Archive for the ‘Image Processing’ Category

STScI’s Engineering and Technology Colloquia

Tuesday, April 2nd, 2013

STScI’s Engineering and Technology Colloquia Series Webcasts by Bruce Berriman.

From the post:

Last week, I wrote a post about Michelle Borkin’s presentation on Astronomical Medicine and Beyond, part of the Space Telescope Science Institute’s (STScI) Engineering and Technology Colloquia Series. STScI archives and posts on-line all the presentations in this series. The talks go back to 2008 (with one earlier one dating to 2001), are generally given monthly or quarterly, and represent a rich source of information on many aspects of engineering and technology. The archive includes, where available, abstracts, Power Point Slides, videos for download, and for the more recent presentations, webcasts.

Definitely a astronomy/space flavor but also includes:

Scientific Data Visualization by Adam Bly (Visualizing.org, Seed Media Group).

Knowledge Retention & Transfer: What You Need to Know by Jay Liebowitz (UMUC).

Fast Parallel Processing Using GPUs for Accelerating Image Processing by Tom Reed (Nvidia Corporation).

Every field is struggling with the same data/knowledge issues, often using different terminologies or examples.

We can all struggle separately or we can learn from others.

Which approach do you use?

Posted in Astroinformatics, GPU, Image Processing, Knowledge Management, Visualization | No Comments »

A Glance at Information-Geometric Signal Processing

Thursday, October 18th, 2012

A Glance at Information-Geometric Signal Processing by Frank Nielsen.

Slides from the MAHI workship (Methodological Aspects of Hyperspectral Imaging)

From the workshop homepage:

The scope of the MAHI workshop is to explore new pathways that can potentially lead to breakthroughs in the extraction of the informative content of hyperspectral images. It will bring together researchers involved in hyperspectral image processing and in various innovative aspects of data processing.

Images, their informational content and the tools to analyze them have semantics too.

Posted in Image Processing, Image Recognition, Semantics | No Comments »

Visual Clues: A Brain “feature,” not a “bug”

Saturday, September 29th, 2012

You will read in When Your Eyes Tell Your Hands What to Think: You’re Far Less in Control of Your Brain Than You Think that:

You’ve probably never given much thought to the fact that picking up your cup of morning coffee presents your brain with a set of complex decisions. You need to decide how to aim your hand, grasp the handle and raise the cup to your mouth, all without spilling the contents on your lap.

A new Northwestern University study shows that, not only does your brain handle such complex decisions for you, it also hides information from you about how those decisions are made.

“Our study gives a salient example,” said Yangqing ‘Lucie’ Xu, lead author of the study and a doctoral candidate in psychology at Northwestern. “When you pick up an object, your brain automatically decides how to control your muscles based on what your eyes provide about the object’s shape. When you pick up a mug by the handle with your right hand, you need to add a clockwise twist to your grip to compensate for the extra weight that you see on the left side of the mug.

“We showed that the use of this visual information is so powerful and automatic that we cannot turn it off. When people see an object weighted in one direction, they actually can’t help but ‘feel’ the weight in that direction, even when they know that we’re tricking them,” Xu said. (emphasis added)

I never quite trusted my brain and now I have proof that it is untrustworthy. Hiding stuff indeed! ;-)

But that’s the trick of subject identification/identity isn’t it?

That our brains “recognize” all manner of subjects without any effort on our part.

Another part of the effortless features of our brains. But it hides the information we need to integrate information stores from ourselves and others.

Or rather, making it more work than we are usually willing to devote to digging it out.

When called upon to be “explicit” about subject identification, or even worse, to imagine how other people identify subjects, we prefer to stay at home consuming passive entertainment.

Two quick points:

First, need to think about how to incorporate this “feature” into delivery interfaces for users.

Second, what subjects would users pay others to mine/collate/identify for them? (Delivery being a separate issue.)

Posted in Identification, Identifiers, Image Processing, Image Recognition, Marketing, Subject Identifiers, Subject Identity | No Comments »

“What Makes Paris Look Like Paris?”

Saturday, September 1st, 2012

“What Makes Paris Look Like Paris?” by Erwin Gianchandani.

From the post:

We all identify cities by certain attributes, such as building architecture, street signage, even the lamp posts and parking meters dotting the sidewalks. Now there’s a neat study by computer graphics researchers at Carnegie Mellon University — presented at SIGGRAPH 2012 earlier this month — that develops novel computational techniques to analyze imagery in Google Street View and identify what gives a city its character….

