Event Attendance Tracking

Finally – AI doing something useful for education! 🎓 I’ve been working on an AI-powered attendance system that can automatically detect students from classroom videos and mark their attendance with 92%+ accuracy ✅ We’ve all seen AI generating art, text, or chat responses. But here’s AI actually solving a real problem that teachers and institutions face every single day. Manual attendance takes time and is often error-prone. This system makes it fully automated! 👉 How it works Input: Classroom video + student dataset Detect & recognize faces using InsightFace (RetinaFace + ArcFace) Build embeddings, match with roster, and generate: ✔ Annotated video ✔ Attendance summary (CSV) ✔ Absent list (TXT) 👉 Technologies Used Python (OpenCV, Pandas, TQDM, Dataclasses) InsightFace (RetinaFace + ArcFace) for face detection & recognition ONNXRuntime (GPU) for fast inference NumPy & CSV processing for embeddings & reports The current prototype is already working well with videos, but my vision is bigger: ✨ Inshaa-Allah, this is just the first step. Next, I’ll take it to the next level so attendance can be taken directly from live classroom cameras — without teachers needing to do it manually. This is the kind of AI revolution I want to see — not replacing teachers, but helping them by saving time and reducing errors. #AI #ComputerVision #DeepLearning #Automation #EdTech #FaceRecognition

The funniest part of “face recognition” is that it doesn’t really recognise faces. Back then we tried to describe faces with hand-made features (edges/textures) and a classifier. It worked… until lighting, angle, motion blur, or a new camera sensor showed up. Now we turn a face into an embedding (a compact list of numbers) and do fast “closest match” search in that number space. It’s basically Google Maps for faces: we’re not comparing photos, we’re comparing coordinates. Where it gets real is the trade-offs: ➤ Fast vs safe: a loose threshold is quick… and lets lookalikes through ➤ Cheap vs smooth: 10× users → bigger indexes + higher GPU bills ➤ Convenient vs secure: deepfakes/replays → liveness checks + least-privilege access One move that saved us: every day we plot the match-distance histogram. Distance = “how close this face is to the stored face” (lower is better). We log two curves: real matches vs random mismatches, plus FAR/FRR (false accept/reject rates). Then we alert on drift. A camera firmware update changed noise/color enough to shift embeddings. Nothing crashed—distances just slid worse. That alert cut our time-to-debug from ~2 hours to ~15 minutes because we stopped guessing and went straight to the camera pipeline. Slide 4 shows the latency split. Slide 7 shows the “fast but wrong” threshold we shipped once. Where have you seen similarity search fail in production, and what guardrail actually prevented the next incident? Follow me, Bhavishya, for AI systems that survive real traffic 🔥 #ml #ai #genai #aiengineer

Australian retailer Bunnings has been cleared to deploy AI facial recognition technology in its stores. The company had been stymied by a 2024 Australian Information Commissioner ruling that the practice was unlawful under Australia’s Privacy Principles (APP), and appealed via the Administrative Review Tribunal, which handed down its decision this week. Read more in this article by Luke Cooper for ABC: https://lnkd.in/guNwS33N What’s the deal? ▪️The tribunal overturned the commissioner’s finding that Bunnings breached privacy principles, accepting that a “permitted general situation” justified the collection of people’s sensitive biometric data without their consent ▪️It found Bunnings had a reasonable belief that facial recognition was necessary to address repeat retail crime and serious threats to staff safety, rejecting arguments that alternatives could achieve the same outcome ▪️It placed weight on proportionality and system design, accepting that the milliseconds-long capture, processing, retention and subsequent deletion, of biometric faceprints of every customer who entered Bunnings stores reduced the privacy impact ▪️However, the tribunal affirmed the commissioner’s view that Bunnings failed to adequately inform customers their sensitive biometric data was being captured, neglected to conduct necessary privacy risk assessments before launching the system, and maintained a privacy policy that made no mention of facial recognition technology. My take ▪️This is the wedge—mass biometric surveillance without consent is now lawful in Australia for preventing crime ▪️While it does not open the door to broad surveillance for other purposes, such as behavioural profiling, it sets an important precedent ▪️Australia doesn’t have AI-specific legislation, so cases like these are likely to have significant watershed impacts ▪️This matters because we know some Australian businesses are still using facial recognition unlawfully, to grow revenue or identify high-value customers in gambling venues, for example; and some are also deploying Chinese AI camera tech that’s banned in the US, but not in Australia ▪️I expect the scope to grow, with deployment of systems designed to predict behaviour and intent, based on inference of visual attributes, and extract maximal commercial value accordingly. What’s next ▪️The commissioner is considering the decision and its implications. An appeal window applies.

