Discontinuous Features Research Articles

Magnetic Discontinuities in the Solar Wind and Magnetosheath: Magnetospheric Multiscale Mission (MMS) Observations

We perform a statistical investigation of the geometric features of interplanetary discontinuities (IDs) in the near-Earth solar wind and magnetosheath, by utilizing 14 months of Magnetospheric Multiscale mission data. 117,669 IDs are collected, including 108,049 events in the solar wind and 6399 events in the magnetosheath, with the remnant in the magnetosphere or near the bow shock/magnetopause. We find the following: (1) the ID occurrence rate is 17.0 events hr−1 in the solar wind and 5.5 events hr−1 in the magnetosheath, (2) the field rotation angles during ID crossings in the magnetosheath exhibit a two-exponential distribution with a breakpoint at 50°, which is not observed for IDs in the solar wind, (3) the magnetosheath IDs with small field rotation angles tend to be clustered, (4) by classifying the IDs into rotational discontinuities (RDs), tangential discontinuities (TDs), either TDs or RDs (EDs), and neither TDs nor RDs (NDs), we estimate RD:TD:ED:ND = 68%:5%:20%:7% in the solar wind, and RD:TD:ED:ND = 15%:44%:18%:23% in the magnetosheath, (5) the occurrence rates of RDs and TDs are, respectively 7.95 and 0.58 events hr−1 in the solar wind, and 0.57 and 1.60 events hr−1 in the magnetosheath, (6) RDs are more likely to propagate antisunward in the plasma rest frame, especially in the magnetosheath, and (7) the average thicknesses of the RDs and TDs are estimated, respectively, as 10.4 and 8.1 proton gyroradii (r p ) in the solar wind, and 17.4 and 5.0 r p in the magnetosheath. This work can improve our understanding of IDs’ interaction with the terrestrial bow shock.

A Novel Reference-Based and Gradient-Guided Deep Learning Model for Daily Precipitation Downscaling

The spatial resolution of precipitation predicted by general circulation models is too coarse to meet current research and operational needs. Downscaling is one way to provide finer resolution data at local scales. The single-image super-resolution method in the computer vision field has made great strides lately and has been applied in various fields. In this article, we propose a novel reference-based and gradient-guided deep learning model (RBGGM) to downscale daily precipitation considering the discontinuity of precipitation and ill-posed nature of downscaling. Global Precipitation Measurement Mission (GPM) precipitation data, variables in ERA5 re-analysis data, and topographic data are selected to perform the downscaling, and a residual dense attention block is constructed to extract features of them. By exploring the discontinuous feature of precipitation, we introduce gradient feature to reconstruct precipitation distribution. We also extract the feature of high-resolution monthly precipitation as a reference feature to resolve the ill-posed nature of downscaling. Extensive experimental results on benchmark data sets demonstrate that our proposed model performs better than other baseline methods. Furthermore, we construct a daily precipitation downscaling data set based on GPM precipitation data, ERA5 re-analysis data and topographic data.

Depressed 660-km discontinuity caused by akimotoite\u2013bridgmanite transition

The 660-kilometre seismic discontinuity is the boundary between the Earth’s lower mantle and transition zone and is commonly interpreted as being due to the dissociation of ringwoodite to bridgmanite plus ferropericlase (post-spinel transition)1–3. A distinct feature of the 660-kilometre discontinuity is its depression to 750 kilometres beneath subduction zones4–10. However, in situ X-ray diffraction studies using multi-anvil techniques have demonstrated negative but gentle Clapeyron slopes (that is, the ratio between pressure and temperature changes) of the post-spinel transition that do not allow a significant depression11–13. On the other hand, conventional high-pressure experiments face difficulties in accurate phase identification due to inevitable pressure changes during heating and the persistent presence of metastable phases1,3. Here we determine the post-spinel and akimotoite–bridgmanite transition boundaries by multi-anvil experiments using in situ X-ray diffraction, with the boundaries strictly based on the definition of phase equilibrium. The post-spinel boundary has almost no temperature dependence, whereas the akimotoite–bridgmanite transition has a very steep negative boundary slope at temperatures lower than ambient mantle geotherms. The large depressions of the 660-kilometre discontinuity in cold subduction zones are thus interpreted as the akimotoite–bridgmanite transition. The steep negative boundary of the akimotoite–bridgmanite transition will cause slab stagnation (a stalling of the slab’s descent) due to significant upward buoyancy14,15.