From the abstract:

Given a large repository of geotagged imagery, we seek to automatically find visual elements, e.g. windows, balconies, and street signs, that are most distinctive for a certain geo-spatial area, for example the city of Paris. This is a tremendously difficult task as the visual features distinguishing architectural elements of different places can be very subtle. In addition, we face a hard search problem: given all possible patches in all images, which of them are both frequently occurring and geographically informative? To address these issues, we propose to use a discriminative clustering approach able to take into account the weak geographic supervision. We show that geographically representative image elements can be discovered automatically from Google Street View imagery in a discriminative manner. We demonstrate that these elements are visually interpretable and perceptually geo-informative. The discovered visual elements can also support a variety of computational geography tasks, such as mapping architectural correspondences and influences within and across cities, finding representative elements at different geo-spatial scales, and geographically-informed image retrieval.

The video and other resources are worth the time to review/read.

What features do you rely on to “recognize” a city?

The potential to explore features within a city or between cities looks particularly promising.

Posted in Geo Analytics, Geographic Data, Image Processing, Image Recognition | No Comments »

Halide Wins Image Processing Gold Medal!

Friday, August 3rd, 2012

OK, the real title is: Decoupling Algorithms from Schedules for Easy Optimization of Image Processing Pipelines (Jonathan Ragan-Kelley, Andrew Adams, Sylvain Paris, Marc Levoy, Saman Amarasinghe, and Frédo Durand.)

And there is no image processing gold medal. (To avoid angry letters from the big O folks.)

Still, when an abstract says:

Using existing programming tools, writing high-performance image processing code requires sacrificing readability, portability, and modularity. We argue that this is a consequence of conflating what computations define the algorithm, with decisions about storage and the order of computation. We refer to these latter two concerns as the schedule, including choices of tiling, fusion, recomputation vs. storage, vectorization, and parallelism.

We propose a representation for feed-forward imaging pipelines that separates the algorithm from its schedule, enabling high-performance without sacrificing code clarity. This decoupling simplifies the algorithm specification: images and intermediate buffers become functions over an infinite integer domain, with no explicit storage or boundary conditions. Imaging pipelines are compositions of functions. Programmers separately specify scheduling strategies for the various functions composing the algorithm, which allows them to efficiently explore different optimizations without changing the algorithmic code.

We demonstrate the power of this representation by expressing a range of recent image processing applications in an embedded domain specific language called Halide, and compiling them for ARM, x86, and GPUs. Our compiler targets SIMD units, multiple cores, and complex memory hierarchies. We demonstrate that it can handle algorithms such as a camera raw pipeline, the bilateral grid, fast local Laplacian filtering, and image segmentation. The algorithms expressed in our language are both shorter and faster than state-of-the-art implementations.

Some excitement is understandable.

Expect programmers will generalize this decoupling of algorithms from storage and order.

What did Grace Slick say? “It’s a new dawn, people.”

Paper (12 MB PDF)

Code: http://halide-lang.org/

Posted in Graphics, Halide, Image Processing, Programming | 1 Comment »

SAOImage DS9

Sunday, July 29th, 2012

SAOImage DS9

From the webpage:

SAOImage DS9 is an astronomical imaging and data visualization application. DS9 supports FITS images and binary tables, multiple frame buffers, region manipulation, and many scale algorithms and colormaps. It provides for easy communication with external analysis tasks and is highly configurable and extensible via XPA and SAMP.

DS9 is a stand-alone application. It requires no installation or support files. All versions and platforms support a consistent set of GUI and functional capabilities.

DS9 supports advanced features such as 2-D, 3-D and RGB frame buffers, mosaic images, tiling, blinking, geometric markers, colormap manipulation, scaling, arbitrary zoom, cropping, rotation, pan, and a variety of coordinate systems.

The GUI for DS9 is user configurable. GUI elements such as the coordinate display, panner, magnifier, horizontal and vertical graphs, button bar, and color bar can be configured via menus or the command line.

New in Version 7

3-D Data Visualization

Previous versions of SAOImage DS9 would allow users to load 3-D data into traditional 2-D frames, and would allow users to step through successive z-dimension pixel slices of the data cube. To visualize 3-D data in DS9 v. 7.0, a new module, encompassed by the new Frame 3D option, allows users to load and view data cubes in multiple dimensions.

The new module implements a simple ray-trace algorithm. For each pixel on the screen, a ray is projected back into the view volume, based on the current viewing parameters, returning a data value if the ray intersects the FITS data cube. To determine the value returned, there are 2 methods available, Maximum Intensity Projection (MIP) and Average Intensity Projection (AIP). MIP returns the maximum value encountered, AIP returns an average of all values encountered. At this point, normal DS9 operations are applied, such as scaling, clipping and applying a color map.