One of the most compelling applications of AI, 𝐟𝐚𝐜𝐢𝐚𝐥 𝐫𝐞𝐜𝐨𝐠𝐧𝐢𝐭𝐢𝐨𝐧 𝐭𝐞𝐜𝐡𝐧𝐨𝐥𝐨𝐠𝐲 is rapidly gaining traction worldwide. Countries like the United States, China, and India are integrating facial recognition into public safety initiatives, with advanced deep learning algorithms enhancing its capability to interpret complex scenarios. In China, 𝐭𝐡𝐞 𝐒𝐤𝐲𝐧𝐞𝐭 𝐏𝐫𝐨𝐣𝐞𝐜𝐭, equipped with over 700 million surveillance cameras, has drastically improved crime detection and public security, but it has also sparked global debates on privacy concerns and state surveillance. Similarly, 𝐈𝐧𝐝𝐢𝐚’𝐬 𝐃𝐢𝐠𝐢𝐘𝐚𝐭𝐫𝐚 𝐩𝐫𝐨𝐠𝐫𝐚𝐦 piloted at Delhi Airport, leverages AI-driven facial recognition for seamless passenger verification, showcasing how technology can create more efficient public systems. Additionally, the National Crime Records Bureau is leveraging facial recognition 𝐭𝐨 𝐢𝐝𝐞𝐧𝐭𝐢𝐟𝐲 𝐦𝐢𝐬𝐬𝐢𝐧𝐠 𝐩𝐞𝐫𝐬𝐨𝐧𝐬, 𝐬𝐨𝐥𝐯𝐢𝐧𝐠 𝐭𝐡𝐨𝐮𝐬𝐚𝐧𝐝𝐬 𝐨𝐟 𝐜𝐚𝐬𝐞𝐬 𝐰𝐢𝐭𝐡𝐢𝐧 𝐦𝐨𝐧𝐭𝐡𝐬 𝐨𝐟 𝐢𝐦𝐩𝐥𝐞𝐦𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧. The technology is also transforming retail. Brands like Amazon and Alibaba employ facial recognition in cashier-less stores, enabling consumers to "just walk out" after their purchases. However, 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞𝐬 persist on the ground. Issues of accuracy and fairness remain pressing. Studies, including a 2019 NIST report, revealed that some facial recognition systems exhibit higher error rates for darker skin tones, highlighting biases in training datasets. This has raised concerns in countries like the United States, where lawsuits and protests have emerged against the use of facial recognition in policing. Ground-level adoption faces practical hurdles in developing nations. In Africa, for instance, countries like Kenya and South Africa are piloting facial recognition to combat urban crime and enhance airport security. 𝐇𝐨𝐰𝐞𝐯𝐞𝐫, 𝐥𝐢𝐦𝐢𝐭𝐞𝐝 𝐢𝐧𝐟𝐫𝐚𝐬𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞, 𝐥𝐨𝐰 𝐩𝐮𝐛𝐥𝐢𝐜 𝐚𝐰𝐚𝐫𝐞𝐧𝐞𝐬𝐬, 𝐚𝐧𝐝 𝐡𝐢𝐠𝐡 𝐜𝐨𝐬𝐭𝐬 𝐨𝐟 𝐝𝐞𝐩𝐥𝐨𝐲𝐦𝐞𝐧𝐭 𝐬𝐥𝐨𝐰 𝐩𝐫𝐨𝐠𝐫𝐞𝐬𝐬. Despite these challenges, the potential of facial recognition remains immense. Japan's Tokyo Olympics showcased its ability to manage security in large-scale global events efficiently. In France, it aids in monitoring major events like the Tour de France. Research from Allied Market Research suggests that by 2030, 80% of security checkpoints globally will integrate facial recognition for better efficiency and safety. In Singapore, The SingPass Face Verification System allows citizens to authenticate their identity for tasks such as filing taxes or accessing public services. This innovation not only streamlines processes but also showcases how AI-driven facial recognition can enhance convenience and security on a national scale. #artificialintelligence #security #faceverificationsystem #airport #camera #globalevents #deeplearning #datascience

