Search

Sheet metal stamping is widely used for high-volume production. Despite the wide adoption, it can lead to defects in the manufactured components, making their quality unacceptable. Because of the variety of defects that can occur on the final product, human inspectors are frequently employed to detect them. However, they can be unreliable and costly, particularly at speeds that match the stamping rate. In this paper, we propose an automatic inspection framework for the stamping process that is based on computer vision and deep learning techniques. The low cost, remote sensing capability and simple implementation mean that it can be easily deployed in an industrial setting. A particular focus of this research is to account for the harsh lighting conditions and the highly reflective nature of products found in manufacturing environments that affect optical sensing techniques by making it difficult to capture the details of a scene. High dynamic range images can capture details of an environment in harsh lighting conditions, and in the context of this work, can capture highly reflective metals found in sheet metal stamping manufacturing. Building on this imaging technique, we propose a framework including a deep learning model to detect defects in sheet metal stamping parts. To test the framework, sheet metal ‘Nakajima’ samples were pressed with an industrial stamping press. Then optimally exposed, sequence of exposures, tone-mapped and high dynamic range images of the samples were used to train convolutional neural network-based detectors. Analysis of the resulting models showed that high dynamic range image-based models achieved substantially higher accuracy and minimal false-positive predictions.

In this work, we attempted to find out the relationship between different gait patterns and their corresponding cognitive states by using different statistical and machine learning approaches. This paper strongly focusses on the simulations followed by implementation of the proposed cognitive states i.e. (i) EmotionOriented State (EOS) (ii) Thinking Oriented State (TOS) (iii) Memory Oriented State(MOS) (iv) Simple Regular Oriented State (SROS). A novel approach was implemented by creating different environmental contexts for different gaits in our lab. An experimental method was performed to isolate movement artifact using Independent Component Analysis from recorded EEG(Electroencephalogram) signals. Measurement of joint angles from joint positions captured using Kinect V2 sensors was done with the help of OpenSim software. The relationship between different gaits and mental states was established using Pearsons Correlation Coefficient, ANOVA(Analysis of variance) and SVM(Support Vector Machine) classifier respectively. A strong relationship was found between them. The SVM classifier for the EOS and the non-EOS states based on joint angles inferred an accuracy of 81.08%. The ROC Curve for SVM classification depicted an AUC (area under the curve) of 0.9724.

Investigating features from gait biometric is an essential step for solving human identification problems, medical diagnosis, monitoring and rehabilitation. This chapter addresses the use of a low-cost Kinect V2.0 sensor along with hand-crafted and deep learning techniques for the investigation. As deep neural network is a representation of the most effective machine learning technology in biomedical domain, its usage in this work is extremely significant to determine the accuracy, reliability and feasibility of observational assessments of spatio-temporal features of gait. A novel approach for human detection and tracking is proposed in this chapter, which involves gait feature learning principles from Color Depth videos. A proposed semi-dynamic object tracking algorithm is used to extract the human object. Gait energy image (GEI) representation is exemplified to train a 2D Convolutional Neural Network for automatic feature extraction in one case. In another case, kinematic hip joint angles are extracted via the stick model generated using body aspect ratios. A maximum accuracy of 95.1% is attained from the CNN models, which infers that the gait features automatically extracted are informative enough. Reliability analysis of all features is carried out using statistical methods such as hypothesis testing (T-test as sample size > 30), Kolmogorov-Smirnov (KS) test, Pearson’s r test and energy distance test to ensure feature learning for biometric applications. Almost all the outcomes illustrate that the features come from the same population mean (as critical region value of 0.05 is crossed) and hence are promising for assessing the strategies that impact the inter-record contrasts among motion signatures.

Investigating new features for human cognitive state classification is an intiguing area of research with Electroencephalography (EEG) based signal analysis. We plan to develop a cost-effective system for cognitive state classification using ambulatory EEG signals. A novel event driven environment is created using external stimuli for capturing EEG data using a 14-channel Emotiv neuro-headset. A new feature extraction method, Gammatone Cepstrum Coefficients (GTCC) is introduced for ambulatory EEG signal analysis. The efficacy of this technique is compared with other feature extraction methods such as Discrete Wavelet Transformation (DWT) and Mel−Frequency Cepstral Coefficients (MFCC) using statistical metrics such as Fisher Discriminant Ratio (FDR) and Logistic Regression (LR). We obtain higher values for GTCC features, demonstrating its discriminative power during classification. A superior performance is achieved for the EEG dataset with a novel ensemble feature space comprising of GTCC and MFCC. Furthermore, the ensemble feature sets are passed through a proposed 1D Convolution Neural Networks (CNN) model to extract novel features. Various classification models like Probabilistic neural network (P-NN), Linear Discriminant Analysis (LDA), Multi-Class Support Vector Machine (MCSVM), Decision Tree (DT), Random Forest (RF) and Deep Convolutional Generative Adversarial Network (DCGAN) are employed to observe best accuracy on extracted features. The proposed GTCC, (GTCC+MFCC) & (GTCC +MFCC +CNN) features outperform the state-of-the-art techniques for all cases in our work. With GTCC+MFCC feature space and GTCC+MFCC+CNN features, accuracies of 96.42% and 96.14% are attained with the DCGAN classifier. Higher classification accuracies of the proposed system makes it a cynosure in the field of cognitive science.