Diffraction Extraction Using a Low-Rank Matrix Approximation Method

Subsurface discontinuous features such as faults, cavities, and pinch-outs are commonly related to the spatial distribution of hydrocarbon reservoir zones and safe coal mining. Diffractions generated from subsurface discontinuities carry valuable information and thus are capable of accurately revealing these geological structures. Because diffractions behave as weak amplitudes, they are easily covered by specular reflections. The low-rank method performs well for diffraction extraction from specular reflections. However, the separation results are sensitive to the noise levels in traditional rank-reduction methods. The higher the noise level, the weaker the low-rank operator; therefore, the presence of noise affects the subsequent imaging. To improve the separation quality, an improved diffraction-separation method is proposed that uses parameterized non-convex penalty functions in terms of the low-rank assumption of seismic records. This new algorithm considers arctangent penalty functions as regularization terms for an accurate low-rank matrix approximation. The proposed algorithm is used to extract diffracted energy and eliminate reflected energy from noisy data. We use applications to synthetic and field examples to demonstrate that the new algorithm is able to extract high-quality diffractions, which helps locate and reveal subsurface geological discontinuities.

Flexible fabrication of Fresnel micro-lens array by off-spindle-axis diamond turning and precision glass molding

Fresnel micro-lens arrays with close-to-wavelength features have significant advantages in minimization of optical systems. However, in the fabrication of a Fresnel micro-lens array by conventional diamond turning, the discontinuous features of the surface profile cause interference between the tool flank face and the finished surface. In this manuscript, a novel off-spindle-axis diamond turning method is proposed to fabricate Fresnel micro-lens array mold insert and a toolpath generation algorithm is developed. The generation of each lenslet is treated as an independent turning operation, and the whole fabrication of a Fresnel micro-lens array is completed by a succession of repetitive turning operations. With this approach, the interference between the tool and the finished surface is avoided, and the form accuracy and surface integrity are improved for each lenslet. Then, the Fresnel micro-lens array mold insert is further utilized in precision glass molding to replicate the micro-lens structures onto transparent polymer substrates. The experimental results indicate that both the diamond-turned and molded Fresnel micro-lens arrays are achieved with homogeneous quality. As an application, a compact imaging system based on the molded Fresnel micro-lens array is demonstrated. The proposed machining method in this study can be employed in the fabrication of Fresnel micro-lens arrays and other micro-optics with discontinuous profiles with high accuracy and machining efficiency.

Rock Mass Characterization by UAV and Close-Range Photogrammetry: A Multiscale Approach Applied along the Vallone dell’Elva Road (Italy)

Geostructural rock mass surveys and the collection of data related to discontinues provide the basis for the characterization of rock masses and the study of their stability conditions. This paper describes a multiscale approach that was carried out using both non-contact techniques and traditional support techniques to survey certain geometrical features of discontinuities, such as their orientation, spacing, and useful persistence. This information is useful in identifying the possible kinematics and stability conditions. These techniques are extremely useful in the case study of the Elva valley road (Northern Italy), in which instability phenomena are spread across 9 km in an overhanging rocky mass. A multiscale approach was applied, obtaining digital surface models (DSMs) at three different scales: large-scale DSM of the entire road, a medium-scale DSM to assess portions of the slope, and a small-scale DSM to assess single discontinuities. The georeferenced point cloud and consequent DSMs of the slopes were obtained using an unmanned aerial vehicle (UAV) and terrestrial photogrammetric technique, allowing topographic and rapid traditional geostructural surveys. This technique allowed us to take measurements along the entire road, obtaining geometrical data for the discontinuities that are statistically representative of the rock mass and useful in defining the possible kinematic mechanisms and volumes of potentially detachable blocks. The main purpose of this study was to analyse how the geostructural features of a rock mass can affect the stability slope conditions at different scales in order to identify road sectors susceptible to different potential failure mechanisms using only kinematic analysis.

