Everand Logo

Welcome to Everand!

  • Discover millions of ebooks, audiobooks, and so much more with a free trial

    Only $11.99/month after trial. Cancel anytime.

    Human Recognition in Unconstrained Environments: Using Computer Vision, Pattern Recognition and Machine Learning Methods for Biometrics
    Human Recognition in Unconstrained Environments: Using Computer Vision, Pattern Recognition and Machine Learning Methods for Biometrics
    Human Recognition in Unconstrained Environments: Using Computer Vision, Pattern Recognition and Machine Learning Methods for Biometrics
    Ebook439 pages4 hours

    Human Recognition in Unconstrained Environments: Using Computer Vision, Pattern Recognition and Machine Learning Methods for Biometrics

    ()

    Read preview

    About this ebook

    Human Recognition in Unconstrained Environments provides a unique picture of the complete ‘in-the-wild’ biometric recognition processing chain; from data acquisition through to detection, segmentation, encoding, and matching reactions against security incidents.

    Coverage includes:

    • Data hardware architecture fundamentals
    • Background subtraction of humans in outdoor scenes
    • Camera synchronization
    • Biometric traits: Real-time detection and data segmentation
    • Biometric traits: Feature encoding / matching
    • Fusion at different levels
    • Reaction against security incidents
    • Ethical issues in non-cooperative biometric recognition in public spaces

      • With this book readers will learn how to:

    • Use computer vision, pattern recognition and machine learning methods for biometric recognition in real-world, real-time settings, especially those related to forensics and security
    • Choose the most suited biometric traits and recognition methods for uncontrolled settings
    • Evaluate the performance of a biometric system on real world data
    • Presents a complete picture of the biometric recognition processing chain, ranging from data acquisition to the reaction procedures against security incidents
    • Provides specific requirements and issues behind each typical phase of the development of a robust biometric recognition system
    • Includes a contextualization of the ethical/privacy issues behind the development of a covert recognition system which can be used for forensics and security activities
    LanguageEnglish
    PublisherAcademic Press
    Release dateJan 9, 2017
    ISBN9780081007129
    Human Recognition in Unconstrained Environments: Using Computer Vision, Pattern Recognition and Machine Learning Methods for Biometrics

    Related to Human Recognition in Unconstrained Environments

    Related ebooks

    Computers For You

    View More
    View More

    Related podcast episodes

    Related articles

    • Article

      Rise Of The Robots

      Jan 12, 2021

      Rise Of The Robots
      7 min read

    • Article

      Rokoko Studio 2.0

      Feb 23, 2021

      Rokoko Studio 2.0
      1 min read

    • Article

      Federica Fragapane

      Sep 17, 2020

      Federica Fragapane
      7 min read

    • Article

      Is Artificial Intelligence Permanently Inscrutable?

      Sep 1, 2016

      Dmitry Malioutov can’t say much about what he built. As a research scientist at IBM, Malioutov spends part of his time building machine learning systems that solve difficult problems faced by IBM’s corporate clients. One such program was meant for a

      13 min read

    • Article

      Is Artificial Intelligence Permanently Inscrutable?: Despite new biology-like tools, some insist interpretation is impossible.

      Sep 1, 2016

      Dmitry Malioutov can’t say much about what he built. As a research scientist at IBM, Malioutov spends part of his time building machine learning systems that solve difficult problems faced by IBM’s corporate clients. One such program was meant for a

      13 min read

    • Article

      Opinion: Advancing AI In Health Care: It’s All About Trust

      Oct 23, 2019

      In drug trials, success in Phase 1 is no guarantee of success in Phase 3. In the current mania for AI and deep learning, a proof of concept is taken…

      4 min read

    • Article

      Tech Lets People Play Games With Their Thoughts

      Apr 1, 2024

      Engineers have created a program that lets people use their thoughts to control video games. The innovation is part of research into brain-computer interfaces to help improve the lives of people with motor disabilities. The researchers incorporated m

      2 min read

    • Article

      Electric Eye

      Feb 14, 2023

      Electric Eye
      12 min read

    • Article

      Opening The ‘Black Box,’ Google DeepMind AI System Diagnoses Eye Diseases And Shows Its Work

      Aug 13, 2018

      Experts said the level of accuracy is impressive, but the bigger breakthrough is the DeepMind system’s solution to the so-called “black box” problem of artificial intelligence.