WHO DOES MY FACE BELONG TO? In November 2019, Kashmir Hill, a new reporter at The New York Times, received a tip about a company called Clearview AI, which was working on facial recognition technology. The tip revealed that Clearview AI had developed a powerful app by gathering billions of photos from social media and other websites. This app could recognize a person’s face and find all their photos online. The tip also mentioned that Clearview AI was selling this technology to law enforcement while trying to keep it secret. Since the 1960s, there have been efforts to make facial recognition technology work, but results were often disappointing. However, Clearview claimed to be different with a “98.6% accuracy rate” and a huge photo database that law enforcement had never had access to before. Hill saw the potential risks of facial recognition technology and started looking into how it affected privacy. Clearview AI’s claims showed improvements in accuracy and effectiveness, but there were serious concerns about privacy violations and ethical issues. Hill’s research became a crucial starting point for understanding the impact of facial recognition technology on society and its future use. During the investigation, Hill discovered how secretive Clearview was and how it monitored its use. Clearview was tracking and blocking searches for photos of reporters like Hill. The company could see who law enforcement was searching for and control the results, showing the power of a secretive company. The book Your Face Belongs to Us(*) explores this topic and examines the development of facial recognition technology and its societal impacts. Kashmir Hill has investigated companies like Clearview AI and the ethical and privacy issues associated with this technology. The book provides a broad view, covering the history of facial recognition technology, its current uses, and its potential future effects. Hill discusses the impacts on security, privacy, and human rights, encouraging readers to consider the challenges and opportunities that come with this technology.   (*) Hill, K. (2023). Your Face Belongs to Us: The Secretive Startup Dismantling Your Privacy, Simon & Schuster, pp. 347.   #technology #facialrecognition #future #privacy #security #cybersecurity  

Once a leader in women’s labor force participation, the US now trails peer countries; that impacts businesses and the US economy. 🔹 Canada, France, Germany and the UK, which had similar participation rates as the US in 1995, have increased their rates much beyond the US. The rate in the US rose by 2.3 percentage points since 1995; that is smaller than Canada (+9.4 ppts), France (+7.5 ppts), Germany (+11.1 ppts) and the UK (+9.1 ppts). 🔹 The Netherlands, Spain, Japan and Australia, which lagged the US in 1995, have not only caught up, but they now exceed the US. 🔹 Researchers cite several reasons for the US falling behind, including limited family and care policies such as paid leave and childcare subsidies, and greater availability of part-time work. Differences in tax systems, health care, disability benefits, and workplace culture also contribute. 🔹 According to a study by the US Labor Department, if the US had the same women’s prime-age participation rate as in Canada and Germany, around 5 million more women would be in the workforce. That translates to around $775 billion in additional economic activity each year. That is about the size of the economies of Belgium or Ireland; it is an untapped growth opportunity for US businesses. Women’s prime-age labor force participation rate in the US has stagnated compared to peer countries over the past three decades. Pandemic-era gains are now reversing, especially among college-educated mothers of young children. Declining participation, often driven by limited choices, undermines women’s career prospects and family financial stability. Employers are less likely to retain top talent, harming productivity. They can gain an edge over competitors by investing in flexible work arrangements, part-time opportunities, childcare benefits and paid leave. Overall, the US economy is smaller and grows more slowly.

Nationally, 2M+ high school students take dual enrollment college courses each year-- How many are enrolled at your local schools, and what are the gaps in access? In my latest Community College Research Center blog post, I present a set of dashboards showing disaggregated results by state, district, and school on participation in #DualEnrollment and #AdvancedPlacement nationwide. You can see the dual enrollment and AP hotspots in your state using the map feature, hover over districts to see detailed, school-level results, and view disaggregated trends in both state- and school-level participation in these early college courses (which we an others have shown to reliably provide a boost for students into and through college). Here's the post with the dashboard: https://lnkd.in/e3pzMuAd Here are some takeaways from the analysis: 💡 States differ quite a bit in terms of the overall dual enrollment participation rate: Nationally 10.6% of high schoolers took a DE course but in Washington, Indiana, and Iowa it's more than 25% and in 6 states it's under 5%. And differences state-by-state varies even more for specific subgroups of student (see the second tab). 🔎 Within states, there are substantial differences across school districts in the level of dual enrollment and AP participation-- and in many states these two programs serve geographically different areas (as you can see from toggling between DE and AP in the first tab) 🔍 🔍 Within districts with multiple high schools, there are key differences school-by-school both in overall participation as well as disparities by student subgroup (hover over the district in the map or view school-level results in the third tab) 📈 📊 Dual enrollment has steadily grown in the past 5 years -- even through the pandemic years -- but gaps in access for students of color, English learners, and students with disabilities remain in essentially every state and the vast majority of districts. These tools are meant to inform efforts to expand access to dual enrollment and other early college opportunities as an on-ramp into college and career opportunity after high school. They utilize federal data which is incredibly rich and actionable (e.g. each school is a principal or counselor that colleges can reach out to!) -- we need to ensure continuity in collection and access to the U.S. Department of Education Civil Rights data into the future! I'd love to hear how these tools can support your work and what you have learned about effective strategies for increasing access and broadening the benefits of dual enrollment 🙌 National Alliance of Concurrent Enrollment Partnerships

