Facial landmark automatic identification from three dimensional (3D) data by using Hidden Markov Model (HMM)

Landmark identification is one of the fundamental aspects and a necessary step of Three Dimensional (3D) data process. Numerous methods for landmark identification have been proposed, but none with high efficiency, good robustness and strong adaptability has been found yet. In this study, a novel method was developed and applied on a 120 subject's database to automatically identify facial landmarks from 3D facial scanned data. Spin Image (SI) is used to extract local feature and Hidden Markov Model (HMM) is adopted to implement the landmark identification procedure. Eleven HMMs were trained to identify different facial landmarks, respectively. We developed a three-hierarchy experiment to test the validity and reliability of the algorithm. Results show that SI is highly efficient and robust to extract facial feature. The maximum landmark recognition rate reached 95.9%. The influence of parameters in SI on the validity and reliability of landmark identification was also investigated. It was found that Bin Size of SI can improve or reduce Identification Accuracy Rate (IAR) by Bin Size value variation. The mean value of IAR increases with the Bin Size until Bin Size reaches 10, when IAR acquires its maximum value 100% and remains constant before Bin Size reaches 65. After that, IAR dropped with the increase of Bin Size, and the velocity of the drop keeps increasing until it reaches the minimum value. In contrast, Support Angle of SI influences IAR positively. Support Angle starts to function at the value of 10°. Then, IAR increases with it until Support Angle reaches the degree of 90, when IAR acquired and maintained a constant maximum value of 100%. At last, a comparison was made to address the superiority of HMM over Artificial Neural Network (ANN) on facial landmark identification and we figured out the direction of future work as well. Besides the parameters of SI as discussed in this study, we can investigate the influence of the point sampling granularity on the identification accuracy as well in the future.Relevance to industryProcessing the 3D anthropometric data in order to make it useful for the design of products and facilities is still a challenging problem. One of the typical difficulties is that there is no valid human anatomical landmarks identification method. The improvement of reliability and accuracy of the automatic 3D landmarks identification algorithm for various human body shapes will reduce the time and cost for performing manual landmark palpating and dimension extraction. This work is expected to bring benefits to human-dimension-related ergonomic design and improvement.     

An analysis of the geometry of light-striping vision systems for feedrate control in robot welding and other industrial processes

Light-stripping, whereby a laser or other source of a stripe of light in conjunction with a single camera can provide three-dimensional information of a scene, can be used to estimate the volume of a seam gap for welding, filling, or gluing robots, and thus provide automated feedrate control. The geometry of light-striping systems is analyzed to yield an efficient method to map the locations of stripe pixels in the image to three-dimensional coordinates. Methods are discussed to determine fill-points by recognizing the pattern produced by seam walls despite noise. Combined with computation of areas and volumes, the steps simplify to an effective algorithm for microprocessor implementation.     

Integration of Hough Transform of lines and planes in the framework of conformal geometric algebra for 2D and 3D robot vision

This paper presents the application of 2D and 3D Hough Transforms together with conformal geometric algebra to build 3D geometric maps using the geometric entities of lines and planes. Among several existing techniques for robot self-localization, a new approach is proposed for map matching in the Hough domain. The geometric Hough representation is formulated in such a way that one can easily relate it to the conformal geometric algebra framework; thus, the detected lines and planes can be used for algebra-of-incidence computations to find geometric constraints, useful when perceiving special configurations in 3D visual space for exploration, navigation, relocation and obstacle avoidance. We believe that this work is very useful for 2D and 3D geometric pattern recognition in robot vision tasks.     

3D-2D deep convolutional neural network (DCNN) Cascade for robust video face identification

Multimedia Tools and Applications - This paper proposes a novel video face identification method, named “3D-2D-DCNN cascade” that serially combines 3D and 2D deep convolutional neural...     

Artificial bee colony-based fuzzy c means (ABC-FCM) segmentation algorithm and dimensionality reduction for leaf disease detection in bioinformatics

The Journal of Supercomputing - The rapid increase in human population has necessitated a corresponding increase in agricultural production. The advancements made in the arena of genomics and...     