Color Tags

The purpose of color tags are to highlight (or hide) certain values of data, regardless of the color map selected. The user creates, edits, and deletes color tags via the GUI. From the color parameters dialog, the user can load, save, and delete all color tags for that frame.

Cropping

DS9 now supports cropping the current image, via the GUI, command line, or XPA/SAMP in both 2-D and 3-D. The user may specify a rectangular region of the image data as a center and width/height in any coordinate system via the Crop Dialog, or can interactively select the region of the image to display by clicking and dragging while in Crop Mode.

I encountered SAOImage DS9 in the links section of an astroinformatics blog.

Good example of very high end image/data cube exploration/processing application.

You are likely to encounter a number of subjects worthy of comment using this application.

Posted in Astroinformatics, Image Processing | No Comments »

Montage: An Astronomical Image Mosaic Engine

Saturday, July 28th, 2012

Montage An Astronomical Image Mosaic Engine

From the webpage:

Montage is a toolkit for assembling Flexible Image Transport System (FITS) images into custom mosaics.

Since I mentioned astronomical data earlier today I thought about including this for your weekend leisure time!

Posted in Astroinformatics, Image Processing | No Comments »

Sage Bionetworks and Amazon SWF

Friday, June 22nd, 2012

Sage Bionetworks and Amazon SWF

From the post:

Over the past couple of decades the medical research community has witnessed a huge increase in the creation of genetic and other bio molecular data on human patients. However, their ability to meaningfully interpret this information and translate it into advances in patient care has been much more modest. The difficulty of accessing, understanding, and reusing data, analysis methods, or disease models across multiple labs with complimentary expertise is a major barrier to the effective interpretation of genomic data. Sage Bionetworks is a non-profit biomedical research organization that seeks to revolutionize the way researchers work together by catalyzing a shift to an open, transparent research environment. Such a shift would benefit future patients by accelerating development of disease treatments, and society as a whole by reducing costs and efficacy of health care.

To drive collaboration among researchers, Sage Bionetworks built an on-line environment, called Synapse. Synapse hosts clinical-genomic datasets and provides researchers with a platform for collaborative analyses. Just like GitHub and Source Forge provide tools and shared code for software engineers, Synapse provides a shared compute space and suite of analysis tools for researchers. Synapse leverages a variety of AWS products to handle basic infrastructure tasks, which has freed the Sage Bionetworks development team to focus on the most scientifically-relevant and unique aspects of their application.

Amazon Simple Workflow Service (Amazon SWF) is a key technology leveraged in Synapse. Synapse relies on Amazon SWF to orchestrate complex, heterogeneous scientific workflows. Michael Kellen, Director of Technology for Sage Bionetworks states, “SWF allowed us to quickly decompose analysis pipelines in an orderly way by separating state transition logic from the actual activities in each step of the pipeline. This allowed software engineers to work on the state transition logic and our scientists to implement the activities, all at the same time. Moreover by using Amazon SWF, Synapse is able to use a heterogeneity of computing resources including our servers hosted in-house, shared infrastructure hosted at our partners’ sites, and public resources, such as Amazon’s Elastic Compute Cloud (Amazon EC2). This gives us immense flexibility is where we run computational jobs which enables Synapse to leverage the right combination of infrastructure for every project.”

The Sage Bionetworks case study (above) and another one, NASA JPL and Amazon SWF, will get you excited about reaching out to the documentation on Amazon Simple Workflow Service (Amazon SWF).

In ways that presentations that consist of reading slides about management advantages to Amazon SWF simply can’t reach. At least not for me.

Take the tip and follow the case studies, then onto the documentation.

Full disclosure: I have always been fascinated by space and really hard bioinformatics problems. And have < 0 interest in DRM antics on material if piped to /dev/null would raise a user’s IQ.

Posted in Amazon Web Services AWS, Astroinformatics, Bioinformatics, Biomedical, Cloud Computing, Image Processing, JPL, NASA | No Comments »

Does She or Doesn’t She?

Saturday, June 16th, 2012

Information Processing: Adding a Touch of Color

From the post:

An innovative computer program brings color to grayscale images.

Creating a high-quality realistic color image from a grayscale picture can be challenging. Conventional methods typically require the user’s input, either by using a scribbling tool to color the image manually or by using a color transfer. Both options can result in poor colorization quality limited by the user’s degree of skill or the range of reference images available.

