Face Pose Alignment with Event Cameras

Event camera (EC) emerges as a bio-inspired sensor which can be an alternative or complementary vision modality with the benefits of energy efficiency, high dynamic range, and high temporal resolution coupled with activity dependent sparse sensing. In this study we investigate with ECs the problem of face pose alignment, which is an essential pre-processing stage for facial processing pipelines. EC-based alignment can unlock all these benefits in facial applications, especially where motion and dynamics carry the most relevant information due to the temporal change event sensing. We specifically aim at efficient processing by developing a coarse alignment method to handle large pose variations in facial applications. For this purpose, we have prepared by multiple human annotations a dataset of extreme head rotations with varying motion intensity. We propose a motion detection based alignment approach in order to generate activity dependent pose-events that prevents unnecessary computations in the absence of pose change. The alignment is realized by cascaded regression of extremely randomized trees. Since EC sensors perform temporal differentiation, we characterize the performance of the alignment in terms of different levels of head movement speeds and face localization uncertainty ranges as well as face resolution and predictor complexity. Our method obtained 2.7% alignment failure on average, whereas annotator disagreement was 1%. The promising coarse alignment performance on EC sensor data together with a comprehensive analysis demonstrate the potential of ECs in facial applications.

Prediction of the Hardness of X12m Using Barkhausen Noise and Chebyshev Polynomials Regression Methods

Barkhausen noise (BN) is electromagnetic pulse sequence that could be used to nondestructively predict the properties of materials such as hardness, residual stress and carbon content. Current BN signal analysis methods fail to describe the highly variated BN signal and achieve high regression accuracy due to the low interpretability of neural network and limited capacity of mathematical regression tools. In this paper, two multi-variable regression tools, named partial Chebyshev polynomial regression (PCPR) and Mutual Information-based Feature Selection with Class-dependent Redundancy and multi-variable Chebyshev polynomials regression (MIFS-CR+MCPR), are employed for the first time to predict the hardness of Cr12MoV steel (i.e. X12m). Combined with Chebyshev polynomials, our regression tools are designed on the basis of cascaded regression and mutual-information-based feature selection. As represented by the experimental results for predicting the hardness of X12m, the proposed method outperforms other comparative methods including neural network and partial linear square regression method.

Constrained Local Models (CLM) For Facial Feature Extraction using CLNF and SVR as Patch Experts

Methods for detection of facial characteristics have again developed greatly in recent times. However, they also argue in the presence of poor lighting conditions for amazing pose or occlusions. A well-established group of strategies for facial feature extraction is the Constrained Local Model (CLM). Recently, they are bringing cascaded regression-built methodologies out of favor. This is because the failure of presenting nearby CLM detectors to model the highly complex special signature look affected to a small degree by voice, illumination, facial hair and make-up. This paper keeps tabs on execution to collect facial features for the Constrained Local Model (CLM). CLM model relies on patch model to collect facial image demand features. In this paper patch model built using Support Vector Regression (SVR) and Constrained Local Neural Field (CLNF). We show that the CLNF model exceeds SVR by a large margin on the LFPW database to identify facial landmarks.

Cascaded Regression-Based Segmentation of Cardiac CT under Probabilistic Correspondences

The creation of 3D models for cardiac mapping systems is time-consuming, and the models suffer from issues with repeatability among operators. The present study aimed to construct a double-shaped model composed of the left ventricle and left atrium. We developed cascaded-regression-based segmentation software with probabilistic point and appearance correspondence. Group-wise registration of point sets constructs the point correspondence from probabilistic matches, and the proposed method also calculates appearance correspondence from these probabilistic matches. Final point correspondence of group-wise registration constructed independently for three surfaces of the double-shaped model. Stochastic appearance selection of cascaded regression enables the effective construction in the aspect of memory usage and computation time. The two correspondence construction methods of active appearance models were compared in terms of the paired segmentation of the left atrium (LA) and left ventricle (LV). The proposed method segmented 35 cardiac CTs in six-fold cross-validation, and the symmetric surface distance (SSD), Hausdorff distance (HD), and Dice coefficient (DC), were used for evaluation. The proposed method produced 1.88 ± 0.37 mm of LV SSD, 2.25 ± 0.51 mm* of LA SSD, and 2.06 ± 0.34 mm* of the left heart (LH) SSD. Additionally, DC was 80.45% ± 4.27%***, where * p < 0.05, ** p < 0.01, and *** p < 0.001. All p values derive from paired t-tests comparing iterative closest registration with the proposed method. In conclusion, the authors developed a cascaded regression framework for 3D cardiac CT segmentation.