A rapid polymerisation process realizing 3D biocompatible structures in a microfluidic channel suitable for genetic analysis

Surface probe immobilisation is a complex and time consuming task undertaken prior to microfluidic integration, this requires surface functionalisation, biomolecule spotting, incubation and blocking steps. Traditional bonding techniques (anodic, thermal, etc.) or adhesives (UV cured) used to seal fluidic systems may denature biomolecules due to high temperature or vapour effects, thus bonding techniques such as thin film laminate or PDMS are used to seal systems, with substrate-fluidic alignment required prior to bonding. We propose a technique allowing probe DNA molecules to be immobilised in a sealed microfluidic system using (3D) hydrogel structures without any alignment steps. A prepolymer solution is introduced to the channels where photo-polymerisation is undertaken forming 3D structures covalently attached to the channel surface. We use a photo-initiated prepolymer material poly-ethylene-glycol (PEG) to form structures containing probe DNA. This process is fast compared to conventional biomolecule immobilisation techniques and is also biocompatible, this direct write approach removes overnight immobilisation/incubation of the probe DNA, it also facilitates immobilisation within a sealed fluidic system where conventionally DNA probe spots must be immobilised prior to channel sealing. We consider the transport of target DNA from bulk analyte to the 3D gel structure and evaluate hybridisation within the microfluidic system.     

Thermochemical analysis for the reduction behavior of FeO in EAF slag via Aluminothermic Smelting Reduction (ASR) process: Part Ι. Effect of aluminum on Fe & Mn recovery

We investigated Fe recovery from EAF slag by means of Aluminothermic Smelting Reduction (ASR) at 1773 K, especially the quantitative effect of initial Al/FeO molar ratio upon the Fe recovery. Both calculated and experimentally measured system temperatures continuously increased with increasing initial Al/FeO molar ratio. Furthermore, to predict the reduction behavior we calculated variations in the slag composition by using FactSage™ 7.0 software. FeO and Al₂O₃ contents in molten slag varied sharply within the first 5 min of the reaction and stabilized soon thereafter. The aluminothermic reduction of FeO appeared to proceed rapidly and in good stoichiometric balance, based upon the mass balance between the consumption of FeO and MnO (ΔFeO and ΔMnO) and the production of Al₂O₃ (∆Al₂O₃). Adding an optimal amount of Al (Al/FeO molar ratio ~ 0.8) yielded a Fe recovery of about 90%. Furthermore, the Mn could also be reduced from the EAF slag in the case of excess Al addition (Al/FeO≥0.8). The solid compound spinel (MgO·Al₂O₃) was precipitated from the slag during the FeO reduction, as confirmed by means of XRD analysis and thermochemical computations. Herein, the mechanism of ASR reaction between FeO in molten slag and Al is explained in several steps.     

Thermochemical analysis for the reduction behavior of FeO in EAF slag via Aluminothermic Smelting Reduction (ASR) process: Part II. Effect of aluminum dross and lime fluxing on Fe and Mn recovery

We investigated Fe recovery from EAF slag by means of aluminothermic smelting reduction (ASR) at 1773 K with Al dross as the reductant, especially the effect of the added amount of the fluxing agent CaO on the Fe recovery. The maximum reaction temperature calculated using FactSage™ 7.0 decreased with increasing CaO addition, but the experimentally measured maximum temperatures increased with increasing CaO addition. We calculated the amounts of various phases before and after Al dross addition under different conditions of added CaO. FeO and Al₂O₃ contents in molten slag sharply varied within the first 5 min of the reaction, stabilizing soon thereafter. The aluminothermic reduction of FeO appeared to proceed rapidly and in good stoichiometric balance, based upon the mass balance between the consumption of FeO and MnO (ΔFeO and ΔMnO) and the production of Al₂O₃ (∆Al₂O₃). Iron recovery from EAF slag was maximized at about 90% when 40 g of CaO was added to 100 g slag. Furthermore, Mn could also be reduced from the EAF slags by the metallic Al in the Al dross reductant. The solid compounds of spinel (MgO∙Al₂O₃) and MgO were precipitated from the slag during the FeO reduction reaction, as confirmed by means of XRD analysis and thermochemical computations. To maximize Fe recovery from EAF slag, it is crucial to control the slag composition, namely to ensure high fluidity by suppressing the formation of solid compounds.     

