HP newsroom blog
Showing results for 
Search instead for 
Did you mean: 
Published: August 28, 2016


original (6).jpg

Fu Jiang recently completed his M.Sc. in Imaging Science at the Rochester Institute of Technology (RIT) and this fall begins studying for a Ph.D. in Color Science, also at RIT. Jiang grew up in Huaian, China and received his B.Sc. in Physics from the Nanjing University of Information Science and Technology. This summer, he has been working with mentors in HP’s Print and 3D Lab, hoping to move the bar on our understanding of color perception at small scales. While in Palo Alto, Jiang is enjoying hiking and cycling, and appreciating the Bay Area’s good weather.

HP: Can you describe the research project you’re working on?

My project focuses on our perception of color differences in what we call “small features.” These are areas of color that represent less than 2 degrees of your field of view, which is roughly the size of your thumbnail when you hold your arm straight out in front of you. We know quite a lot about our ability to perceive color differences at a larger scale, but very little research has been done on our perception of color in areas of less than 2 degrees.

HP: What’s the main question you are asking?

There’s a certain point where the human visual system can no longer distinguish two very similar colors that are actually different. We’re interested in finding out where that threshold is for different people and for different sets of colors at this smaller scale. We call the threshold “JND”, which stands for “just noticeable difference.”

HP: How are you doing the research?

I’m designing a psychophysical experiment that asks people to evaluate color differences between two small squares of color on a display.  We’ve already run a pilot test with a small set of expert subjects. These are people who have a background in color science. That has given us some parameters that we can use when performing tests with naïve subjects. We’re just starting those tests.

HP: Any results yet?

Yes, we have already found some differences between our data and the results from published experiments where people were shown larger color patches. It suggests that human perception of color at smaller scales may well not conform to the current commonly used color difference models.

HP: How could that impact HP’s work?

If the results hold up, we’ll have a better understanding of the point at which most people can tell the difference between two small patches of color – and that should provide data that we can use to for the design and optimization of our color pipelines for 3D Printing.

HP: What has particularly struck you about working at HP Labs?

I’m surprised how flexible the schedule is – that I can work whatever hours I need to get the job done. Plus we have access to the latest equipment, like light booths and 3D printers that you don’t find in all university labs. It’s also really easy to arrange to meet with my supervisor when I need to and it’s been great to be able to talk with people who know so much about how the industry works and to learn about what they are interested in.

    HP Labs
Published: October 10, 2017

From left: HP Labs researchers Adrian Baldwin and Jonathan GriffinFrom left: HP Labs researchers Adrian Baldwin and Jonathan GriffinHP Connection Inspector, a new intelligent embedded security feature for enterprise printers developed at HP Labs, helps networked HP printers stay one step ahead of malware attacks by giving them advanced self-healing capabilities.

Announced at this month’s HP World Partner Forum in Chicago, HP Connection Inspector was developed specifically for enterprise printers, notes Adrian Baldwin, one of the Bristol, UK-based researchers behind the innovation.

“A lot of security technology that gets put into printers simply copies what is put into PCs,” he says. “HP Connection Inspector has been developed from the outset with the mechanics of how printers work – and the needs of printer users – in mind.”

Malicious actors are constantly looking for less-protected gateways into an enterprise’s larger IT network. To prevent networked printers becoming that conduit, the HP Security Lab team focused on developing a novel approach to network traffic monitoring designed to detect threats and enable immediate responses.

Where many malware detectors need to refer to libraries of known hostile programs or network addresses known to be associated with an attack, HP Connection Inspector focuses on detecting anomalous behaviors and then acts to secure the networked printer even before the malware is confirmed to be present.

It does this by keeping a continuous watch for moments when malware is attempting to make contact with its command and control server. In the process, HP Connection Inspector learns what “normal” network traffic looks like, meaning that it can detect suspicious outbound requests even when those requests aren’t sent to known “bad” web addresses. When it detects suspicious activity, the software can immediately go into a protected mode, stopping any further unfamiliar requests and sending a warning to IT administrators.

