Robogals Blog

Surely at some point, we've been fascinated by fingerprints and how they can be used to solve crimes. Human fingerprints are unique and are fairly consistent over time. Thanks to technological advancements, fingerprint pattern recognition systems are becoming automated and are increasingly used in applications such as identity management and access control [1].

Image taken from Fingerprinting Express.

Fingerprint Physiology

All humans are born with flow-like pattern of ridges and valleys on each finger. No two people have the same pattern – not even identical twins [2]. Light injuries on the finger surface only damage the pattern temporarily, and hence, the ridge will reappear when the injury heals [1].

Level 1 Features. Image taken from [3].

Fingerprint ridges can be categorised into three levels [4]:

• Level 1 features (Patterns) refer to macroscopic details such as ridge flow and pattern type. Generally, there are three basic pattern types: arches, loops, and whorls. These types are still insufficient in fingerprint identification.
• Level 2 features (Points) are the minutiae such as when ridges split into two, ridge endings, "eyes", and "hooks" etc. These features are sufficient in establishing the individuality of fingerprints.
• Level 3 features (Shape) include all dimensional attributes of the ridge and other permanent details such as line shape, creases, pores, breaks, and scars etc. These features are what forensic experts look for.

Level 2 and 3 features can provide quantitative and qualitative information in identification, which are useful in latent or partial fingerprint examinations [4].

Level 2 Features: Minutiae. Image taken from [3].

Fingerprint Sensing

Fingerprints can be sampled using the following methods [1]:

• The traditional "ink and paper" method involves applying ink to the finger surface, rolling the finger on a card, and scanning the card to generate a digital image.
• The manual "lifting" method usually refers to the dusting technique used to sample latent fingerprints during crime scene investigations.
• The automated "live-scan" method produces a digital image which is obtained by placing the finger on the surface of an electronic fingerprint reader/scanner.

For Automated Fingerprint Identification Systems (AFIS), there are two main types of "live-scan" sensors: optical and solid-state [1,5].

Optical sensors require the finger is to be placed on the top side of a glass prism (part of the sensor). Afterwards, one side of the prism is illuminated via a diffused light. The fingerprint valleys which have no contact with the glass platen reflect the light, whereas ridges that touch the platen absorb the light. This differential property of light reflection allows the ridges (which appear dark) to be discriminated from the valleys [4].

Solid-state sensors use silicon-based, direct contact sensors to convert the physical information of a fingerprint into electrical signals [4]. Differences in physical properties, such as capacitance and conductance of the ridges and valleys are detected by pressing or sweeping a finger against the solid-state sensor [1].

Fingerprint Matching

Automated fingerprint recognition systems usually have two stages of operation: enrollment phase and identification phase [1].

During the enrollment phase [1], the sensor scans the user's fingerprint and converts it into a digital image. A minutiae extractor processes the fingerprint image to identify minutia points that are unique for every user. The system saves the minutiae information, such as location and direction, along with the user's  information in the enrollment database.

During the identification phase [1], the user touches the same sensor, generating a new fingerprint image called a query print. Minutiae matching is one of the most common approaches used in fingerprint-matching algorithms: minutia points are extracted from the query print, and the matcher module compares the extracted set with stored data in the enrollment database to find the number of common minutia points. Minutiae that have similar location and directions are deemed to be matched. The match score between two fingerprints should be high for the same finger and low for those from different fingers.

...

Things become more difficult and complicated when altered, fake, or severely damaged fingerprints [6] come to play, but this should hopefully get you interested in fingerprint matching.

This is a great example of how technology can aid identity management, forensics and law enforcement.