Enhanced reliable reactive routing (ER3) protocol for multimedia applications in 3D wireless sensor networks

Sensor networks designed especially for the multimedia applications require high data rate and better Quality of Service (QoS). Offering a reliable and energy efficient routing technique in a harsh and complex three-dimensional (3-D) environment for multimedia applications is a challenging job. Geo-routing and geometric routing have been efficient routing schemes for two-dimensional (2-D), but are unable to work properly for 3-D sensor networks. In order to enhance the resilience to link the dynamics in the 3-D sensor network, in this research an Enhanced Reliable Reactive Routing (ER3) is proposed. ER3 is an advancement to the existing reactive routing schemes, to provide energy efficient and reliable routing of data packets in the complex 3-D sensor networks for multimedia applications. The major attraction of ER3 is its backoff scheme, which occurs in the route discovery phase. In backoff scheme robust pilot paths formed between the source and destination are calculated to enable cooperative forwarding of the data packets. The data packets in ER3 are forwarded greedily to the destination from the source and doesn’t require any prior location information of the nodes. The encompassing simulations suggest that the ER3 outperforms the existing routing protocols on the basis of energy efficiency, low latency and high packet delivery ratio.

     

A Hybrid Method for Quality Evaluation in the Context of Use for Mobile (3D) Television

Controlled psychoperceptual quality evaluation experiments are used to assess the excellence of produced audiovisual quality from fundamental signal processing algorithms to consumer services. When compromising produced quality for consumer services, used in dynamic and heterogeneous mobile contexts, the ecological validity of conventional quality evaluation methods can be questioned. The goal of this paper is to develop a method for evaluating the experienced multimedia quality in the context of use. We conducted three studies where the quality of mobile 2D and 3D television was assessed in three different field contexts, one simulated context and one controlled laboratory situation when audio-video compression and transmission parameters were varied. We propose a hybrid method for the design, data-collection and analysis of the experiments in the contexts of use. Its novelty is to complement conventional quantitative quality evaluation with concrete tools to identify factors that surround the assessment in the context. The methodological framework is part of our long-term aim to measure and understand the user-centered quality of experience.     

新能源汽车节能减排技术研究进展(3)——传感器系统

描述了电动力汽车(EV)、混合动力汽车(HEV)和燃料电池汽车(FCV)节能减排技术的研究进展,主要从以下三方面论述:发动机系统、能量管理系统、传感器系统,并指出了存在问题和发展方向.本文介绍了传感器系统,包括新型汽车传感器、新的零部件和新的系统应用.     

Using the analytic network process (ANP) in a SWOT analysis - A case study for a textile firm

Strengths, Weaknesses, Opportunities and Threats (SWOT) analysis does not provide an analytical means to determine the importance of the identified factors or the ability to assess decision alternatives according to these factors. Although the analysis successfully pinpoints the factors, individual factors are usually described briefly and very generally. For this reason, SWOT analysis possesses deficiencies in the measurement and evaluation steps. Although the analytic hierarchy process (AHP) technique removes these deficiencies, it does not allow for measurement of the possible dependencies among the factors. The AHP method assumes that the factors presented in the hierarchical structure are independent; however, this assumption may be inappropriate in light of certain internal and external environmental effects. Therefore, it is necessary to employ a form of SWOT analysis that measures and takes into account the possible dependency among the factors. This paper demonstrates a process for quantitative SWOT analysis that can be performed even when there is dependence among strategic factors. The proposed algorithm uses the analytic network process (ANP), which allows measurement of the dependency among the strategic factors, as well as AHP, which is based on the independence between the factors. Dependency among the SWOT factors is observed to effect the strategic and sub-factor weights, as well as to change the strategy priorities.     