🔍 Trends in Adult Learning: New Data from the 2023 Survey of Adult Skills (PIAAC) 👉 See: https://lnkd.in/dSwDC4tc 📘This timely OECD Education and Skills report sheds light on the evolving landscape of adult learning across 31 countries. With rich data and sharp insights, it offers essential guidance for shaping inclusive and future-ready skills strategies. 🎯 Why it matters: Amid fast-paced technological, economic, and climate transitions, adult learning is a cornerstone for upskilling, employability, and social resilience. Yet, participation is stagnating or declining — even in advanced economies. 📌 Key Messages: ▪️Stagnating Participation: Only 40% of adults engage in learning yearly. Participation is falling in more countries than it's rising — a red flag for skills policy. ▪️A Narrow Focus on Short, Compliance-Based Training: Most learning is non-formal (37%) and very short (42% ≤ 1 day). Health & safety dominates, while broader reskilling needs — especially digital & transversal skills — remain underserved. ▪️Formal Learning in Decline: Only 8% of adults engage in formal education, mostly tertiary. Second-chance education plays a significant role in countries like 🇵🇹 Portugal, 🇬🇧 UK, 🇪🇸 Spain. ▪️Informal Learning at Work – A Hidden Engine: Highly prevalent but uneven. Daily workplace learning ranges from 4% (Poland) to 41% (Portugal). Recognition remains weak. ▪️Barriers Persist – and Are Unevenly Felt: Time, cost, and access limit participation — especially for women, low-skilled adults, and part-timers. Half of adults did not learn and didn’t want to, suggesting disengagement. ▪️Employer Role is Crucial: Two-thirds of training is employer-funded and occurs during working hours. Countries with strong employer engagement show higher participation. ⏭️Policy Call: From Fragmentation to Systemic Reform: The report calls for a paradigm shift — from short-term fixes to long-term strategies: 🔹 Flexible, stackable learning pathways 🔹 Broader certification of non-formal learning 🔹 Better targeting of low-skilled adults 🔹 Stronger public-private partnerships 🔹 Greater integration of adult learning into VET & skills strategies 🌐 Implications for VET systems: ▪️VET providers must step up as lifelong learning hubs, integrating short and longer-term learning, recognizing prior learning, and aligning offers with evolving job roles and digital transitions. 💡Conclusion: ▪️Adult learning must be seen not as a policy add-on, but as an essential building block for a just transition and economic adaptability. ▪️The report is a must-read for policymakers, education leaders, and employers alike. #LifelongLearning #SkillsForTheFuture #AdultEducation EU Employment and Skills Cedefop Eurofound European Training Foundation EfVET European Association of Institutes for Vocational Training (EVBB) European Vocational Training Association - EVTA EUproVET EURASHE eucen CoP CoVEs

In a world of accelerating market shifts, understanding stock market participation is more critical than ever. The latest data, visualized here by Visual Capitalist (April 2025), reveals fascinating global disparities in stock market engagement. The U.S. leads with 55% of the population participating, followed by Canada (49%) and Australia (37%). Meanwhile, despite having nearly 99 million shareholders, China’s participation rate remains just 7%, highlighting a vast under-tapped retail investor potential relative to population size. Recent market turbulence — from tech sector corrections to evolving central bank policies — has reignited conversations about financial literacy, access to investment platforms, and the resilience of retail investing communities. A few reflections: • Mature markets like the U.S. and Canada demonstrate the stabilizing power of widespread shareholder bases, even amid volatility • Emerging economies, despite growing absolute numbers of investors, still have significant room to deepen participation — a huge opportunity, but also a structural challenge • As digital platforms proliferate and financial inclusion initiatives expand, we may be standing at the edge of a historic shift in global investing patterns In this environment, trust, education, and smart regulation will be key to ensuring that broader participation translates into more resilient financial systems.

In Luxembourg, immigrants work more than locals. What does this mean for our talent strategy in 2026? OECD data on labour force participation (ages 15–64, 2024) is clear: Foreign-born participation in Luxembourg: 79.2% Native-born participation: 67.8% Gap: +11.4 percentage points Add one more fact: foreign-born residents now represent 51% of the population. So we are not speaking about a small niche. We are speaking about the majority of people who keep the economy running, pay taxes, raise families, and build futures here. Across the OECD, immigrants participate slightly more than natives on average (76.9% vs 76.1%). Luxembourg pushes that pattern to an extreme. My takeaway: participation is now a core metric of competitiveness. If foreign-born talent wants to work, the question becomes: how fast can the system help them contribute at full capacity? For me, “integration speed” becomes an economic KPI in its own right: → Recognition of skills and credentials without long delays → Clear language pathways linked to real jobs → Affordable childcare that allows both parents to work → Mobility across borders and sectors → Fast matching of skills with real vacancies, not only in finance If Luxembourg wants to stay second to none, the talent strategy cannot stop at attraction. The real edge comes from activation. My question for 2025: what is, in your view, the biggest blocker to faster labour market integration in Luxembourg today? Source: OECD, International Migration Outlook 2025 (Annex Table 1.A.6; labour force participation, ages 15–64, 2024).