Crime Scene Investigation: Photographic Portfolio

A former forensic crime lab technician turned professional photographer named Angela Strassheim has used her fascination with crime scenes to create a photographic portfolio.  For the portfolio, she visited dozens of former crime scenes and photographed them using a combination of low light, long exposure times, black and white film, and a chemical reagent used to highlight blood stains.  The results are fascinating and you can see them here.

Image Forensics: Bad "Photoshopped" Mad Men cover on Rolling Stones

The title of this post says it all - the writers at Jezebel (a celebrity news for women) wrote about it first. See for yourself.
Enjoy!

Image Forensics: Seeing is NOT believing

Spectrum Magazine (by the Institute of Electrical and Electronic Engineers, or IEEE, USA) has an excellent overview article on detecting tampering in digital photographs by Professor Hany Farid (Dartmouth College, USA).

Enjoy!

Photography: Automatic panning device for gigabit images

Engadget profiled the GigaPan Epic some time ago. The Epic is a robotic camera mount that holds your point-and-shoot digital camera and then automatically pans the visual scene, taking picture after picture (up to thousands, according to the manufacturer). Software is included that then automatically stiches the individual images into a single digital panoramic image. Very cool. The inventor used it at the recent inauguration to capture a panorama of the mall. Many more images can be found at a community page devoted to these images. Here is a link to the product page with more details (and the sales price).

Why would anyone need so many pixels in an image? Over the Christmas holidays, the pundits were telling us that no one needs more than, say, 6 megapixels in a camera. Two examples where more pixels are needed include when one needs to zoom in to get small details or when one requires very wide angle shots with good resolution (i.e. which is hard to do with a fisheye lens or a dome mirror).

A potential forensics application is crime scene photography, thanks not only to its functionality, but also its modest cost and compatibility with a wide range of digital cameras.

Enjoy!

Image Recognition: Facial recognition feature in iPhoto

I installed Apple's iPhoto '09 last night to test how the face recognition feature (called "Faces", of all things) worked. There are nearly 4,000 photos in my personal library, so I left it running overnight while it went through the database and, I assume, ran its face detection algorithm. I then decided to run a test. I manually identified the same person in two different photographs and had iPhoto go out and locate matches, which is its next step in its learning process - the user next needs to confirm or not confirm the identity of each one of the identifications it produces.

So how did it do at the end of this first step? Surprisingly well is the answer, particularly for a consumer-grade product. The raw numbers were 72 correct and 16 incorrect at this first step, but that doesn't tell the whole story. In the instances where it was incorrect, all but three were confused with family members (which admittedly is the most likely confusion outcome since for all pictures with faces in the database, generally at least one is a family member). In addition, it also correctly chose pictures where only one eye was visible, where the age was significantly different, and where there were different emotions clearly visible on the faces. It also did not seem to have a problem with different compression levels, low resolution (including one that was very granulated), face paint, under-exposure, black-and-white, scans (of printed pictures), and color. Finally, it made only one error out of 86 pictures in correctly detecting and locating the face.

So, even though this was not a properly constructed test, the results were more than impressive enough to warrant looking at it further for professional use in some applications.

PS. This is not a product review, per se, but I should say that my experience with this just-released version was not all positive. Namely, it was horribly slow during the step where one has to select a picture, go into the Faces mode, and then type in the subject's name. Each entry took two to three minutes to accomplish, so I saw the "spinning beach ball" that Mac OS-X uses to let you know it is busy quite a lot. Hopefully this bug will get corrected and patched quickly.

Image Recognition: Facial and license plate recognition news items

There are two on-line news articles related to image recognition that I would like to bring to your attention.

The first news article is about law enforcement in Tacoma, Washington, USA using a facial recognition package to match 16 years worth of prisoner mug shots with pictures taken by ATM (Automated Teller Machines) in a forgery and theft investigation to generate the lead needed to solve the case.

The second news article is from New Orleans, Louisiana, USA where local law enforcement used a license-plate recognition system to make 20 arrests and recover 23 stolen vehicles and license plates in a 25 day period.

The common thread here is, of course, automatic image recognition. These software algorithms have come a long way in the last decade. However, one should understand that the conditions are partially or completely controlled in both of these applications - i.e. distance, lighting, exposure, aspect (turned toward the camera), and (possibly) compression all fall within acceptable boundaries. In addition, with the license plate recognition problem, the character set and fonts were known in advance. The controlled conditions and a priori knowledge significantly increase the accuracy of the results tremendously and the chances of a successful investigation and prosecution.

(Hat-tip to JUSTNETNews, USA - I highly recommend this free service of the National Law Enforcement and Corrections Technology Center, or NLECTC, which is part of the National Institute of Justice, USA)

Photoshop: Most blatant Photoshopped covers

I met a graphics artist today whose job is to "Photoshop" pictures for advertisements. We got to comparing stories and she mentioned an incident involving Kate Winslet, the actress, where her legs were slimmed a bit too drastically and caused a stir. Well, before long we were pulling out my MacBook and Googling for that and other instances of "Photoshopped" covers. Here is the best link we found.

Enjoy!

Photography: Year's top ten tips and tutorials

Digital Photography School has an excellent roundup of ten tips and tutorials for this year.

Enjoy!

Image Forensics: Was North Korean leader's photograph tampered with?

A photograph was released by the North Korean government last week that purported to show Kim Jong-il, their national leader, reviewing military troops - and looking suspiciously healthy after reportedly suffering a stroke. The Times Online and BBC (both center-left UK newspapers) report on the discrepancies in the photograph, including mismatching shadows and a missing black line.

