Deep Convolutional Sequence Approach Towards Real-Time Intelligent Optical Scanning

Visual text recognition is the most dynamic computer vision application due to its rising demand in several applications like crime scene detection, assisting blind people, digitizing, book scanning, etc. However, numerous research works were executed on static visuals having organized text and on captured video frames in the past. The key objective of this study is to develop the real-time intelligent optical scanner that will extract every sequence of text from high-speed video, noisy visual input, and offline handwritten script. The scientific work has been carried out with the combination of multiple deep learning approaches, namely EAST, CNN, and Bi-LSTM with CTC. The system is trained and tested on four public datasets (i.e., ICDAR 2015, SVT, Synth-Text, IAM-3.0) and measured on the basis of recall, precision, and f-measure. Based on the challenges, performance has been examined under three different categories, and the outcomes are optimistic and encouraging for future advancement.

Numerical Methods for Calculating Component Modes for Geometric Mistuning Reduced-order Models

Geometric mistuning models formulated from a component mode synthesis methods often require the calculation of component modes, particularly constraint and fixed interface normal modes, during substructuring. For Integrally Bladed Rotors, these calculations are required for each sector. This paper proposes methods that reuse information garnered from solving the constraint modes of a single sector on the remaining sectors to reduce memory requirements and solution times. A mesh metamorphosis tool is used to ensure finite element models match geometry obtained from a 3D optical scanner. This tool also produces a common mesh pattern from sector-to-sector. This is exploited to produce common permutation matrices and symbolic factorizations of sector stiffness matrices that are proposed for reuse in solving subsequent constraint modes. Furthermore, a drop tolerance is introduced to remove small values during constraint mode calculation to reduce memory requirements. It is proposed to reuse this dropping pattern produced from a single sector on the remaining sectors. Approaches are then extended to a parallel processing scheme to propose effective matrix partitioning methods. Finally, information gathered during the constraint mode calculations are reused during the solution of the fixed interface normal modes to improve solution time. Results show reusing permutation matrices and symbolic factorizations from sector-to-sector improves solution time and introduces no error. Using a drop tolerance is shown to reduce storage requirements of a constraint mode matrix, while reusing the dropping pattern introduces minimal error. Similarly, reusing constraint mode information in calculating normal modes greatly improves the performance.

Numerical Methods for Calculating Component Modes for Geometric Mistuning Reduced-Order Models

Geometric mistuning models formulated from a component mode synthesis methods often require the calculation of component modes, particularly constraint and fixed interface normal modes, during substructuring. For Integrally Bladed Rotors, these calculations are required for each sector. This paper proposes methods that reuse information garnered from solving the constraint modes of a single sector on the remaining sectors to reduce memory requirements and solution times. A mesh metamorphosis tool is used to ensure finite element models match geometry obtained from a 3D optical scanner. This tool also produces a common mesh pattern from sector-to-sector. This is exploited to produce common permutation matrices and symbolic factorizations of sector stiffness matrices that are proposed for reuse in solving subsequent constraint modes. Furthermore, a drop tolerance is introduced to remove small values during constraint mode calculation to reduce memory requirements. It is proposed to reuse this dropping pattern produced from a single sector on the remaining sectors. Approaches are then extended to a parallel processing scheme to propose effective matrix partitioning methods. Finally, information gathered during the constraint mode calculations are reused during the solution of the fixed interface normal modes to improve solution time. Results show reusing permutation matrices and symbolic factorizations from sector-to-sector improves solution time and introduces no error. Using a drop tolerance is shown to reduce storage requirements of a constraint mode matrix. Additionally, it is shown that reusing the same dropping pattern introduces minimal error without degradation in solution times. Similarly, reusing the information from constraint modes for calculating fixed interface normal modes greatly improves the performance in a shift-and-invert technique for solving eigenvalue problems.

Accuracy of Three-Dimensional (3D) Printed Dental Digital Models Generated with Three Types of Resin Polymers by Extra-Oral Optical Scanning

Digital impression devices are used alternatively to conventional impression techniques and materials. The aim of this study was to evaluate the precision of extraoral digitalization of three types of photosensitive resin polymers used for 3D printing with the aid of a digital extraoral optical scanner. The alignment of the scans was performed by a standard best-fit alignment. Trueness and precision were used to evaluate the models. The trueness was evaluated by using bias as a measure and the standard deviation was used to evaluate the precision. After assessing the normality of the distributions, an independent Kruskal–Wallis test was used to compare the trueness and precision across the material groups. The Mann–Whitney test was used as a post-hoc test for significant differences. The result of the analysis showed significant differences (U = 66, z = −2.337, p = 0.019) in trueness of mesiodistal distances. Upon visual inspection of the models, defects were noticed on two out of nine of the models printed with a photosensitive polymer. The defects were presented as cavities caused by air bubbles and were also reflected in the scans. Mean precision did not vary too much between these three photosensitive polymer resins, therefore, the selection of 3D printing materials should be based on the trueness and the required precision of the clinical purpose of the model.

Restorative Space Analysis by Jaw Motion Tracking Using a Template in Completely Edentulous Patients

Improvements in computer-aided design/computer-aided manufacturing technologies have led to multiple attempts being made to simplify and improve the workflow of prosthesis fabrication for completely edentulous patients. However, most attempts still involve the conventional methods of impression-making and recording the maxillomandibular relationships using alginate, rubber impression materials, and wax materials. In the case of a completely edentulous arch, the presence of movable tissues and the absence of stable landmarks make it difficult to perform direct digitization using an intraoral scanner and to digitally determine the vertical dimension. In the alternative technique described herein, data are obtained by scanning a template such as the patient’s existing old dentures and jaw movement data using target materials and an optical scanner, and an appropriate maxillomandibular relationship that has the desired restorative space is determined on the basis of the obtained trajectory of mandibular movements while opening and closing the mouth. After designing dentures on the basis of the newly established maxillomandibular relationships and performing a try-in process, the final dentures can be manufactured. This alternative technique can reduce the need for multiple visits and complex procedures, improving the workflow for fabricating prostheses with the correct maxillomandibular relationships for individual patients.

Image processing and machine learning for telehealth craniosynostosis screening in newborns

OBJECTIVE The authors sought to evaluate the accuracy of a novel telehealth-compatible diagnostic software system for identifying craniosynostosis within a newborn (< 1 year old) population. Agreement with gold standard craniometric diagnostics was also assessed. METHODS Cranial shape classification software accuracy was compared to that of blinded craniofacial specialists using a data set of open-source (n = 40) and retrospectively collected newborn orthogonal top-down cranial images, with or without additional facial views (n = 339), culled between April 1, 2008, and February 29, 2020. Based on image quality, midface visibility, and visibility of the cranial equator, 351 image sets were deemed acceptable. Accuracy, sensitivity, and specificity were calculated for the software versus specialist classification. Software agreement with optical craniometrics was assessed with intraclass correlation coefficients. RESULTS The cranial shape classification software had an accuracy of 93.3% (95% CI 86.8–98.8; p < 0.001), with a sensitivity of 92.0% and specificity of 94.3%. Intraclass correlation coefficients for measurements of the cephalic index and cranial vault asymmetry index compared to optical measurements were 0.95 (95% CI 0.84–0.98; p < 0.001) and 0.67 (95% CI 0.24–0.88; p = 0.003), respectively. CONCLUSIONS These results support the use of image processing–based neonatal cranial deformity classification software for remote screening of nonsyndromic craniosynostosis in a newborn population and as a substitute for optical scanner– or CT-based craniometrics. This work has implications that suggest the potential for the development of software for a mobile platform that would allow for screening by telemedicine or in a primary care setting.