Concealed-Fault Detection in Low-Amplitude Tectonic Area—An Example of Tight Sandstone Reservoirs

Fault detection is important to seismic interpretation, especially for tight oil and gas reservoirs. Generally speaking, large-scale faults can be accurately imaged and are easy to detect by conventional methods, but the concealed ones in low-amplitude structural regions are difficult to find. In these areas, the scale and displacement of concealed faults are usually very small. Due to the good uniform and weak amplitude disturbances in the seismic events, the traditional discontinuity attributes extracted from seismic data are always not effective. This is because the discontinuous features of large faults are very significant, and the weak anomalies caused by hidden faults are very close to the continuous background. This paper takes a tight sandstone reservoir in the Ordos Basin of China as an example to explore the detection method of subtle faults in low-amplitude structural areas. With the phase congruency analysis method, we extract edge features from the post-stack coherence attributes to identify hidden faults. Practice shows that this idea has outstanding performance in mining hidden fracture features and improving the accuracy of fracture recognition. The results successfully predict a shear fault zone in the northeast of the work area, find a new fracture zone in the center of the survey and a series of hidden faults in non-target strata. It would be beneficial to extend the strata and area of oil and gas reservoirs.

Machine learning-based classification of rock discontinuity trace: SMOTE oversampling integrated with GBT ensemble learning

This paper presents a hybrid ensemble classifier combined synthetic minority oversampling technique (SMOTE), random search (RS) hyper-parameters optimization algorithm and gradient boosting tree (GBT) to achieve efficient and accurate rock trace identification. A thirteen-dimensional database consisting of basic, vector, and discontinuity features is established from image samples. All data points are classified as either “trace” or “non-trace” to divide the ultimate results into candidate trace samples. It is found that the SMOTE technology can effectively improve classification performance by recommending an optimized imbalance ratio of 1:5 to 1:4. Then, sixteen classifiers generated from four basic machine learning (ML) models are applied for performance comparison. The results reveal that the proposed RS-SMOTE-GBT classifier outperforms the other fifteen hybrid ML algorithms for both trace and non-trace classifications. Finally, discussions on feature importance, generalization ability and classification error are conducted for the proposed classifier. The experimental results indicate that more critical features affecting the trace classification are primarily from the discontinuity features. Besides, cleaning up the sedimentary pumice and reducing the area of fractured rock contribute to improving the overall classification performance. The proposed method provides a new alternative approach for the identification of 3D rock trace.

Ultra-Short Term Power Load Prediction Based on Gated Cycle Neural Network and XGBoost Models

Load forecasting is an important guarantee for power system design, planning and operation. In order to further improve the accuracy of power load forecasting, a combined forecasting model based on gating recurrent neural network (GRU) and limit gradient lifting (XGBoost) is proposed. Firstly, according to the load data and the input structure of GRU and XGBoost models, the data are preprocessed, and the preprocessed data are input into the corresponding model respectively. Then, the model is weighted by entropy weight method to obtain the predicted value of the final combination model. Finally, the first mock exam is used to compare the combination forecasting model with the common forecasting models. The results show that the proposed method can effectively combine the advantages of the two models, and take into account the continuous time series and discontinuous feature variables, which is more accurate than the single model and the common forecasting models.

An optical-electrical co-sensing tape for cross-sectional deformation monitoring of shield tunnels

Cross-sectional deformation is a crucial index for evaluating the stability and safety of shield tunnels. Monitoring the cross-sectional deformation has been an important content in assessing the health condition of tunnels. For this reason, an optical-electrical co-sensing tape (OECST) by embedding distributed optical fiber sensor (DOFS) and coaxial cable F-P interferometer sensors (CCFPI) into a high elastic polyurethane tape has been proposed in this paper. It can simultaneously measure the low-strain area of structure with high accuracy by DOFS and large-strain area with relatively lower accuracy by CCFPI. The conceptual and geometric design, fabrication method, and sensing mechanism have been discussed. A laboratory test has also been conducted to validate that the OECST can provide reliable strain measurement. Subsequently, an algorithm has been proposed to measure the cross-sectional deformation of shield tunnels by using OECST strain measurements. The cross-sectional deformation has discontinuous features with large deformation of joints (dislocation, opening, closing, etc.) and small deformation of segments. The former can be obtained by performing geometrical analysis on rough strain measurements of the CCFPI in OECST. The latter can be derived by implementing the strain–displacement conversion on the accurate distributed strain measured by the DOFS-S in OECST. The method has been investigated experimentally. The findings from the study have demonstrated that the proposed OECST can measure the cross-sectional deformation of shield tunnels with a satisfactory accuracy, which can be used to assess the health condition of tunnels.

Investigation on the Exit Burr Formation in Micro Milling.