      5 min read

    • Article

      Danger On The Road

      Oct 14, 2019

      Danger On The Road
      3 min read

    • Article

      The robot WILL SEE YOU NOW...

      Dec 27, 2019

      The robot WILL SEE YOU NOW...
      2 min read

    • Article

      Technology Under Your Skin

      Dec 1, 2022

      Technology Under Your Skin
      4 min read

    • Article

      In Tandem

      Aug 31, 2023

      The 2023 World Robot Conference (WRC), held in Beijing from August 16 to 22, showcased the latest technological innovations in robotics from around the world. It featured a main forum and more than 20 subforums, each with a different focus—ranging fr

      4 min read

    • Article

      Deep-learning AI Technique Helps Scientists See More Clearly Inside The Cell

      Sep 4, 2019

      A new imaging restoration technique using deep learning offers scientists a higher-resolution, less-blurry, less-noisy view of the interior of cells.

      3 min read

    • Article

      Wireless Network Gets Data From Sensors The Size Of Salt Grains

      Mar 19, 2024

      Tiny chips may be a big breakthrough, researchers report. They have a new approach for a wireless communication network that can efficiently transmit, receive, and decode data from thousands of microelectronic chips that are each no larger than a gra

      3 min read

    • Article

      Dr. Eric Topol

      Mar 25, 2019

      In his new book, Deep Learning, the cardiologist argues that artificial intelligence can bring humanity back to medicine

      2 min read

    • Article

      How To Make Sense From And With AI ?

      Sep 25, 2021

      How To Make Sense From And With AI ?
      4 min read

    • Article

      To Make Sense Of A.I. Decisions, ‘Peek Under The Hood’

      Oct 8, 2018

      Now that humans have programmed computers to learn, we want to know exactly what they’ve learned and how they make decisions after their learning process is complete. The answers to such questions could shed light on our own decision-making processes

      6 min read

    Related categories

    Reviews for Human Recognition in Unconstrained Environments

    0 ratings

    0 ratings0 reviews

    What did you think?

    Tap to rate

    Review must be at least 10 words

      Book preview

      Human Recognition in Unconstrained Environments - Maria De Marsico

      2016

      Chapter 1

      Unconstrained Data Acquisition Frameworks and Protocols

      João C. Neves⁎; Juan C. Moreno⁎; Silvio Barra⁎⁎; Fabio Narducci⁎⁎⁎; Hugo Proença⁎    ⁎IT – Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal

      ⁎⁎Department of Mathematic and Computer Science, University of Cagliari, Cagliari, Italy

      ⁎⁎⁎BIPLab – University of Salerno, Fisciano, Italy

      Abstract

      The identification of humans in non-ideal conditions has been gaining increasing attention, mainly supported by the multitude of novel methods specifically developed to address the covariates of non-cooperative biometric recognition. Surveillance environments are one of the most representative cases of unconstrained scenarios, where fully automated human recognition has not been achieved, yet. These environments are particularly harsh for several reasons (e.g., high variations in illumination, pose, and expression), but the limited resolution of the biometric data acquired is regarded as the major factor for performance degradation. Consequently, different strategies for imaging subjects at-a-distance have been introduced. This chapter provides a comprehensive review of the state-of-the-art surveillance systems for acquiring biometric data at-a-distance in a non-cooperative manner. The challenges and the open issues of current architectures are highlighted. Also, the most promising strategies and future lines of research are outlined.

