A system for forensic analysis of large image sets

Simske, Steven J.; Sturgill, Margaret; Everest, Paul; Guillory, George

doi:10.1109/wifs.2009.5386492

Cited by 8 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This continuous tone image is suitable for forensic analysis 5 , and can also be used to convey product branding information or carry a digital watermark payload. Finally, in the upper right portion of the medallion is a set of microtext and brand-specific logos and photos.…”

Section: Security Printingmentioning

confidence: 99%

Parallel processing considerations for image recognition tasks

Simske

2011

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Many image recognition tasks are well-suited to parallel processing. The most obvious example is that many imaging tasks require the analysis of multiple images. From this standpoint, then, parallel processing need be no more complicated than assigning individual images to individual processors. However, there are three less trivial categories of parallel processing that will be considered in this paper: parallel processing (1) by task; (2) by image region; and (3) by meta-algorithm. Parallel processing by task allows the assignment of multiple workflows --as diverse as optical character recognition [OCR], document classification and barcode reading --to parallel pipelines. This can substantially decrease time to completion for the document tasks. For this approach, each parallel pipeline is generally performing a different task. Parallel processing by image region allows a larger imaging task to be sub-divided into a set of parallel pipelines, each performing the same task but on a different data set. This type of image analysis is readily addressed by a map-reduce approach. Examples include document skew detection and multiple face detection and tracking. Finally, parallel processing by meta-algorithm allows different algorithms to be deployed on the same image simultaneously. This approach may result in improved accuracy. ABSTRACTMany image recognition tasks are well-suited to parallel processing. The most obvious example is that many imaging tasks require the analysis of multiple images. From this standpoint, then, parallel processing need be no more complicated than assigning individual images to individual processors. However, there are three less trivial categories of parallel processing that will be considered in this paper: parallel processing (1) by task; (2) by image region; and (3) by meta-algorithm. Parallel processing by task allows the assignment of multiple workflows-as diverse as optical character recognition [OCR], document classification and barcode reading-to parallel pipelines. This can substantially decrease time to completion for the document tasks. For this approach, each parallel pipeline is generally performing a different task. Parallel processing by image region allows a larger imaging task to be sub-divided into a set of parallel pipelines, each performing the same task but on a different data set. This type of image analysis is readily addressed by a map-reduce approach. Examples include document skew detection and multiple face detection and tracking. Finally, parallel processing by meta-algorithm allows different algorithms to be deployed on the same image simultaneously. This approach may result in improved accuracy.

show abstract

Section: Security Printingmentioning

confidence: 99%

Parallel processing considerations for image recognition tasks

Simske

2011

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…The second forensic system is software-based. Named the imagebased forensic system, or IBFS [20], it is an imaging system that typically uses a small set of pre-classified ("training") images for initial training, and thereafter adaptively classifies and aggregates images from multiple sources as they join the population to be classified. The system can also work without any training images whatsoever.…”

Section: Forensicsmentioning

confidence: 99%

“…We used a static color array for the purposes of deploying the IBFS as part of our testing [20]. The color tiles are arranged as in Figure 2.…”

Section: Test Sheetsmentioning

confidence: 99%

“…Similar capability was observed for LJ prints (Figure 10). Interestingly, however, the image-based forensic service (IBFS), initially described in [20], actually performs better when using the device with lower resolving capability -the 8200 scanner (Tables 3-11). The data in Tables 9 and 10 are also of interestthe lower authentication accuracy of the LJ prints is consistent with the lower accuracy of classification for the LJ prints when using the IBFS.…”

Section: Forensicsmentioning

confidence: 99%

“…This includes printer identification [2][21] [22], since these types of analyses can be performed across more than one unique print. As such, the so-called "IBFS" [20] is also an imaging inspection approach. Only when these approaches are applied to a large set of images simultaneously can they be called "forensic", inasmuch as batch inspection of large set of images structurally considers the image set (and not a unique image) as its forensic "atomic unit".…”

Section: What Is Inspection?mentioning

confidence: 99%

See 2 more Smart Citations

Document imaging security and forensics ecosystem considerations

Simske

Sturgill

Adams

et al. 2010

Proceedings of the 10th ACM Symposium on Document Engineering

Self Cite

View full text Add to dashboard Cite

Much of the focus in document security tends to be on the deterrent -the physical (printed, manufactured) item placed on a document, often used for routing in addition to security purposes. Hybrid (multiple) deterrents are not always reliably read by a single imaging device, and so a single device generally cannot simultaneously provide overall document security. We herein show how a relatively simple deterrent can be used in combination with multiple imaging devices to provide document security. In this paper, we show how these devices can be used to classify the printing technology used, a subject of importance for counterfeiter identification as well as printer quality control. Forensic-level imaging is also useful in preventing repudiation and forging, while mobile and/or simple scanning can be used to prevent tampering -propitiously in addition to providing useful, non-security related, capabilities such as document routing (track and trace) and workflow association.

show abstract

Domain Areas: Where are These Relevant?

Simske¹

2013

Meta‐Algorithmics

View full text Add to dashboard Cite

A system for forensic analysis of large image sets

Cited by 8 publications

References 4 publications

Parallel processing considerations for image recognition tasks

Parallel processing considerations for image recognition tasks

Document imaging security and forensics ecosystem considerations

Domain Areas: Where are These Relevant?

Contact Info

Product

Resources

About