The auricular conchae of 310 young Chinese people (169 men and 141 women) aged 18–28 years were classified into different groups and differentiated in terms of shape as a basis to designing wearable and non‐slip earphones. Seven characteristic distances could be obtained accurately by defining 5 characteristic points and extracting their 3‐dimensional (3D) coordinates from 3D digital models (obtained by scanning 310 ear impressions) automatically. The shape differences of auricular conchae were statistically analyzed. Results show that the average dimensions of auricular conchae for men are generally larger than those for women, and the shapes of auricular conchae significantly differ among the participants. The shapes of auricular concha were classified into 24 groups, depending on the characteristic distances. For each group, the coordinates of 5 common‐characteristic points were determined and the basic shape was summarized. The percentage of the samples in each group was statistically given, and 8 prioritized groups of samples more than 5% were suggested. Finally, the feasibility of the classification method was demonstrated by designing earphone, 3D printing, and wearing verification.

SUMMARY:A detailed data of concha is currently not available. Therefore, the present study aimed to determine twelve morphometric measurements of concha, to investigate its sexual dimorphism and bilateral asymmetry, and to establish basic shapes of concha for both sexes and sides. The study sample comprised of 310 young Chinese aged 18-28 years. 141 left and 141 right ear impressions for females, 169 left and 169 right ear impressions for males were collected and scanned. The 3D coordinates of seven landmarks on each auricular concha were obtained using 3D scanning technology and curvature theory. From the landmarks, twelve morphometric measurements of concha were calculated and analyzed. The conchal morphometry exist significantly sexual dimorphism in this study sample. On average, all measurements were larger in males than in females regardless of the sides. There was significantly bilateral asymmetry among left and right conchae in both sexes. Some measurements were larger in the right sides and some measurements were larger in the left sides, but the bilateral difference in both measurements found to be less than 1mm. Additionally, the basic shapes of concha for both sexes and sides were established on the basis of the mean 3D coordinates of each landmark and the mean value of each measurement. The anthropometric method of this study could overcome the difficulty in locating landmarks of auricle complex structures, and attain a higher level of accuracy in the procedure of measurement. The quantitative description of conchal morphometry will be beneficial for plastic surgeons, and for the ergonomic design of hearing aids.

This paper proposes an image authentication scheme for mobile devices. The proposed scheme generates an image watermark by using discrete cosine transform (DCT) and hides the watermark in the spatial pixels for image authentication and tamper detection. The hiding operator used in this paper is very simple in a mobile environment allowing high-speed authentication using a low-power mobile device. The quality of the stego-image and the recovered image becomes excellent as a result of the proposed scheme.

One of the challenges of the Optical Music Recognition task is to transcript the symbols of the camera-captured images into digital music notations. Previous end-to-end model which was developed as a Convolutional Recurrent Neural Network does not explore sufficient contextual information from full scales and there is still a large room for improvement. We propose an innovative framework that combines a block of Residual Recurrent Convolutional Neural Network with a recurrent Encoder-Decoder network to map a sequence of monophonic music symbols corresponding to the notations present in the image. The Residual Recurrent Convolutional block can improve the ability of the model to enrich the context information. The experiment results are benchmarked against a publicly available dataset called CAMERA-PRIMUS, which demonstrates that our approach surpass the state-of-the-art end-to-end method using Convolutional Recurrent Neural Network. CCS CONCEPTS• Computing methodologies → Neural networks.

Optical Music Recognition is a field that attempts to extract digital information from images of either the printed music scores or the handwritten music scores. One of the challenges of the Optical Music Recognition task is to transcript the symbols of the camera-captured images into digital music notations. Previous end-to-end model, based on deep leanring, was developed as a Convolutional Recurrent Neural Network. However, it does not explore sufficient contextual information from full scales and there is still a large room for improvement. In this paper, we propose an innovative endto-end framework that combines a block of Residual Recurrent Convolutional Neural Network with a recurrent Encoder-Decoder network to map a sequence of monophonic music symbols corresponding to the notations present in the image. The Residual Recurrent Convolutional block can improve the ability of the model to enrich the context information while the number of parameter will not be increasing. The experiment results were benchmarked against a publicly available dataset called CAMERA-PRIMUS. We evaluate the performances of our model on both the images with ideal conditions and that with non-ideal conditions. The experiments show that our approach surpass the state-of-the-art end-to-end method using Convolutional Recurrent Neural Network.

No abstract

A detailed data of shape of auricular concha is currently not available. Therefore, this study constructed a framework to statistically analyze the shape of the auricular concha based on a database of 3D scanned images. The 3D models of the auricular concha from 308 study participants are converted into compatible NURBS surfaces generated through 795 data points to perform a requisite statistical analysis. Subsequently, the shape of the auricular concha of the participants is grouped into 29 clusters with a modified hierarchical clustering algorithm. Finally, a wear trial and simulation test are carried out to validate the wear comfort of a designed OTC hearing aids based on the average shape of each cluster. The experimental results show that the average shape obtained as per the cluster is capable of representing the common geometric properties of their corresponding members, and could thus be used as a reference in designing mass-customized OTC hearing aid. The method in this study is superior to conventional methods that rely on sparse results for shape analysis because it takes into account the intricate geometric shape of the auricular concha. The quantitative description of conchal morphometry will be beneficial for plastic surgeons, and for the ergonomic design of ear-related products.