• Product  
• Developer 
• Cost (USD) 
• Open source 
• Software license  
• OS 
• Continuous 
• Industries, Uses and Applications

I thought that the type of license, open/closed source, OS, etc aren’t very interesting, while some more important, in my view, data should be added. Based on the inspection of the vendors’ sites, I tried to answer the following questions.

What is the price? In the absence of that information, I put $$$$ indicating that the price might be in the thousands.

Is there a free version available for download? Companies with $$$$ usually don’t have that.

Does the site provide examples of how the software has been used for image analysis? Very often, surprisingly little is provided.

Does the site reveal the methods/algorithms behind the software? Commercial vendors say nothing. Open source certainly qualifies for Yes in this category but most of the time the source is all you get. The actual math, algorithms, errors, etc are ignored.

To see the new table follow this link: Image analysis software.

The images below came from the same source and show the results of analysis of the first image by means of their algorithm (right) vs. Pixcavator’s (left). The comparison is unfavorable.

I ran Pixcavator myself with the first image, high intensity. I had to move the maximal contrast slider and in about 5 seconds I had a satisfactory result, below.

The low intensity image is here.

A new paper that uses Pixcavator:

Down-regulation of CXCR4 and CD62L in Chronic Lymphocytic Leukemia Cells Is Triggered by B-Cell Receptor Ligation and Associated with Progressive Disease [1] by Amalia Vlad, Pierre-Antoine Deglesne, Re´mi Letestu, Ste´phane Saint-Georges, Nathalie Chevallier, Fanny Baran-Marszak, Nadine Varin-Blank, Florence Ajchenbaum-Cymbalista, and Dominique Ledoux (Cancer Research 69, 6387, August 15, 2009).

From the paper:

“Progressive cases of B-cell chronic lymphocytic leukemia (CLL) are frequently associated with lymphadenopathy, highlighting a critical role for signals emanating from the tumor environment in the accumulation of malignant B cells.”

“BCR-stimulated and unstimulated fluorescent cells were mixed in RPMI 1640/10% FCS and added together onto the endothelial cell layer. After incubation for 2 h at 37jC, the nonadherent CLL cells were washed off. Remaining adherent cells were fixed, and 10 fields from duplicate chamber slides (average of 500 cells/field) were photographed under fluorescent microscope. Red and green fluorescence were separately quantified using the Pixcavator IA 3.3 software (Intelligence Perception Co.).”

Take a look at other papers that use Pixcavator.

The guy does not seem to realize though that Microsoft released its own similarity search a few months before. I am not judging because I missed it myself when it came out. It would be interesting to test and see which one is better (or not as bad). One point in favor of Microsoft is that Google didn’t index all images.

UPDATE: Another good revew at Rich Marr’s Tech Blog.

The software has a huge multitude of tools for image processing (and, of course, photo manipulation). There is no point in listing them here. The “extended” version also has a few fun features like auto-blending or content-aware scaling.

However, its image analysis capabilities are very limited. After searching for a while, just these two below all I found:

Use selection tools to define and calculate distance, perimeter, area, and many other measurements. Record data points in a Measurement Log and then export the data, including histogram data, to a spreadsheet for further quantitative analysis.

Easily and accurately tally objects or features in scientific images with the Count tool, which eliminates the need to perform manual calculations or rely on visual assessments of changes from image to image. Save even more time by performing multiple counts in a single image. Use separate colors for each count and save your counts in the file.

Adobe Photoshop CS4 Extended is priced at $999.

This program demonstrates some capabilities of Numenta’s Hierarchical Temporal Memory (HTM) technology applied to visual object recognition. .. The HTM network contained in this demo has been trained to recognize four types of objects: cell phones, sailboats, cows, and rubber ducks.

Every image is given four ratings. Each represents how much the image resembles one of the four types.

As you can see, the goal is modest and there are no unsubstantiated claims of how this is ready to be applied in real life (and don’t get me started on academic publications!). This is refreshing. The program is also fun to play with. You can load your own images, you can add noise, blur etc to the images and see the effect on the recognition. The recognition results are often good and when they aren’t, it’s still interesting.

For serious purposes, it is unclear where this is going though.

It’s fine with me that there are only four categories – just one would be enough to test the concept. It does not bother me when a face is rated high in the cow category and another face high in the duck category. My main complaint is the instability of recognition under image transformations. For example, after turning “sailboat” a few degrees it became “cell phone”. A few degrees more and it becomes mixed – half “cow” (first image below). Adding noise, occlusion, etc has similar effect (second image).

Certainly, one does not expect rotations to affect image recognition. Meanwhile, a mixed recognition is a failed recognition and should be presented as such.

I am certainly biased here. I don’t believe in “build[ing] machines that work on principles used by the brain”. I don’t believe in trying to imitate brain and I’ve written a few times about that. Traditionally, a scientist tries to understand nature by observing it, analyzing it, etc. Instead, it is suggested to try to understand nature by first understanding how the brain understands it? Seems like a roundabout to me, bordering on a vicious circle. I also have serious reservations about the use of machine learning in computer vision.

Annoying bug: every time I start it, the program would turn on my webcam and it would keep it on even after I shut it down.

Milabra claims that it can categorize images, “from puppies to porn”:

…when searching through a library of images for dogs, Milabra doesn’t need to constantly compare each image with its database of known ‘dog’ images – instead, it can look for traits that it has learned to associate with “doggyness”…

The two examples in the demo are “beach” and “dog”. You upload an image with people on the beach, click “Search” and you get a page of beach photos… Wait, you don’t get to upload anything – this is just a video! So, there is no way to test their claims. Unfortunately, this is not unusual in this area and in computer vision in general.

If your software can recognize a puppy in an image (95% of the time as you claim), it should be easy for you to demonstrate this ability. Create a little web application (or desktop, I don’t care) that allows me to upload my own image which is then identified as “puppy” (or “tree”, or “street”, I don’t care). There is no such program. Why not? The answer is obvious.

In response to some skepticism, this is what one of the founders wrote:

…if you think that this cannot be done, then you are completely clueless: object classifiers have been made for more than 10 years now at leading CS labs around the world.

That reminds me of the episode of Seinfeld when Kramer decides to build levels in his apartment:

KRAMER: It’s a simple job. Why, you don’t think I can?

JERRY: Oh, no. It’s not that I don’t think you can. I know that you can’t, and I’m positive that you won’t.

This is Millabra’s team:

• MBA
• MS in Biological Engineering and PhD in neuroscience
• MS in Computer Science and Ph.D. in Biophysics
• Professional Project Manager
• Expert in computer networking, user interface design

JERRY: I don’t see it happening.

And what about TechCrunch? Same story again and again since I started to keep track a couple of years ago: they publish an enthusiastic report about a company doing image analysis/search/recognition, and then silence. The company slips into obscurity and there is no follow-up, nothing. These people never learn…

The people who do seem to learn, slowly, are the investors: Riya (like.com) $20 million or more, Polar Rose $5 million, Milabra $1.4 million. Or maybe this is just the effect of the economic downturn?

I tried its Facebook application. I uploaded a few standard images and a few test images of my own and ran Gazopa. Some of the matches were awful while others were sort of meaningful. See for yourselves. The first match is displayed under the target image.

Gazopa also found a cropped copy of the “cameraman”, but not a rotated copy. The inability to handle rotations is a common problem with almost all visual search engines. Pixcavator Image Search can handle rotations with ease (read about it here or wait for the last version – to be released soon).

As far as the underlying technology, the site says that “GazoPa enables users to search for a similar image from characteristics such as a color or a shape extracted from an image itself” and nothing more. So, even what they consider similar is unknown.