Human mental state classification using Electroen-cephalogram(EEG) signal is one of the dynamic investigating areas in developing intelligent machine frameworks. In this paper, we propose an ambulatory cognitive state classification system using statistical feature analysis. The aim is to develop a realtime system which captures human cognitive states through computer-mediated help based on physiological signals. The walking cognitive state estimator is developed using a realtime Augmented Cognition (AugCog) framework. Six different normality testing methods i.e. Kolmogorov-Smirnov, Anderson Darling, Cramer-Von Mises, Shapiro Wilk, Jarque-Bera, D'Ago-stino and Pearson's test are applied to achieve better accuracy. Box - Cox - transformation is also applied to ensure whether the data follows a normal distribution. We apply Fisher Discriminant Ratio (FDR) for selecting the most discriminative feature amongst all the statistical features (i.e. Mean, Median, Mode, Standard Deviation, Variance, Skewness and Kurtosis) obtained from the signal. Various machine learning methods are applied on the extracted features for training, testing and validation. Probabilistic neural network (P-NN) with Kurtosis feature is found to produces a maximum accuracy of 92.61 % as compared to other classifiers.

Human pose estimation in a gait sequence is an essential step for solving human identification problems, medical diagnosis, monitoring, and rehabilitation. In this paper, a low-cost Kinect V2.0 sensor is used for investigating motion signatures obtained from normal healthy adults. The purpose of this study is to determine the accuracy and reliability of observational assessments of spatio-temporal features. A novel approach for human detection and tracking is proposed, which involves gait feature learning principles from depth and RGB video. In the first step, a human object from the depth image is extracted using the proposed semi-dynamic object tracking algorithm, and a stick model is generated using body aspect ratios to extract hip angles. In the second step, the gait energy image (GEI) representation is utilized for training a 2D Convolutional Neural Network (AlexNet) for automatic feature extraction. A key point detection algorithm is proposed for estimating knee, hip, and ankle joints from RGB gait videos. The reliability analysis of motion signatures is performed using various statistical methods to ensure feature learning for multi-scenario applications. The statistical results are promising for evaluating the methods which influence the inter-record differences among motion signatures.

Human gait analysis using microsoft Kinect sensor is an intriguing area of research. Fusing multiple sensors’ data for clinical gait analysis using calibrated instruments helps in producing more accurate results. A novel technique for spatial calibration is proposed and implemented in this paper. This paper emphasizes on a novel technique of using five Kinect V2 sensors (four clients and one server) and data fusion methods to create unified skeletons for subject-wise gait analysis. These eradicate the problems of inaccurate skeleton poses caused due to occlusions or tracking failures from a single Kinect which otherwise remains a problem in most vision-based sensing systems. Two methods are compared for estimating states of discrete time linear systems. The first one is classical Kalman filtering, which gives accurate results when state disturbances are assumed to be Gaussian white noises and measurement noises and the statistical properties are procurable. Secondly, a Set-Membership filter is used which relies upon the principle of prediction and correction as well. A novel Set-Membership filtering approach is proposed where the measurement noise is modelled by multivariate Gaussian probability density function bounded by − 1 to +1. Based on our observations of the linear frameworks joined with interval investigation, the two phases of the estimator are done in a productive way. Both the fusion techniques are tested on overground and treadmill data and the results are validated and compared with ground truth obtained using Qualisys motion capture systems. The proposed approach is also compared quantitatively with state-of-the-art methods.

Human cognitive state classification using Electroencephalogram (EEG) signal is one of the dynamic exploring regions in emerging smart machine systems. It motivates to build estimator for revealing the human cognitive behaviours for different environments. In this work, we present an operational human cognitive behaviour detection system based on ambulatory EEG signal analysis. A novel event driven environment is created using external stimuli to collect those signals. They are captured using 14 channel Emotiv neuro-headset. Mel-Frequency Cepstral Coefficients (MFCC) is a very popular feature extraction method in acoustic signal processing. In spite of it’s popularity, it has not been explored much when it comes to EEG signals. This paper proposes a novel technique of applying MFCC feature extraction method for ambulatory EEG signals and the results are found to be promising. Besides other feature extraction methods such as: Power Spectral Density (PSD), Discrete Wavelet Transformation (DWT) are used to extract intrinsic features from EEG signal. A statistical technique, Fisher Discriminant Ratio (FDR) is applied on them to evaluate the robustness of each feature. A higher FDR value is observed from MFCC features which demonstrate its discriminative power during classification. Different machine learning techniques such as Probabilistic neural network (P-NN), k-nearest neighbor (kNN), multi-class support vector machine (MCSVM) are applied for training, testing and validating the extracted features. A comparative analysis is discussed for each classifier coupled with each feature. It is found that P-NN with MFCC feature produces the maximum accuracy of 92.61% amongst all the remaining classifiers.

IDDRG - Conference Proceedings - Tools and Technologies for the Processing of ultra high strength steels