Supernumerary teeth (ST) not only commonly obstruct adjacent permanent teeth, causing ectopic eruption, rotation, and root absorption but also present the potential for cystic lesions extending into the nasal cavity. Early intervention is crucial to avoid severe complications like periodontal abscesses and severe dental caries. However, ST may occur in any oral region with variable shapes and growth directions, posing a significant challenge for image recognition. This prevalent dental condition in the Asian population (3-5%) lacks sufficient representation in AI-assisted systems. Given this, the study suggests a system reliant on Convolutional Neural Network (CNN) for identifying supernumerary teeth in occlusal radiographs. The algorithm incorporates feature enhancement and AI integration methods. Additionally, the study introduces a color mapping approach to address the variability in ST shape and growth direction, significantly improving recognition accuracy from 63.16% to 76.32%. The result of this research demonstrates an improvement of 18.43% in accuracy and 78.95% in recall rate for supernumerary tooth detection compared to existing technology. This study successfully addresses the challenge of identifying supernumerary teeth, which were previously difficult to recognize. To ensure compliance with ethical and regulatory standards, the proposal has obtained certification from the Institutional Review Board (IRB) with the reference number 202400084B0.

Summary In the recent years, there is a growing trend toward digitization of cultural heritage for better accessibility and preservation. For instance, the development of image processing techniques in traditional Chinese painting (TCP) has begun to attract researchers' attention in the computer vision field. TCP is one of the representative of Chinese traditional arts. Evidenced by the successes of development in image processing techniques in various applications, this article aim to apply the deep learning approach on TCP for several purposes, which include automatic establishment of unified image library, facilitating update‐to‐date data in the database, reduction of cost required for image classification and retrieval. First, a unified database is established, that consists of more than a thousand of images from six major TCP themes. Then, several deep learning algorithms that are based on mathematical models are applied to examine the classification performance. In addition, the salient regions that denote significant features are identified, by adopting the instance segmentation technique. As a result, the modified pretrained neural network is capable to achieve 99.66% recognition accuracy. Qualitative results are also presented to demonstrate the effectiveness of the proposed method. We also note that this is the first work that performs multiclass classification on six categories in this domain. Furthermore, a 10‐class classification result of 96% is obtained when performing on one of the painting types, namely, ghost‐and‐god.

In the recent year, state-of-the-art for facial micro-expression recognition have been significantly advanced by deep neural networks. The robustness of deep learning has yielded promising performance beyond that of traditional handcrafted approaches. Most works in literature emphasized on increasing the depth of networks and employing highly complex objective functions to learn more features. In this paper, we design a Shallow Triple Stream Three-dimensional CNN (STSTNet) that is computationally light whilst capable of extracting discriminative high level features and details of micro-expressions. The network learns from three optical flow features (i.e., optical strain, horizontal and vertical optical flow fields) computed based on the onset and apex frames of each video. Our experimental results demonstrate the effectiveness of the proposed STSTNet, which obtained an unweighted average recall rate of 0.7605 and unweighted F1-score of 0.7353 on the composite database consisting of 442 samples from the SMIC, CASME II and SAMM databases.

Micro-expressions are spontaneous, brief and subtle facial muscle movements that exposes underlying emotions. Motivated by recent exploits into deep learning for micro-expression analysis, we propose a lightweight dual-stream shallow network in the form of a pair of truncated CNNs with heterogeneous input features. The merging of the convolutional features allows for discriminative learning of micro-expression classes stemming from both streams. Using activation heatmaps, we further demonstrate that salient facial areas are well emphasized, and correspond closely to relevant action units belonging to emotion classes. We empirically validate the proposed network on three benchmark databases, obtaining state-of-the-art performance on the CASME II and SAMM while remaining competitive on the SMIC. Further observations point towards the sufficiency of utilizing shallower deep networks for micro-expression recognition.