Integration of Gait and Side Face for Human Recognition in Video

Author(s):  
Qi-Shen Li ◽  
Zhi-Tian Lu ◽  
Dan-Dan Zhang
Keyword(s):  
Author(s):  
Xiaoli Zhou ◽  
Bir Bhanu

This chapter introduces a new video based recognition system to recognize noncooperating individuals at a distance in video, who expose side views to the camera. Information from two biometric sources, side face and gait, is utilized and integrated for recognition. For side face, an enhanced side face image (ESFI), a higher resolution image compared with the image directly obtained from a single video frame, is constructed, which integrates face information from multiple video frames. For gait, the gait energy image (GEI), a spatiotemporal compact representation of gait in video, is used to characterize human walking properties. The features of face and gait are extracted from ESFI and GEI, respectively. They are integrated at both of the match score level and the feature level by using different fusion strategies. The system is tested on a database of video sequences, corresponding to 45 people, which are collected over several months. The performance of different fusion methods are compared and analyzed. The experimental results show that (a) the idea of constructing ESFI from multiple frames is promising for human recognition in video and better face features are extracted from ESFI compared to those from the original side face images; (b) the synchronization of face and gait is not necessary for face template ESFI and gait template GEI; (c) integrated information from side face and gait is effective for human recognition in video. The feature level fusion methods achieve better performance than the match score level methods fusion overall.


Author(s):  
Natalia Marandiuc

The chapter proposes that human beings are conditioned by a double embeddedness: humans are immersed in inescapable frameworks of meaning and shaped by relationships of significance. In dialogue with Charles Taylor, the chapter discusses how these two elements are constitutive features of human subjectivity and how they relate to each other. In order to operate, subjectivity needs a horizon of meaning, which accrues in relationships of attachment that, in turn, thrive under the canopy of common meaning. After discussing the specificity of one such framework, the culture of authenticity, the chapter delves more deeply into one of its paradoxical dimensions: recognition. It is shown how human recognition from loving others is an ineliminable trait for an authentic self, the implication of which is that relationships of significance constitute relational homes that “house” the human self as it grows and flourishes and as it heals when broken.


Author(s):  
Eckart Uhlmann ◽  
Linus Lichtschlag

AbstractIn grinding, the design of the dressing process is an essential part of work preparation and restoration of the grinding wheel’s profile and cutting ability. In contrast to most grinding processes, the choice of dressing parameters in double face grinding with planetary kinematics has so far only been experience-based. As a consequence, the dressing process causes a higher degree of tool wear than the machining of the workpieces. A focused design of the dressing process based on a scientific data could help to improve the ecological and the economic efficiency by reducing tool wear and the amount of dressing tools used. In this paper, methods for determining the wear condition and the result of the dressing process, including macro- and microscopic characteristic are presented. This includes a correlation analysis between parameters of wear characteristics and workpiece surface quality. Furthermore, technological investigations are carried out in order to systematically limit the main influencing factors on the dressing process. As a result, the parameters dresser grain size dgd, rotational speed ratio nld and the machined dresser height ∆hd are identified as significant for dressing. The knowledge about their principal influence on the dressing result could provide the basis for further research.


2013 ◽  
Vol 2013 ◽  
pp. 1-14 ◽  
Author(s):  
Sambit Bakshi ◽  
Pankaj K. Sa ◽  
Banshidhar Majhi

A novel approach for selecting a rectangular template around periocular region optimally potential for human recognition is proposed. A comparatively larger template of periocular image than the optimal one can be slightly more potent for recognition, but the larger template heavily slows down the biometric system by making feature extraction computationally intensive and increasing the database size. A smaller template, on the contrary, cannot yield desirable recognition though the smaller template performs faster due to low computation for feature extraction. These two contradictory objectives (namely, (a) to minimize the size of periocular template and (b) to maximize the recognition through the template) are aimed to be optimized through the proposed research. This paper proposes four different approaches for dynamic optimal template selection from periocular region. The proposed methods are tested on publicly available unconstrained UBIRISv2 and FERET databases and satisfactory results have been achieved. Thus obtained template can be used for recognition of individuals in an organization and can be generalized to recognize every citizen of a nation.


2021 ◽  
pp. 004051752110550
Author(s):  
Norina Asfand ◽  
Virginija Daukantienė

Different fiber blends, knit patterns, and treatments may be applied to increase the functionality and comfort of knitted fabrics. In this research, the physical properties and bending stiffness of 1 × 1 rib and half-milano rib fabrics with four fiber blends (90% cotton/10% antistatic PET, 80% cotton/20% antistatic PET, 70% cotton/30% antistatic PET, and 65% cotton/35% antistatic PET) applied to each knit pattern were studied. The effect of fabric direction (course and wale), technical side (face side and back side), and treatment (dying, softening with Aquasoft® SI hydrophilic softener, and Polygiene VO-600 antibacterial finish) on the physical characteristics and bending stiffness of the fabrics was evaluated. The results revealed that dyeing and softening increased the fabric area density and both wale and course densities and decreased fabric thicknesses compared to the control fabrics. The antibacterial finish applied to the softened samples did not change the physical properties. Bending stiffness in the course direction was lower than in the wale direction, and it was higher for technical face samples than for technical back ones. The 1 × 1 rib knitted fabrics showed lower stiffness than the half-milano rib fabrics. Treatment of the investigated fabrics decreased bending stiffness for both treatment sample groups compared to the control group.


2011 ◽  
Vol 368-373 ◽  
pp. 489-494 ◽  
Author(s):  
Xu Lin Tang ◽  
Jian Cai ◽  
Qing Jun Chen ◽  
An He ◽  
Chun Yang

In order to study the mechanical behavior of the joint between concrete filled steel tubular column and beam with discontinuous column tube at the joint zone under axial pressure, the finite element analysis software ANSYS is adopted for parametric analysis and the analysis results are compared with experimental ones. The principal compressive stress is mainly transmitted by the inside area of the joint which is subjected to local compression if it is low, but extends to more outside areas of the joint if it is high. The radial compressive stress, which is the confined stress of the ring beam to the core concrete of the joint, keeps the same as that the width of the ring beam equal to the diameter of the core area of the joint. The vertical strain on the edge of the joint, which would lead to horizontal annular cracks in the side face of the ring beam, changes from tension in the whole height to tension only in the top part and compression in the lower part of the joint, which is consistent with the experimental phenomenon.


Sign in / Sign up

Export Citation Format

Share Document