application is to find and recognise data fields from CN22 and CN23 labels of international consignments for customs.

DROIDI employs three different effectiveness metrics: precision (or positive predictive value), recall (or sensitivity) and F1-score. Here, they are used to measure area, that is, pixels with respect to the minimal rectangle encompassing the address block. A 100% precision means that the result contains exactly the address text and no additional barcodes, customer codes or any other non-address text or blob. A 100% recall means the result contains all the required address pixels and we miss none. Obviously, these two have a trade-off: we get 100% recall by returning the whole letter image, but the precision would be very low. By returning just one correct pixel we obtain 100% precision, but a very low recall. For system comparisons, we need a single evaluation measure. To this end, we combine precision and recall into F1-score, which is just the harmonic mean of the two. Unlike normal average, the harmonic mean is small if either of its components is small.