      Keywords

      Surveillance scenarios; Unconstrained data acquisition; Non-cooperative biometric; Recognition; Biometric recognition at a distance; PTZ cameras; Camera calibration

      Chapter Outline

      1.1  Introduction

      1.2  Unconstrained Biometric Data Acquisition Modalities

      1.3  Typical Challenges

      1.3.1  Optical Constraints

      1.3.2  Non-comprehensive View of the Scene

      1.3.3  Out-of-Focus

      1.3.4  Calibration of Multi-camera Systems

      1.4  Unconstrained Biometric Data Acquisition Systems

      1.4.1  Low Resolutions Systems

      1.4.1.1  Super-resolution Approach

      1.4.1.2  Gait Recognition

      1.4.2  PTZ-Based Systems

      1.4.3  Face

      1.4.3.1  Typical Design of Master–Slave Systems

      1.4.3.2  Systems Based on Logical Alignment of the Cameras

      1.4.3.3  QUIS–CAMPI System

      1.4.3.4  Other Biometrics: Iris, Periocular, and Ear

      1.5  Conclusions

      References

      1.1 Introduction

      The recognition of individuals either from physical or behavioral traits, usually denoted as biometric traits, is common practice in environments where the subjects cooperate with the acquisition system.

      In the last years, the focus has been placed on extending the robustness of recognition methods to address less constrained scenarios with non-cooperative subjects. Researchers have introduced different strategies to address high variability in the age [1], pose [2], illumination [3], expression [4] (A-PIE), and other confounding factors such as occlusion [5] and blur [6]. Also, these improvements have been evidenced by the performance advances reported in unconstrained biometric datasets, such as the Labeled Faces in the Wild (LFW) [7].

      Despite these achievements, the recognition of humans in totally wild conditions observed in visual surveillance scenarios has not been achieved, yet. In this kind of setup, images are captured from large distances, and the acquired data have limited discriminative capabilities, even when using high-resolution cameras [8]. Considering that in unconstrained environments data resolution may have a greater impact on the performance than A-PIE factors, several authors have been particularly devoted to extending the workability of biometric data acquisition frameworks to unconstrained scenarios in which human collaboration is not assumed.

      In this chapter, we review most of the relevant frameworks and protocols for acquiring biometric data in unconstrained scenarios. In Section 1.2, we provide a comparative analysis between the different acquisition modalities. The advantages of using magnifications devices, such as PTZ cameras, are evidenced by the difference in the resolution between the eyes (interpupillary distance). The resolution of biometric data acquired by PTZ cameras at the maximum zoom is five times higher than typical surveillance cameras. Also, the minimum resolution required to acquire high-resolution face images (interpupillary distance greater than 60 pixels) with a stand-off distance larger than 5 m can only be attained using PTZ devices.

      Section 1.3 discusses the advantages and drawbacks of the different acquisition modalities with special attention given to the use of magnification devices in unconstrained environments. The use of a highly narrow field of view introduces a multitude of challenges that restrict the workability of PTZ-based systems in outdoor scenarios (inter-camera calibration) and degrade image quality (e.g., out-of-focus, incorrect exposure).

      In Section 1.4, we present a comprehensive collection of the state-of-the-art systems for unconstrained scenarios. The systems are organized according to the modalities of unconstrained biometric data acquisition: (i) low-resolution systems; and (ii) PTZ-based systems. In the former, most approaches rely on soft biometrics (e.g., gait) for recognizing individuals in unconstrained scenarios, since the reduced discrimination of data inhibits the use of hard biometrics. The use of these traits is only feasible when relying on super-resolution. In the latter, the systems are grouped with respect to the biometric trait that they were designed to acquire. Despite the advantages of iris regarding recognition performance, its reduced size curtails the maximum stand-off distance of these systems. Consequently, most approaches have introduced multiple strategies to acquire facial imagery at large stand-off distances. The workability of these approaches in real unconstrained environments is discussed by analyzing their feasibility in surveillance scenarios, which are among of the most representative examples of these environments. Among these systems, particular attention is given to the works of Park et al. [9] and Neves et al. [10], which are two representative examples of PTZ-based systems capable of acquiring high-resolution face images in surveillance scenarios. Finally, Section 1.5 concludes the

      Enjoying the preview?
      Page 1 of 1