LFP: A PC-program for ligand-field analysis of 3d(n) ions in Oh and lower symmetries

A modular and efficient version of PC program for calculating ligand-field parameters, i.e. crystal-field model (CFM) and angular overlap model (AOM) is presented. The LFP program is designed to calculate the ligand-field parameters of low symmetry transition metal complexes. It is based on the general method for the analysis of central ion states distortion using group theory. The program has not closed form. It will be extended, according to spectroscopic studies in our laboratory. It is written in FORTRAN language.     

Multi-scale kernel Fisher discriminant analysis with adaptive neuro-fuzzy inference system (ANFIS) in fault detection and diagnosis framework for chemical process systems

Fault detection and diagnosis (FDD) framework is one of safety aspects that is important to the industrial sector to ensure its high-quality production and processes. However, the development of FDD system in chemical process systems could have difficulties, e.g. highly nonlinear correlation within the variables, highly complex process, and an enormous number of sensors to be monitored. These issues have encouraged the development of various approaches to increase the effectiveness and robustness of the FDD framework, such as the wavelet transform analysis, where it has the advantage in extracting the significant features in both time and frequency domain. It has motivated us to propose an extension work of the multi-scale KFDA method, where we have modified it with the implementation of Parseval’s theorem and the application of ANFIS method to improve the performance of the fault classification. In this work, through the implementation of Parseval’s theorem, the observation of fault features via the energy spectrum and effective reduction in DWT analysis data quantity can be accomplished. The extracted features from the multi-scale KFDA method are used for fault diagnosis and classification, where multiple ANFIS models were developed for each designated fault pattern to increase the classification accuracy and reduce the diagnosis error rate. The fault classification performance of the proposed framework has been evaluated using a benchmarked Tennessee Eastman process. The results indicated that the proposed multi-scale KFDA-ANFIS framework has shown the improvement with an average of 87.02% in classification accuracy over the multi-scale PCA-ANFIS (78.90%) and FDA-ANFIS (70.80%).

     

A new recurslve method for the analysis of linear time invariant dynamic systems via double-term triangular functions （DTTF） in state space environment

This paper presents a new recursive method for system analysis via double-term triangular functions (DTTF) in state space environment. The proposed method uses orthogonal triangular function sets and proves to be more accurate as compared to single term Walsh series (STWS) method with respect to mean integral square error (MISE). This has been established theoretically and comparison of error with respect to MISE is presented for clarity. A numerical example is treated to establish the proposed method. Relevant curves for the solutions of states of the dynamic system are also presented with plots of percentage error for DTTF-based analysis.     

Wafer bonding with nano-imprint resists as sacrificial adhesive for fabrication of silicon-on-integrated-circuit (SOIC) wafers in 3D integration of MEMS and ICs

In this paper, we present the use of thermosetting nano-imprint resists in adhesive wafer bonding. The presented wafer bonding process is suitable for heterogeneous three-dimensional (3D) integration of microelectromechanical systems (MEMS) and integrated circuits (ICs). Detailed adhesive bonding process parameters are presented to achieve void-free, well-defined and uniform wafer bonding interfaces. Experiments have been performed to optimize the thickness control and uniformity of the nano-imprint resist layer in between the bonded wafers. In contrast to established polymer adhesives such as, e.g., BCB, nano-imprint resists as adhesives for wafer-to-wafer bonding are specifically suitable if the adhesive is intended as sacrificial material. This is often the case, e.g., in fabrication of silicon-on-integrated-circuit (SOIC) wafers for 3D integration of MEMS membrane structures on top of IC wafers. Such IC integrated MEMS includes, e.g., micro-mirror arrays, infrared bolometer arrays, resonators, capacitive inertial sensors, pressure sensors and microphones.     

Study of the Radio Frequency (RF) performance of a Wafer-Level Package (WLP) with Through Silicon Vias (TSVs) for the integration of RF-MEMS and micromachined waveguides in the context of 5G and Internet of Things (IoT) applications. Part 2: parameterised 3D model and optimisation

Microsystem Technologies - This study discusses the exploitation of a full-3D methodology for the electromagnetic simulation of a Wafer-Level Packaging solution featuring Through Silicon Vias...