An image analysis system that can differentiate between different black toners or inks non-destructively on printed text documents and images is currently under development at The London College of Printing. It is envisaged that the system will be able to find alterations in documents or images that are difficult to detect even by the most skilled expert document examiners using established forensic techniques. This paper describes the development of a nondestructive method that is intended to detect imperceptible fraudulent alterations to digital print samples. A digital image analysis system that incorporated a high-resolution low noise CCD monochrome camera with an optical system to enlarge images was used. Software that could obtain measurements of the relative optical reflectivity and sharpness characteristics of printed image areas from the raw image analysis data was developed. A single A4 sized paper sheet with a printed image that was produced using a combination of two different laser printers and an optical photocopier was illuminated using visible light. The results of subsequent image analysis measurements demonstrated it was possible to detect imperceptible alterations on the A4 sheet using this technique.
The objective of this investigation is to establish whether it is possible to produce a practical forensic tool that can identify the production sources of printed text from different digital print engines. The identification of print using an automated machine system is important because although expert observers can be employed for this task, there are cases when they make mistakes or do not possess the required knowledge. Therefore the development of an automated print identification system is under consideration. It is envisaged that the system will be useful in solving criminal cases involving the analysis of fraudulent replication of official documents, threatening letters and the counterfeiting of consumer products.
The methodology used in this investigation employed a digital image analysis system and specially developed software to measure the shape characteristics of text characters. The information about the shapes of the text characters can be stored in a database along with the corresponding data about the print engines that produced them. A database search engine can then be used to classify text characters of unknown origin. The paper will report on the methodology and techniques used in the investigation and the latest experimental results for the project.
A human expert observer can be employed to identify the production source of a print. The observer achieves this task by visual inspection of the print using a microscope. However, there are cases when the expert observer fails to identify correctly the production source. It is for this reason that the development of a method which can identify the production source is under consideration. This paper discusses the initial stages of the project which focuses on the development of a system that can classify prints from three different digital printing process. The system comprised an image analyzer that supplied image data from the print samples for initial analysis using a data pre- processing program and artificial neural networks which then used the pre-processed data to produce the classification models. The three different digital printing processes employed in this investigation were laser printing, optical photocopying and inkjet printing. Print samples were obtained from a range of laser printers,,optical photocopiers and inkjet printers. The prints used in the investigation were of a monochrome image of a square. The results show that the system is capable of classifying prints accurately for the range of printing machines and the image used in the trials.
An image analysis system that simulates human print quality perception is being developed at The London College of Printing. This paper reports on some of the interim results of this project. The image analysis system has been tested to see whether it could detect the degradation of printed text character images when they are photocopied. The variables measured were the size, reflectance intensity and reflectance intensity gradients of these images. The system has been tested by making measurements on text characters without any need for alignment of the text character to the camera using neural networks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.