The burr on micro part has harmful effect on the dimensional accuracy and service performance. The original control of exit burr formation during micro milling is desirable and advisable. In this paper, the formation mechanism of exit burr was studied based on the varying cutting direction during micro milling. Three exit burr control strategies were concluded, the material properties embrittlement, the support stiffness increasing and machining parameter optimizing operations. Then, micro milling experiments were carried out to investigate the exit burr morphology and size. It was found that the exit burr formation was attributed to the change of material flowing path at the exit surface, which was caused by the negative shear deformation zone that was induced by the discontinuous shape features. Different exit burr morphologies were classified; the triangle exit burr type was caused by the varying exit burr growing direction along the exit surface. The optimal machining parameters in micro milling to obtain a small exit burr were suggested.

Methods for sampling discontinuity traces on rock mass 3D models: state of the art

Discontinuities are an intrinsic characteristic of rock masses, and they appear at every scale of a technical survey. Issues related to the procedure’s duration and the operator’s safety during the survey have encouraged the development of non-contact methods: images and digital models serve as representations of the rock mass for surveying the geometric features of discontinuities. In particular, various automatic and semi-automatic trace sampling methods were developed in the last decade, focused on estimating persistence and the degree of fracturing. A review of these methods is presented in this paper, highlighting their strengths and disadvantages.

An Adaptive Surface Interpolation Filter Using Cloth Simulation and Relief Amplitude for Airborne Laser Scanning Data

Separating point clouds into ground and nonground points is an essential step in the processing of airborne laser scanning (ALS) data for various applications. Interpolation-based filtering algorithms have been commonly used for filtering ALS point cloud data. However, most conventional interpolation-based algorithms have exhibited a drawback in terms of retaining abrupt terrain characteristics, resulting in poor algorithmic precision in these regions. To overcome this drawback, this paper proposes an improved adaptive surface interpolation filter with a multilevel hierarchy by using a cloth simulation and relief amplitude. This method uses three hierarchy levels of provisional digital elevation model (DEM) raster surfaces with thin plate spline (TPS) interpolation to separate ground points from unclassified points based on adaptive residual thresholds. A cloth simulation algorithm is adopted to generate sufficient effective initial ground seeds for constructing topographic surfaces with high quality. Residual thresholds are adaptively constructed by the relief amplitude of the examined area to capture complex landscape characteristics during the classification process. Fifteen samples from the International Society for Photogrammetry and Remote Sensing (ISPRS) commission are used to assess the performance of the proposed algorithm. The experimental results indicate that the proposed method can produce satisfying results in both flat areas and steep areas. In a comparison with other approaches, this method demonstrates its superior performance in terms of filtering results with the lowest omission error rate; in particular, the proposed approach retains discontinuous terrain features with steep slopes and terraces.

Comprehensive identification of statistical homogeneity of fractured rock masses for a candidate HLW repository site, China

Determining the statistically homogeneous regions is important for engineering geological modeling and promoting systematic research on regional rock mass characteristics and rock engineering designs. This study proposes a comprehensive framework considering multiple discontinuity geometry parameters (e.g., orientation, trace length, density, and cluster characteristics.) to distinguish statistical homogeneity of fractured rock masses. First, based on the equal-area plot method (Schmidt net), the quantitative judgment ability of the Miller method for determining the similarity between two discontinuity orientation populations was improved by optimizing block network division scheme and blank area merging principle. Then, considering the distribution characteristics of discontinuity in rock mass space and the variation features of discontinuity at different geographical locations, a three-dimensional fracture network model, established using the discontinuity geometry parameters obtained from field investigation, was combined with the fractal dimension method (called the network fractal dimension method; NFD) to further evaluate the statistical homogeneity of fractured rock mass. The proposed approaches were subsequently applied to the identification of the statistical homogeneity of several typical granite fracture outcrops in the Beishan area, which is a candidate site for high-level radioactive waste (HLW) repository of China. The case study reveals that the optimized Miller method is more flexible and applicable than the conventional orientation-based methods, especially in dealing with the complex situation of the coexistence of gentle dip angle and steep dip angle as well as clustering characteristics of discontinuity. The NFD method was used to unify the influence of the main discontinuity characteristic parameters for a logical and unbiased evaluation of the statistical homogeneity. The comprehensive framework developed herein integrates the advantages of the two methods and reduces the interference of subjective evaluation. Therefore, it can be employed to efficiently determine the statistical homogeneity of rock masses at different locations at a large scale without concern over the deviation caused by different directions and size of the compared areas.

