Improved measurement of lateral parasagittal articulation integrating three-dimensional palate shape

Face recognition from three-dimensional (3D) shape data has been proposed as a method of biometric identification as a way of either supplanting or reinforcing a two-dimensional approach. This paper presents a 3D face recognition system capable of recognizing the identity of an individual from a 3D facial scan in any pose across the view-sphere, by suitably comparing it with a set of models (all in frontal pose) stored in a database. The system makes use of only 3D shape data, ignoring textural information completely. Firstly, we propose a generic learning strategy using support vector regression [Burges, Data Mining Knowl Discov 2(2): 121–167, 1998] to estimate the approximate pose of a 3D head. The support vector machine (SVM) is trained on range images in several poses belonging to only a small set of individuals and is able to coarsely estimate the pose of any unseen facial scan. Secondly, we propose a hierarchical two-step strategy to normalize a facial scan to a nearly frontal pose before performing any recognition. The first step consists of either a coarse normalization making use of facial features or the generic learning algorithm using the SVM. This is followed by an iterative technique to refine the alignment to the frontal pose, which is basically an improved form of the Iterated Closest Point Algorithm [Besl and Mckay, IEEE Trans Pattern Anal Mach Intell 14(2):239–256, 1992]. The latter step produces a residual error value, which can be used as a metric to gauge the similarity between two faces. Our two-step approach is experimentally shown to outperform both of the individual normalization methods in terms of recognition rates, over a very wide range of facial poses. Our strategy has been tested on a large database of 3D facial scans in which the training and test images of each individual were acquired at significantly different times, unlike all except two of the existing 3D face recognition methods.

Phase-measuring deflectometry (PMD)-based methods have been widely used in the measurement of the threedimensional (3D) shape of specular objects, and the existing PMD methods utilize visible light. However, specular surfaces are sensitive to ambient light. As a result, the reconstructed 3D shape results are mostly affected by the external environment in actual measurements. To overcome this problem, a novel infrared-PMD (IR-PMD) method is proposed to measure specular objects by directly establishing the relationship between the absolute phase and depth data. In addition, a new calibration method for the measurement system has been proposed by combining fringe projection and fringe reflection. The proposed IR-PMD method uses an IR projector to project sinusoidal fringe patterns onto a ground glass, which can be regarded as an IR digital screen. The IR fringe patterns are reflected by the measured specular surfaces and the deformed fringe patterns captured by an IR camera. The multiple-step phase-shifting algorithm and the optimum three-fringe number selection method are applied to the deformed fringe patterns to obtain the wrapped and unwrapped phase data, respectively. Then 3D shape data can be directly calculated by the unwrapped phase data on the screen located at two positions. The results have validated the effectiveness and accuracy of the proposed method. It can be used to measure specular components in the application fields of advanced manufacturing, automobile industry, and aerospace industry.

A three-dimensional active surface model has been suggested as a possible solution to the difficult problem of segmenting lymph nodes in CT x-rays. In this paper, a computationally simple active surface, or balloon, is proposed which requires minimal user interaction or a priori shape knowledge. A structure is proposed for the balloon model in which each balloon point is guaranteed a fixed number of neighbors, and a method is provided for adding points to the model while still maintaining that structural regularity. Equations are provided for deriving surface energy from 3D shape and 3D image data. Minimal user interaction is required, with only a single point somewhere inside the node needed to initialize the algorithm. The balloon naturally inflates to find the correct surface due to a unique candidate point selection algorithm that is biased in favor of outward moves. Preliminary results show the model to be successful in finding boundaries in synthetic 3-D images.