“One thing that’s hard about doing this is avoiding false alarms,” says Baldwin. “We do that by restricting what the printer is allowed to do if we get suspicious, but not stopping it completely until we know that we need to – that makes the solution much more reliable than usual.”

When HP Connection Inspector detects a specific, customer-determined level of malware-like behavior, the technology can also trigger a printer reboot. This initiates a self-healing procedure without IT needing to be involved. 

“Printers need to be on all the time,” adds project manager Jonathan Griffin. “By automatically rebooting the computer, printers aren’t idled while waiting for IT support; that also helps reduce down time, which is a high priority for all enterprise print users.”

In addition, these capabilities had to be developed as elegantly as possible, to ensure they would provide security without interfering with overall printing or networking performance.

“A lot of research went into creating this, but we’re quite pleased with how little space the final code actually takes up,” Baldwin notes.  

After developing the technology behind HP Connection Inspector, the HP Labs team worked extensively with colleagues from HP’s Office Printing Solutions group in Bangalore, India and Boise, Idaho to ready the solution for commercial use. It is now set to be included in all HP Enterprise LaserJet printers by the end of this year.

HP Connection Inspector is just the first of a number of printer-specific security analytics innovations the HP Labs team is developing to help detect and respond to malware attacks.

Published: September 28, 2017


Customers visiting HP’s Customer Welcome Center (CWC) in Palo Alto can now also experience HP’s new state of the art 3D Customer Lab.

Based in HP Labs’ headquarters building adjacent to the CWC, the Multi Jet Fusion 3D Customer Lab is a place where customers and partners can both see and experience HP’s new 3D printers in action. This is also an active research facility, says Lihua Zhao, director of HP’s Advanced Material and Process Research team.

“We opened in late July and have seen over 200 customers, partners and alliance partners come through the lab,” Zhao notes. “They see what our latest printers can do and also witness HP research in action, as we run experiments to refine our 3D technology and print items that help other HP Labs teams conduct their research.”

The lab’s star attractions are a pair of brand new, industrial-grade HP Jet Fusion 4200 printers, each with its own HP 4200 Processing Station. Visitors get to learn how print trolleys the size of a domestic dishwasher are pre-loaded with powdered printing material before being slotted into the main printer body. The printer then goes layer by layer filling the trolley and creating the parts.

3D-printed part3D-printed partAfter printing, the just-built items have to cool down, which can often take as long as the printing process. To avoid keeping the printer out of service for that time, the trolley is removed, placed into a Processing Station and another trolley is wheeled into place, so that production never stops. At the processing station, the printed items are cooled, unpacked, and cleaned of any excess powder, which is recycled for use in the next print run, a huge milestone in 3DP. In traditional 3D technology like SLS only 50% of the powder can be reused. With HP MJF you can reuse all the powder.

“What this means is that you can keep an HP 3D printer going all the time, which is important to our customers as they like using these printers to manufacture customized parts,” says Zhao. “We like to point out that up to 50% of the printer components in each HP 4200 printing system are themselves printed on an HP 3D printer.”

Visitors range from manufacturers, who are already very familiar with 3D printing and want to see HP’s latest commercial offering, to customers that have yet to move into 3D printing but want a clear sense of the technology’s potential. In addition to learning about the print process, they get to see and handle final printed pieces and learn about the flexibility and economics of additive manufacturing.

Some come with very specific questions or manufacturing needs in mind and the HP Labs engineers they meet can often point them to teams within HP’s business units that can help meet their needs or overcome their challenges.  But these conversations also spark ideas for new research directions at HP Labs and potential new partnerships.

“That’s an important aspect of having the 3D Customer Lab in HP Labs,” Zhao says. “We are continually improving our technology and we can run research trials through these printers to better understand many practical challenges that we identify in these conversations and then try out potential solutions to them.”

In addition, the HP Labs 3D print research team is using the facility to test and refine many of its own ideas for 3D printing innovations – it can also draw on more advanced print test facilities that are the forerunners of future HP 3D printers – and to help other HP Labs groups conduct their research.