Cheers,

Sarah Li

References

1. A. K. Jain, J. Feng, and K. Nandakumar, "Fingerprint Matching", IEEE Computer Society: Computer Magazine: February 2010, pp. 36-44, Feb. 2010. Web Link.
2. A. K. Jain, S. Prabhakar, and S. Pankanti, "On the Similarity of Identical Twin Fingerprints", Pattern Recognition, vol. 35, no. 11, pp. 2653-2663, 2002.
3. D. Braggins, "Fingerprint sensing and analysis", Sensor Review, vol. 21, no. 4, pp. 272-277, 2001.
4. A. K. Jain, Y. Chen, and M. Demirkus, "Pores and Ridges: High-Resolution Fingerprint Matching Using Level 3 Features", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 1, pp. 15-27, Jan. 2007.
5. T. Harris, "How Fingerprint Scanners Work", HowStuffWorks.com. Web Link.
6. J. Feng, A. K. Jain, and A. Ross, "Fingerprint Alteration", MSU Technical Report, MSU-CSE-09-30, Dec. 2009.

Last Tuesday, Marita and I were at a lecture and dinner with Nobel physics laureate Professor Brian Schmidt, hosted by one of Robogals' sponsors, NICTA. Professor Schmidt was part of an international team who proved, contrary to what was previously thought, that the rate of expansion of the universe is currently expanding, which he explained to us in a very engaging presentation. At the dinner afterwards we were fortunate enough to meet Nina Hooper, a recent high school graduate who has just been accepted into Harvard University to further her dreams of becoming an astronaut! Marita interviews her in this short video about her goals and ambitions for the future.

This was the essay I wrote that awarded me with a scholarship to attend the ICWES15 Conference.  The scholarship was given by the Victorian Division of Women in Engineering.  The topic we had to discuss was "The best way to attract, develop and retain women engineers and scientists".

The topic of the best way to attract, develop and retain women engineers and scientists is a subject that is very close to my heart. I have done a lot of work in the area of women in engineering as the founder and director of Robogals, so I am aware of the issues that influence whether women pursue a career in engineering or not. I think the best way to attract more women to engineering is through outreach programs where female engineers can present themselves to schoolgirls as role models and do fun engineering activities with them to get girls inspired about engineering. On completion of their tertiary degrees, engineering companies need to engage with female engineering graduates and address any concerns they have about the industry. Once engineering companies deal with the concerns women have about the industry, developing and retaining female engineers is not a problem. This topic has an enormous impact on me as an engineer in the 21^st century as I want to start my own robotics company in the next couple of years.

I am the founder and director of Robogals, which is committed to substantially increasing the number of young women pursuing engineering in their tertiary studies and careers. As well as teaching over 1200 girls LEGO robotics lessons last year to get them inspired about science, technology and engineering, our other activities include the Robogals Rural and Regional programme, which allows us to reach out to and inspire girls in rural and regional areas, as well as the Parents and Daughters Science Challenge, which will be launched in late July this year, and which gets girls and their parents from all over Australia to videotape and submit a science experiment online to win some great prizes. The activities Robogals undertakes around the world are designed for girls primarily aged 10 – 14, as girls in this age range are yet to choose their senior year subjects and hence still have the opportunity to easily go down the engineering study pathway. I think activities such as these are key influences in engaging girls in the possibility of studying engineering and I think more support for them will ensure that more women are attracted to studying engineering and science. Organisations like Robogals will ensure that more girls study engineering in the future.

Once girls have finished their tertiary engineering degrees, engineering companies must engage with women by dealing with the concerns women have about their industry. I think there are two primary concerns for women working in the engineering and science industries – the work/life balance of having a great career, but also having children, and the engineering culture not always being very favourable towards women.

On the first point of the work/life balance, I think this differs for women in academia and women in industry. For women in academia, I know that taking a few years off to have children will result in a lower number of papers and citations, which affects their ability to raise money for research as compared to their male counterparts. I do not have a solution to that. For women in industry, I think it’s just a matter of forward planning. I’ve thought of this issue a great deal as I plan to have a life in technology, but I also want to have a family. Sheryl Sandberg, the Chief Operating Officer at Facebook provided the inspiration behind my solution. I intend to work very hard on my career and company until I’m 29, and then I intend to take a few years off work to start a family, while still being involved in my company in a reduced capacity. That way, I will be able to create a family without compromising on my career and professional contributions to the world. In order to attract women and allay them about their concerns of a work/life balance, I think it’s very important to speak with them and be upfront about the issue from the beginning so they can come up with a plan to have it all, while establishing a great career for themselves in engineering. To retain and develop women engineers and scientists, I think it’s important for employers to recognise that women may want to take leaves of absence in order to go and begin families, and to factor that into the company’s training programmes. If engineering companies were more open about having the conversation about integrating family planning into career planning, retaining and developing women engineers will be a lot easier.