Gravity and magnetic joint inversion for basement and salt structures with the reversible-jump algorithm

SUMMARYGravity and magnetic data resolve the Earth with variable spatial resolution, and Earth structure exhibits both discontinuous and gradual features. Therefore, model parametrization complexity should be able to address such variability by locally adapting to the resolving power of the data. The reversible-jump Markov chain Monte Carlo (rjMcMC) algorithm provides variable spatial resolution that is consistent with data information. To address the prevalent non-uniqueness in joint inversion of potential field data, we use a novel spatial partitioning with nested Voronoi cells that is explored by rjMcMC sampling. The nested Voronoi parametrization partitions the subsurface in terms of rock types, such as sedimentary, salt and basement rocks. Therefore, meaningful prior information can be specified for each type which reduces non-uniqueness. We apply nonoverlapping prior distributions for density contrast and susceptibility between rock types. In addition, the choice of noise parametrization can lead to significant trade-offs with model resolution and complexity. We adopt an empirical estimation of full data covariance matrices that include theory and observational errors to account for spatially correlated noise. The method is applied to 2-D gravity and magnetic data to study salt and basement structures. We demonstrate that meaningful partitioning of the subsurface into sediment, salt, and basement structures is achieved by these advances without requiring regularization. Multiple simulated- and field-data examples are presented. Simulation results show clear delineation of salt and basement structures while resolving variable length scales. The field data show results that are consistent with observations made in the simulations. In particular, we resolve geologically plausible structures with varying length scales and clearly differentiate salt structure and basement topography.

Diffusion MRI Based Myometrium Tractography for Detection of Placenta Accreta Spectrum Disorder.

Prenatal diagnosis of placenta accreta spectrum (PAS) disorders is difficult. Magnetic resonance imaging (MRI) has been shown to be a useful supplementary method to ultrasound. To investigate diffusion MRI (dMRI) based tractography as a tool for detecting PAS disorders, and to evaluate its performance compared with anatomical MRI. Prospective. Forty-seven pregnant women in the third trimester with risk factors for PAS. Using fast imaging employing steady-state acquisition and high-angular resolution dMRI at 1.5 Tesla. Diagnosis of PAS was performed by three radiologists based on the dMRI-based feature of myometrial fiber discontinuity and on commonly used anatomical features including presence of dark band, discontinuous myometrium and bladder wall interruption. We evaluated the sensitivity, specificity, accuracy, and area-under-the-curve (AUC) of the individual features and established an integrated model with random forest analysis. Maternal age and gestational age at scan were compared between PAS and control group using a t-test, and childbearing history was compared using a chi-squared test. The random forest model was employed to combine the anatomical and dMRI features with 5-fold cross-validation, and the weight of each feature was normalized to evaluate its importance in predicting PAS. Based on surgical pathology reports, 16 out of 47 patients had confirmed PAS. The anatomical feature of dark bands and tractography marker achieved the highest AUC of 0.842 for predicting PAS, and the integrated anatomical and tractography features further improved the AUC of 0.880 with an accuracy of 87.2%. The tractography feature contributed most (30.1%) to the integrated model. Myometrial tractography demonstrated superior performance in detecting PAS. Moreover, the combination of dMRI-based tractography and anatomical MRI could potentially improve the diagnosis of PAS disorders in clinical practice. 2 TECHNICAL EFFICACY STAGE: 2.

Application of convolutional neural networks towards nuclei segmentation in localization-based super-resolution fluorescence microscopy images