Potato quality grading based on machine vision and 3D shape analysis

Phase-measuring deflectometry (PMD)-based methods have been widely used in the measurement of the three-dimensional (3D) shape of specular objects, and the existing PMD methods utilize visible light. However, specular surfaces are sensitive to ambient light. As a result, the reconstructed 3D shape is affected by the external environment in actual measurements. To overcome this problem, an infrared PMD (IR-PMD) method is proposed to measure specular objects by directly establishing the relationship between absolute phase and depth data for the first time. Moreover, the proposed method can measure discontinuous surfaces. In addition, a new geometric calibration method is proposed by combining fringe projection and fringe reflection. The proposed IR-PMD method uses a projector to project IR sinusoidal fringe patterns onto a ground glass, which can be regarded as an IR digital screen. The IR fringe patterns are reflected by the measured specular surfaces, and the deformed fringe patterns are captured by an IR camera. A multiple-step phase-shifting algorithm and the optimum three-fringe number selection method are applied to the deformed fringe patterns to obtain wrapped and unwrapped phase data, respectively. Then, 3D shape data can be directly calculated by the unwrapped phase data on the screen located in two positions. The results here presented validate the effectiveness and accuracy of the proposed method. It can be used to measure specular components in the application fields of advanced manufacturing, automobile industry, and aerospace industry.

This study intended to suggest criteria for selection of subjects by lower body shape types necessary for evaluating slacks. For this, the characteristics were examined by lower body parts which would influence the fit of slacks on 3D human body shape data of the front and sides of the lower body for lower body shaping. The frequency of subjects by lower body shape types and the boundary points for discrimination of each type were suggested so that they could be available in selecting subjects. Using the data from Size Korea(2004), indirect measurement values measured on the front and sides of the lower body among 3D human body shape data of 175 subjects were analyzed. Their height, waist, and hip circumference fell under the range of standard deviation based on the mean of women aged 18~24 years, and then lower body shaping was conducted by combining the front and side shapes of the lower body. The front of the lower body was classified into four sections: average waist/average hip type(F1), average waist/narrow hip tyle(F2), narrow waist/narrow hip type(F3) and narrow waist/wide hip type(F4) and the sides of the lower body were divided into four sections: average abdomen/average hip type(S1), flat abdomen/average hip type(S2), average abdomen/protrude hip type(S3)and round abdomen/flat hip type(S4), and thus total 16 lower body types were created by cross analysis. Besides, discriminant analysis suggested the boundary points for each shape type of the front and sides of the lower body as a criterion for deciding lower body shape type of each subject

3D computer vision is considered promising with the use of computers to process and analyze 3D data from sensors to extract information about the 3D world. One key difference between 3D and 2D computer vision is the amount of information available to the system. 3D data contains information about the depth of objects in the scene, which can be used to locate and recognize objects more accurately. 2D data, on the other hand, does not contain this depth information, which can make it more challenging to accurately locate and recognize objects. 3D computer vision also allows for the integration of data from multiple sources such as 2D cameras, depth cameras, lidar scanners and manually created 3D assets. 3D computer vision has the potential to enable new applications and technologies. For example, the ability to accurately understand the 3D structure of a scene could be used to enable augmented reality applications and self-driving cars. Just like 2D computer vision, 3D computer vision also relies on large amounts of training data to train deep learning models. There are two primary ways to obtain 3D data for training, either by collecting real 3D data or creating synthetic 3D data. Advances in technology, such as 3D sensors like Lidar, structured light sensors, Time-of-Flight (ToF) cameras, and RGB-D cameras, have made it much easier and more accurate to collect real 3D data. Photogrammetry is another way to obtain real 3D data from multiple photos of an object or environment from different angles using reconstruction algorithms. However, annotating 3D data can be more challenging than annotating 2D data due to the additional dimensions and complexity. Synthetic 3D data can be generated using various 3D modeling and simulation software. Fortunately, synthetic data inherently contains ground truth labels during the creation process. Nevertheless, creating synthetic 3D data can be a complex and time-consuming process that requires a high degree of technical skill and artistic ability. It involves several stages, including modeling, texturing, lighting, and rendering. Each stage requires a different set of skills, and mastering all of them can take time and practice. Therefore, the goals of this thesis lie in reducing the annotation cost of real 3D data and increasing the size and diversity of synthetic datasets. The first part of this thesis proposes two methods for weakly supervised learning in 3D semantic segmentation. The first method predicts point-level results using weak labels on 3D point clouds, utilizing our multi-path region mining module to generate pseudo-point-level labels for training a point cloud segmentation network in a fully supervised manner. We discuss both scene- and subcloud-level weak labels and perform experiments on them. The second method trains a semantic point cloud segmentation network with a small portion of labeled points, using cross-sample feature reallocating and intra-sample feature redistribution modules to transfer features and propagate supervision signals on unlabeled points. Our weakly supervised method can produce competitive results with only 10\% and 1\% of labels compared to the fully supervised counterpart. The second part introduces Biharmonic Augmentation (BA), an efficient data augmentation method that produces plausible and smooth non-rigid deformations on 3D shapes to increase the diversity of point cloud data. We compute biharmonic coordinates and learn deformation prototypes to obtain the overall deformation using a Coefficient Network (CoefNet). Our Adversarial Tuning (AdvTune) framework employs adversarial training to jointly train the CoefNet and classification network and can generate adaptive shape deformation based on the learner state. Our experiments show that BA outperforms various point cloud augmentation methods on different networks. The third part proposes Text-Guided 3D Textured Shape Generation from Pseudo Supervision (TAPS3D), a novel framework for training a text-guided 3D shape generator using 2D multi-view images and pseudo captions. We construct captions from relevant words retrieved from the Contrastive Language-Image Pre-Training (CLIP) vocabulary and use low-level image regularization to increase geometry diversity and produce fine-grained textures. Our model can generate explicit 3D textured shapes from given text without additional test-time optimization. Extensive experiments show the efficacy of our framework in generating high-fidelity 3D shapes relevant to the given text. In summary, we proposed three approaches to address the data shortage problem in 3D computer vision tasks. Firstly, we developed weakly supervised learning methods to reduce the annotation cost for 3D data. Secondly, we proposed data augmentation techniques to artificially increase the size of 3D datasets. Thirdly, we presented a text-guided 3D data generation method to generate 3D data as needed. We conducted extensive experiments and achieved promising results on various datasets, demonstrating the effectiveness and potential of our approaches in addressing the challenges of 3D computer vision tasks.