Image Recognition: Military requirements push technology forward

The Strategy Page has an article about how the proliferation of video on the battlefield (e.g. from surveillance cameras and even night vision goggles) is driving technology development. Initially, it was the UK (United Kingdom) that drove image recognition technology with its massive deployment of CCTV in public spaces (e.g. train stations, airports, city centers, and shopping malls). Now, it is the military.

The benefit from computer-assistance in analyzing video comes from the following:

1. Volume (i.e. the sheer number of cameras and, hence, images to be monitored and/or analyzed)
2. Concentration (i.e. the human visual system loses the ability to concentrate effectively on images after about 20 minutes of continuous viewing)
3. Memory (i.e. computers can track and, possibly, predict more things simultaneously than a human can because, generally speaking, computers are not nearly as attention and working-memory limited in the short-term as humans and far outstrip us in their ability to recall video sequences over the long term - they can just play back the video recording off of their hard disks)
   

The article claims that the abilities of computer systems to recognize patterns is rapidly improving and approaching that of humans - that is no small feat as humans are simply amazing in their ability to perform real-time pattern analysis.

One intriguing point made in the article is that the current conflicts are generating a lot of real-world recordings of "bad behavior" that can be used to train and test new pattern analysis and prediction algorithms - training data like this is like gold to us signal processing types!

Enjoy!

Image Forensics: More on tamper detection

Steve Eddins (Mathworks Inc., USA), writing on his company-sponsored blog on image processing, has an excellent post regarding an article by Professor Henry Farid in the June 2008 edition of Scientific American (USA, center-left, scientific magazine). The article is primarily about tamper detection or, in other words, spotting retouching or "photoshopping" of photographs.

Image Forensics: How to spot photo retouching

Slate (US, center-left online magazine) has an article (Were the Dove ads retouched? How to spot Photoshop chicanery) on some of the techniques used in identifying if a image has been retouched. In a forensic examination of evidence, this procedure is known as tamper detection. It should be noted that the author, Jacob Leibenluft, reached out to several experts while researching the topic, including George Reis of Imaging Forensics.

Enjoy!

Image Recognition: "Computer, where did I lay the keys?"

The Daily Mail (UK tabloid newspaper) has a gadget article about Smart Goggles, a human wearable image recognition and recall system built into a set of glasses. The user trains the system by focusing its built-in camera on a series of objects, such as car keys, CDs, etc. while speaking the appropriate name of the object. Once trained sufficiently, the system automatically recognizes images it sees and stores the information for later retrieval, again by spoken word. The processor (computer) is worn on the user's back. The system was developed by Professor Kuniyoshi and colleagues at the University of Tokyo.

It isn't much of a stretch to see how these same concepts could be built into other video applications, such as CCTV systems, for instance. Don't be surprised if they don't work this into a future episode of CSI or similar television show (or the next James Bond movie, for that matter).

Photography: 13 things to teach a child about digital photography

I probably am not the only parent who has, upon purchase of a newer digital camera, turned around and given the older model to the children and said something amounting to "Here,  go take some photos with this and come back when its full."  This, of course, leads to some impromptu lessons in photography for the children who are interested.  So, with that lead in, here is a link to an excellent blog posting that summarizes those lessons for you.

Photography: Google Earth

Technology Review (a technical magazine published by MIT) has an excellent article on the technology behind Google Earth - the satellites, the airplanes, the corrections (filtering), elevation mapping, data streaming, et al.

Photography: Cleaning digital camera sensors

For the amateur and professional photographers out there interested in cleaning their digital camera sensors, I highly recommend checking out episode 90 of the Shutters Inc podcast by Shelton Muller and Bruce Williams (who also does the excellent Sine Language and Building the Pod podcasts).  Mr. Williams reports on his own DIY (Do It Yourself) experience cleaning his camera.  During all this, he mentions a very informative website, which I will give the link to - Cleaning Digital Cameras.  There is some follow up information on cleaning in episode 91 also.

Photography: What can you do with a 1.4 BILLION pixel camera?

Hunt for killer asteroids, that is what!  It is going to be part of the Panoramic Survey Telescope and Rapid Response System (Pan-STARRS) in Maui, Hawaii, USA.  By the way, it took sixty digital image sensor chips to construct the imager.  A news article can be found at New Scientist.

Optics: Liquid camera lens, no moving parts, now with zoom

New Scientist has an article on a different type of camera lens - it isn't made of glass or plastic, but instead uses the boundary of an oily liquid and water, which can be shaped by an electrical voltage to different amounts of curvature. Liquid lenses are used in some mass market products. The twist here is the ability to zoom. This latest research development still has some issues that need to be worked out if it is to supplant existing commercial technologies for the mass market (i.e. cheap, plastic lenses), but the principle seems to be sound. That bodes well for it finding at least a niche problem to solve.

Forensic Photography: Retrieving color of ancient textiles

Eurekalert summarizes work by Chirstel Baldia and Kathryn Jakes (both at Ohio State University) that used forensic photography techniques to determine the original color of textiles recovered from Ohio's Seip burial mounds which are about 1600 years old.

Ultrathin folded telephoto lens

Engineers at the University of California San Diego have created a folded lens by machining reflective surfaces into a optical crystal. this technology has the potential to shrink lens assemblies, which would be beneficial to lots of devices, such as cameras and night vision gear. However, this is still early stage research and hurdles remain - such as its inherent narrow depth of field. That being said, there are ways around that problem that might work for selected applications where thickness is more important than length (where I imagine that additional lenses with different focal lengths could be positioned on a rotating disk or similar arrangement to be employed as needs changed) or post-processing power consumption.

The work has been published in Applied Optics (February 1st, 2007)

(Hat tip and image source: PhysOrg)