Alex Yong-Sang Chia at the A*STAR’s Institute for Infocomm Research and co-workers have now developed a computer program that utilizes the vast amount of imagery available on the internet to find suitable color matches for grayscale images. The program searches hundreds of thousands of online color images, cross-referencing their key features and objects in the foreground with those of grayscale pictures.

“We have developed a method that takes advantage of the plentiful supply of internet data to colorize gray photos,” Chia explains. “The user segments the image into separate major foreground objects and adds semantic labels naming these objects in the gray photo. Our program then scans the internet using these inputs for suitable object color matches.”

If you think about it for a moment, it appears that subject recognition in images is being performed here. As the researchers concede, its not 100% but then it doesn’t need to be. They have human users in the loop.

I wonder if the human users have to correct the coloration for an image more than once for a source of color image? That is does the system “remember” earlier choices?

The article doesn’t say so I will follow up with an email.

Keeping track of user-corrected subject recognition would create a bread crumb trail for other users confronted with the same images. (In other words, a topic map.)

Posted in Image Processing, Image Understanding, Information Integration, Topic Maps | No Comments »

Finding Waldo, a flag on the moon and multiple choice tests, with R

Sunday, May 20th, 2012

Finding Waldo, a flag on the moon and multiple choice tests, with R by Arthur Charpentier.

From the post:

I have to admit, first, that finding Waldo has been a difficult task. And I did not succeed. Neither could I correctly spot his shirt (because actually, it was what I was looking for). You know, that red-and-white striped shirt. I guess it should have been possible to look for Waldo’s face (assuming that his face does not change) but I still have problems with size factor (and resolution issues too). The problem is not that simple. At the http://mlsp2009.conwiz.dk/ conference, a price was offered for writing an algorithm in Matlab. And one can even find Mathematica codes online. But most of the those algorithms are based on the idea that we look for similarities with Waldo’s face, as described in problem 3 on http://www1.cs.columbia.edu/~blake/‘s webpage. You can find papers on that problem, e.g. Friencly & Kwan (2009) (based on statistical techniques, but Waldo is here a pretext to discuss other issues actually), or more recently (but more complex) Garg et al. (2011) on matching people in images of crowds.

Not sure how often you will want to find Waldo but then you may not be looking for Waldo.

Tipped off to this post by Simply Statistics.

Posted in Graphics, Image Processing, Image Recognition, R | No Comments »

SAXually Explicit Images: Data Mining Large Shape Databases

Monday, April 2nd, 2012

SAXually Explicit Images: Data Mining Large Shape Databases by Eamonn Keogh.

ABSTRACT

The problem of indexing large collections of time series and images has received much attention in the last decade, however we argue that there is potentially great untapped utility in data mining such collections. Consider the following two concrete examples of problems in data mining.

Motif Discovery (duplication detection): Given a large repository of time series or images, find approximately repeated patterns/images.

Discord Discovery: Given a large repository of time series or images, find the most unusual time series/image.

As we will show, both these problems have applications in fields as diverse as anthropology, crime…

Ancient history in the view of some, this is a Google talk from 2006!

But, it is quite well done and I enjoyed the unexpected application of time series representation to shape data for purposes of evaluating matches. It is one of those insights that will stay with you and that seems obvious after they say it.

I think topic map authors (semantic investigators generally) need to report such insights for the benefit of others.

Posted in Data Mining, Image Processing, Image Recognition, Shape | No Comments »

scikits-image – Name Change

Tuesday, December 27th, 2011

scikits-image – Name Change.

Speaking of naming issues, do note that scikits-image has become skimage, although as of 27 December 2011, PyPi – The Python Package Index isn’t aware of the change.

On the other hand, a search for sklearn (the new name for scikit-learn) resolves to the current package name scikit-learn-0.9.tar.gz.

I will drop the administrators a note because the text shifts between the two names without explanation on sklearn.

I got clued in about the change at: http://pythonvision.org/blog/2011/December/skimage04.

So, how do we deal with all the prior uses of the “scikits-image” and “scikit-learn” identifiers that are about to be disconnected from the software they once named?

Eventually the package pages will be innocent of either one, save perhaps in increasingly old change logs.

Assume I run across a blog post or article that is two or three years old with an interesting technique that uses the old names. Other than by chance, how do I find the package under its new name? And if I do find it, how can I save other people from the same time investment and depending on luck for the result?

To be sure, the package search mechanism puts me out at the right place but what if I am not expecting the resolution to another name? Will I think this is another package?

Posted in Image Processing, Machine Learning, Names, Python | 4 Comments »