Three dimensional (3D) shape reconstruction based on structured light technique is one of the most crucial and attractive techniques in the field of optical metrology and measurements due to the nature of non-contact and high-precision. Acquiring high-quality 3D shape data of objects with complex surface is an issue that is difficult to solve by single-frequency method. However, 3D shape data of objects with complex surface can be obtained only at a limited accuracy by classical multi-frequency approach. In this paper, we propose a new robust deep learning shape reconstruction (DLSR) method based on the structured light technique, where we accurately extract shape information of objects with complex surface from three fringe patterns with different frequencies. In the proposed DLSR method, the input of the network is three deformed fringe patterns, and the output is the corresponding 3D shape data. Compared with traditional approach, the DLSR method is pretty simple without using any geometric information and complicated triangulation computation. The experimental results demonstrate that the proposed DLSR method can effectively achieve robust, high-precision 3D shape reconstruction for objects with complex surface.

Two-channel high-accuracy Holoimage technique for three-dimensional data compression

Background: Three-dimensional surface imaging is widely used in breast surgery. Recently, smartphone-based approaches have emerged. This investigation examines whether smartphone-based three-dimensional surface imaging provides clinically acceptable data in terms of accuracy when compared to a validated reference tool. Methods: Three-dimensional surface models were generated for 40 patients who underwent breast reconstruction surgery using the Vectra H2 (Canfield Scientific, Fairfield, NJ, USA) and the LiDAR sensor of an iPhone 15 Pro in conjunction with photogrammetry. The generated surface models were superimposed using CloudCompare’s ICP algorithm, followed by 14 linear surface-to-surface measurements to assess agreement between the three-dimensional surface models. Statistical methods included absolute error calculation, paired t-test, Bland–Altman analysis, and Intra-Class Correlation Coefficients to evaluate intra- and inter-rater reliability. Results: The average landmark-to-landmark deviation between smartphone-based and Vectra-based surface models was M = 2.997 mm (SD = 1.897 mm). No statistical differences were found in 13 of the 14 measurements for intra-rater comparison and in 12 of the 14 for inter-rater comparison. The Intra-Class Correlation Coefficient for intra-rater reliability of the iPhone was good, ranging from 0.873 to 0.993. Intra-Class Correlation Coefficient values indicated good reliability, ranging from 0.873 to 0.993 (intra-rater) and 0.845 to 0.992 (inter-rater). Bland–Altman analyses confirmed moderate to reliable agreement in 13 of 14 measurements. Conclusions: Smartphone-based three-dimensional surface imaging presents promising possibilities for breast assessment. However, it may not yet be suitable for highly detailed breast assessments requiring accuracy below the 3 mm threshold.