On the second point about the engineering culture not always being very favourable towards women, I think that this will change when we have more women engineers and scientists. As well as that, in the technology industry, I think that companies who have more females in the higher up positions at the company contribute greatly to creating a culture that is kind to females. So, I think the solution to this issue is to just create a bigger pipeline of more women getting involved in science, engineering and technology in the first place.

As I want to start my own robotics company, the subject of how to best attract, develop and retain women engineers and scientists will have a significant impact on me as an engineer in the 21^st century. In order to make my company one where both females and males will work willingly, I intend to incorporate all my suggestions into the recruiting process of my company and ensure that women engineers who come to work for me will be encouraged to come up with a life and career plan to ensure they can have a family while also being a professional engineer. I have already begun developing the technology for my company and expect to launch in the next couple of years. It would be great fun to have other women engineers join me on the journey, so I hope more women step up to the challenge to be an engineer with me.

In conclusion, I think that if we focus our efforts on getting more females into engineering degrees in the first place through programs such as Robogals, then we will have a greater number of women engineers and scientists in general. Following that though, I think that companies need to understand women’s concerns and address them early on so that women can have the freedom to enjoy their engineering careers while also having the flexibility to choose to have a family.

A prominent ancient Greek philosopher once philosophized that a person is ‘defined by the choices they make’. I guess this would be an appropriate way for me to introduce myself to the one reader that happened to stumble across this page (so, a spammer).

I would love to be the perfect little engineering role model, but the sad truth is that I am far from being the girl with the best grades, or the one with the charismatic dreams, or even type of person who always makes the correct choices. Luckily, the happy truth is that I truly and honestly love being an engineer despite the 'I-want-to-kill-my-coursework!' thoughts. And through this blog I hope to show you exactly what our ever-changing and cool world is like. They say that enthusiasm and fun is infectious; hopefully this rule holds through the interwebs too :)

As a plump child who pretended she had a spaceship and alien friends, I began forming a dream. I wanted to be an adventurer! An explorer who pioneered beyond the unknown and fought off bad guys. Slowly this goal would evolve beyond recognition (I mean, I’m a nuclear engineer right now), but you have to have a starting point.

But as I progressed through my Mechanical Engineering degree, it began to dawn on me that I could be more useful if I remained closer to Earth. All my readers will be familiar with ideas such as 'global warming' and 'fuel conservation' (yes, even that spammerbot). Reading articles in the press made me think about nuclear energy as our main energy source in the future. But our current nuclear power plants (in the UK) were old and mouldy and totally outdated (kind of like the cheese in my fridge). I wanted to be a part of the nuclear renaissance, designing cool technologies such as Generation IV reactors and Fusion power plants. It was around this time last year that I moved from Imperial College London to UC Berkeley.

So I guess that’s where I am now. I know I’m on my way to fulfilling my dream, even though I’m not fighting baddies (unless you call CO2 a villain?). But I certainly feel like I’m exploring new territory with groundbreaking technology. I’m only an insignificant miniscule in the nuclear power engineering world, but I like to think that my grad school work will eventually contribute in some convoluted way.

I guess the main point I wanted to get across this jumble of words is that: Don’t be scared to dream big. And don’t be scared if your goals and desires change along the way. In fact, I recommend having more than one dream. I mean, the worst that can happen is that you can't remember what answer you put down to your password security question 'What's your dream job?' As long as you are still passionate and driven about what you want to do, you will change the world. Even if it’s just one math problem at a time.