BackgroundAutomated segmentation of nuclei in microscopic images has been conducted to enhance throughput in pathological diagnostics and biological research. Segmentation accuracy and speed has been significantly enhanced with the advent of convolutional neural networks. A barrier in the broad application of neural networks to nuclei segmentation is the necessity to train the network using a set of application specific images and image labels. Previous works have attempted to create broadly trained networks for universal nuclei segmentation; however, such networks do not work on all imaging modalities, and best results are still commonly found when the network is retrained on user specific data. Stochastic optical reconstruction microscopy (STORM) based super-resolution fluorescence microscopy has opened a new avenue to image nuclear architecture at nanoscale resolutions. Due to the large size and discontinuous features typical of super-resolution images, automatic nuclei segmentation can be difficult. In this study, we apply commonly used networks (Mask R-CNN and UNet architectures) towards the task of segmenting super-resolution images of nuclei. First, we assess whether networks broadly trained on conventional fluorescence microscopy datasets can accurately segment super-resolution images. Then, we compare the resultant segmentations with results obtained using networks trained directly on our super-resolution data. We next attempt to optimize and compare segmentation accuracy using three different neural network architectures.ResultsResults indicate that super-resolution images are not broadly compatible with neural networks trained on conventional bright-field or fluorescence microscopy images. When the networks were trained on super-resolution data, however, we attained nuclei segmentation accuracies (F1-Score) in excess of 0.8, comparable to past results found when conducting nuclei segmentation on conventional fluorescence microscopy images. Overall, we achieved the best results utilizing the Mask R-CNN architecture.ConclusionsWe found that convolutional neural networks are powerful tools capable of accurately and quickly segmenting localization-based super-resolution microscopy images of nuclei. While broadly trained and widely applicable segmentation algorithms are desirable for quick use with minimal input, optimal results are still found when the network is both trained and tested on visually similar images. We provide a set of Colab notebooks to disseminate the software into the broad scientific community (https://github.com/YangLiuLab/Super-Resolution-Nuclei-Segmentation).

The Disputed Responsibility for the Cultural Heritage: The Kvarnbacken Case

This article deals with the conflict about the responsibility for costs in connection with contract archaeology. Today, according to Swedish legislation, whoever wants to disturb, move, or destroy an antiquity must pay for the archaeological excavation. The starting point for the article is an empirical case from the province of Östergötland to which an actor perspective is applied. The case is also placed in a context to do with tendencies towards change and the discussion in recent years concerning the cultural heritage and national memory policy. By showing features of continuity and discontinuity in cultural heritage management the author seeks to reveal and reflect on the dilemmas surrounding the legislation, which dates back to the 1940s and is questioned by many.

Adjoint Tomography of Ambient Noise Data and Teleseismic P Waves: Methodology and Applications to Central California

AbstractAdjoint tomography has been recently applied to ambient seismic noise and teleseismic P waves separately to unveil fine‐scale lithospheric structures beyond the resolving ability of traditional ray‐based traveltime tomography. In this study, we propose an inversion scheme that alternates between frequency‐dependent traveltime inversions of ambient noise surface waves and waveform inversions of teleseismic P waves to take advantage of their complementary sensitivities to the Earth's structure. We apply our method to ambient noise empirical Green's functions from 60 virtual sources, direct P and scattered waves from 11 teleseismic events recorded by a dense linear array (∼7 km station spacing) and other regional stations (∼40 km average station spacing) in central California. To evaluate the performance of the method, we compare tomographic results from ambient noise adjoint tomography, full‐waveform inversion of teleseismic P waves, and the alternating inversion of the two data sets. Both applications to practical field data sets and synthetic checkerboard tests demonstrate the advantage of the alternating inversion over individual inversions as it combines the complementary sensitivities of the two independent data sets toward a more unified model. The three dimensional model from our alternating inversion not only shows major features of velocity anomalies and discontinuities in agreement with previous studies, but also reveals small‐scale heterogeneities which provide new constraints on the geometry of the Isabella Anomaly and mantle dynamic processes in central California. The proposed alternating inversion scheme can be applied to other regions with similar array deployments for high‐resolution lithospheric imaging.

Developing an Artificial Intelligence (A.I)-based descriptor of facial appearance that fits with the assessments of makeup experts.

To develop an A.I-based automatic descriptor that detects and grades, from selfie pictures, 23 facial signs, hairs included, as a help to making-up procedures. The selfie images taken in very different conditions by 3326 women and men were used to create (90% of dataset) and validate (10% of dataset) a new algorithm architecture to appraise and grade 23 different facial signs such as lips, nose, eye color, eyebrows, eyelashes, and hair color as defined by makeup artists. Each selfie image was annotated by 12 experts and defined references to train Artificial Intelligence (A.I)-based algorithm. As some the 23 signs present a continuous or discontinuous feature, these were analyzed by two different statistical approaches. The results provided by the automatic descriptor system were not only in good agreement with the expert's assessments but were even found of a better precision and reproducibility. This automatic descriptor system has proven a good and robust accuracy despite the very variable conditions in the acquisition of selfie pictures. Such automatic descriptor system seems providing a valuable help in making-up procedures and may extend to other activities such as Skincare or Haircare. As such it should allow large investigations to better evaluate the consumers' needs of esthetical improvements.