Researchers designing new software and storage solutions for end-to-end design/print/manufacturing processes, for example, can test their ideas in the near-commercial conditions of the 3D facility. And one off prototypes developed by teams in HP’s Immersive Experience Lab can now be easily printed on demand.

3D-printed part3D-printed part

Published: September 14, 2017


Audiophiles know that sound reproduction is improved by adding more speakers to a room and making them larger. But that won’t help make today’s increasingly slim and often tinny-sounding laptops, tablets, and phones sound good.

There is a way, however, to make small devices sound larger and better, enabling a high-quality, immersive audio experience, suggests HP Labs researcher Sunil Bharitkar a member of the Media team in HP’s Emerging Compute Lab.

“We can use software to process the audio signals on HP devices so that they approximate the spatial quality of sound that you hear in a room with a multi-loudspeaker audio system,” he says. “We call it immersive audio.”

While competing approaches offer similar processing techniques, the key to HP’s lies in applying specific audio filters and “transforms” that create natural sounding audio with a low compute complexity.

Bharitkar has been guiding an effort at HP Labs, in partnership with colleagues in HP’s Personal Systems and Print groups spearheaded by Personal Systems Chief Technologist Mike Nash, to use this research to upgrade the audio quality on HP’s mobile and desktop devices.

“Audio is an essential, and often underestimated, component of any technology experience, which is why we’re thrilled to be working in close collaboration with HP Labs to make our devices sounds second to none in the industry,” says Nash.


Immersive Audio Flow Chart.png

The team first needed to establish objective metrics against which to measure audio performance on HP devices. Based on the outcome of those measurements, they then started redesigning HP’s audio processing technology from the ground up, an effort that has included creating a novel signal topology and a unique set of audio filters.

Additionally, the researchers are applying machine learning in their audio processing topology to classify the sound content (whether it was a movie, for example, or a song). Furthermore, using machine learning it can be ensured that multiple layers of unnecessary processing are not applied where the content is identified as having already been processed, reducing the signal processing compute load and minimizing artifacts.


Head, Torso & Mouth Simulator used by HP Labs for extracting directional cues associated with sound localization, and for speech reproduction.Head, Torso & Mouth Simulator used by HP Labs for extracting directional cues associated with sound localization, and for speech reproduction.This is rapidly taking users towards an experience – delivered either through a device’s small speakers or a set of headphones – that faithfully reproduces the intent of its creator of any kind of audio, from a song recorded in a small studio to a Hollywood blockbuster, while consuming as little processing power as possible.

Thanks to commonalities between internationally standardized testing methodologies used for image and audio quality assessments, the HP team have been able to draw on the experience of HP’s Print Quality Evaluation group to test their improvements, assembling several panels of non-experts to evaluate their innovations..

In an effort led by HP Mobility’s Head of Software, Chris Kruger, the first iterations of HP’s new audio processing algorithms are now being packaged into the Qualcomm Snapdragon audio processing chips used in HP mobile devices. Next up: further refining the technology and adding it to HP’s consumer offerings, and towards that the Labs are working closely with Sound Research, an HP partner, for integration.

Published: August 14, 2017

HP Labs intern Swetha RevanurHP Labs intern Swetha Revanur

We first met with Swetha Revanur last summer, when she was a recent high school graduate heading for Stanford University and interning in HP’s Emerging Compute Lab on a project that used sensor data to create simulations of how people move around in different living spaces. This year, Revanur is back in the same lab but working on a new challenge. We caught up with her to see how her academic interests have developed over the last twelve months and to learn about what she’s been working on this time around.

HP: First of all, how was your freshman year at Stanford?

I had an amazing freshman year! I’ve met some of the most brilliant people, the classes were just the right amount of challenging, and I joined an acapella group on campus. In December, I also traveled out to Sweden to speak at the 2016 Nobel Prize Ceremonies and meet the laureates. I’m excited to start my sophomore year in September!

HP: Are you still planning to major in computer science?

Yes, that hasn’t changed! When I started at Stanford, I was interested in biocomputation, but my interests have since shifted to artificial intelligence.