Electropalatography (EPG) is a useful tool for investigating tongue dynamics in experimental phonetic research and speech therapy. However, data provided by EPG are a two-dimensional representation in which all absolute positional information is lost. This paper presents an enhanced EPG (eEPG) system which uses digitised palate shape data to display the tongue-palate contact pattern in three dimensions. The palate shapes are obtained using a colour-encoded structured light three-dimensional digitisation system. The three-dimensional palate shape is displayed on a Silicon Graphics workstation as a surface made up of polygons represented by a quadrilateral mesh. EPG contact patterns are superimposed on to the three-dimensional palate shape by displaying the relevant polygons in a different colour. By using this system, differences in shape between individual palates, apparent on visual inspection of the actual palates, are also apparent in the image on screen. Further, methods have been devised for computing absolute distances along paths lying on the palate surface. Combining this with calibrated palate shape data allows accurate measurements to be made between contact locations on the palate. These have been validated with manual measurements. In addition, vocal tract areas in the oral cavity have been estimated by using the absolute measurements on the palate for a given contact pattern, and assuming a flat tongue profile in the uncontacted area.

The fast development in the fields of integrated circuits, photovoltaics, the automobile industry, advanced manufacturing, and astronomy have led to the importance and necessity of quickly and accurately obtaining three-dimensional (3D) shape data of specular surfaces for quality control and function evaluation. Owing to the advantages of a large dynamic range, non-contact operation, full-field and fast acquisition, high accuracy, and automatic data processing, phase-measuring deflectometry (PMD, also called fringe reflection profilometry) has been widely studied and applied in many fields. Phase information coded in the reflected fringe patterns relates to the local slope and height of the measured specular objects. The 3D shape is obtained by integrating the local gradient data or directly calculating the depth data from the phase information. We present a review of the relevant techniques regarding classical PMD. The improved PMD technique is then used to measure specular objects having discontinuous and/or isolated surfaces. Some influential factors on the measured results are presented. The challenges and future research directions are discussed to further advance PMD techniques. Finally, the application fields of PMD are briefly introduced.

Virtual structured-light coding for three-dimensional shape data compression

With the fast development of integrated circuits, photovoltaics, automobile industry, advanced manufacturing, and astronomy, it is particularly important to obtain the three-dimensional (3D) shape data of specular objects quickly and accurately. Owing to the advantages of large dynamic range, non-contact operation, full-field and fast acquisition, high accuracy, and automatic data processing, phase-measuring deflectometry (PMD, also called fringe reflection profilometry) has been widely studied and applied in many fields. Direct PMD (DPMD) can directly establish the relationship between phase and depth data without gradient integration process, so it can be used for 3D shape measurement of specular objects having discontinuous surfaces. However, compared with gradient data, depth data is more sensitive to measurement noise, so the measurement accuracy obtained by gradient field integration is higher. In order to make use of the anti-noise property of gradient measurement structure, some PMD techniques usually abandon the height data obtained from the intermediate process and use the gradient data to complete the surface reconstruction. Stereo deflectometry is a typical representative to retrieve 3D shape of the measured object according to the gradient integration. It calculates the gradient field based on the uniqueness of the normal vector of the object points by using two cameras. Although obtaining high-precision measurement results, this method cannot be used for the measurement of discontinuous objects. In this paper, a new stereo DPMD method is proposed to obtain 3D shape of specular objects having discontinuous surfaces. Some experimental results on measuring discontinuous specular objects verify the high precision of the proposed stereo DPMD method.

Portable solution for high-resolution 3D and color texture on-site digitization of cultural heritage objects