HP: What prompted the change?

The decision was actually driven largely by my work at HP Labs last summer where I had a lot of exposure to the algorithmic side of computer science. I think that if I can understand these algorithms and optimize them, I can have a much larger impact in whatever sector I choose to work in. At the end of the day, machine learning can always be applied to health, and it has a huge scope. 

HP: So what are you working on this year?

I’m with the same team in the Emerging Compute Lab, but instead of looking at sensor analytics, I’ve shifted my focus to the intersection of deep learning and robotics. I’m using techniques in reinforcement learning, which lets us train software agents to find the optimal actions to take in specific environments. I’ve developed a hybrid approach that maintains the same performance as state-of-the-art reinforcement learning algorithms, while improving data and cost efficiency.

HP: How’s it going?

Reinforcement learning is a new area of study for me, and so it’s been a fruitful process of self-teaching. Initially, I was wrangling with pages of linear algebra to understand how existing methods work. Once I got my bearings, I was able to point out gaps and come up with optimizations, and now I’ve implemented the algorithm in TensorFlow.

HP: How will you test the new algorithm?

The new hybrid algorithm will be tested in simulation. I’ll start with simple tests with basic software agents. For example, I recently ran a test where a pendulum was trained to stay upright. Gradually, we’ll work up to full humanoid simulations.

HP: Why is HP interested in this work?

A lot of folks in HP Labs are working in a fundamental robotics research space, on projects like mapping, localization, and navigation. My hybrid approach helps cut time and cost requirements in that space. In general, robotics dovetails really well into the social, business, and home application layers that HP is a major player in.

I was invited to speak at the HP Labs global all-employee meeting with our CTO, Shane Wall. The implications of better reinforcement learning are broad, the interest is there, and I’m excited to see where it takes us.

Published: August 09, 2017

HP Labs intern David HoHP Labs intern David Ho

David Ho is about to enter his fifth year in Purdue University’s Ph.D. program in electrical and computer engineering where he specializes in image processing and computer vision research. Ho moved to the US from Gwangju, Korea during high school, and then attended the University of Illinois at Urbana-Champaign to study for both undergraduate and Masters degrees in electrical and computer engineering. This summer, Ho has been working on a collaboration between HP’s Print Software Platform organization and Emerging Compute Lab, called Pixel Intelligence, applying his expertise in image segmentation to the challenge of picking out people in any specific image.

HP: Can you tell us more about your internship project?

I’ve been using deep learning to improve what we call person segmentation, which is where a computer is able to separate the image of a person from any background. Humans can distinguish between different kinds of images very easily. But computers just see images as an array of pixel values. So we need to find ways to make computers “understand” images of people as people.

HP: How have you been doing that?

I’ve been taking several existing data sets of images where we have already established the “ground truth” of the images and using those data sets to teach a computer program what a person looks like. Once it is trained, I input new images and see how well the program can pick people out of them. The idea is to reduce the number of errors we get in doing that, and to be able to do it faster.

HP: How has it been going?

We’ve had some good results. One thing we’ve been able to do is get this running on a webcam camera, so that it can segment out people in every frame it records.

HP: What’s the challenge in doing that?

One is getting it to work for a relatively crude camera. Another, which we’re still working on, is reducing the processing required to do the segmentation. So far we’ve been running it on a processing unit designed for heavy computation. But we’d like to be able to run it on a smaller device.

HP: Will this work feature in your Ph.D. thesis?

Not directly. In my Ph.D., I’m also looking at applying deep learning to image processing, but I’m looking at understanding microscope images and segmenting out different biological structures. So the application is different but the main idea is the same: helping computers to make sense of interesting images.

HP: Is this your first time interning at HP Labs?

Yes, and it’s my first internship in an industrial lab.

HP: What has struck you as different about working in an industrial lab setting?

I’ve been impressed how industrial labs value creating software that anyone can use. My segmentation solution was pretty good, for example, but required a lot of processing power. So my mentor, Dr. Qian Lin, has pushed me to make it smaller so it’s of more value to more people.