RESUMEN

Image super-resolution (ISR) technology aims to enhance resolution and improve image quality. It is widely applied to various real-world applications related to image processing, especially in medical images, while relatively little appliedto anime image production. Furthermore, contemporary ISR tools are often based on convolutional neural networks (CNNs), while few methods attempt to use transformers that perform well in other advanced vision tasks. We propose a so-called anime image super-resolution (AISR) method based on the Swin Transformer in this work. The work was carried out in several stages. First, a shallow feature extraction approach was employed to facilitate the features map of the input image's low-frequency information, which mainly approximates the distribution of detailed information in a spatial structure (shallow feature). Next, we applied deep feature extraction to extract the image semantic information (deep feature). Finally, the image reconstruction method combines shallow and deep features to upsample the feature size and performs sub-pixel convolution to obtain many feature map channels. The novelty of the proposal is the enhancement of the low-frequency information using a Gaussian filter and the introduction of different window sizes to replace the patch merging operations in the Swin Transformer. A high-quality anime dataset was constructed to curb the effects of the model robustness on the online regime. We trained our model on this dataset and tested the model quality. We implement anime image super-resolution tasks at different magnifications (2×, 4×, 8×). The results were compared numerically and graphically with those delivered by conventional convolutional neural network-based and transformer-based methods. We demonstrate the experiments numerically using standard peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), respectively. The series of experiments and ablation study showcase that our proposal outperforms others.

Asunto(s)

RESUMEN

Recently, the dangers associated with face generation technology have been attracting much attention in image processing and forensic science. The current face anti-spoofing methods based on Generative Adversarial Networks (GANs) suffer from defects such as overfitting and generalization problems. This paper proposes a new generation method using a one-class classification model to judge the authenticity of facial images for the purpose of realizing a method to generate a model that is as compatible as possible with other datasets and new data, rather than strongly depending on the dataset used for training. The method proposed in this paper has the following features: (a) we adopted various filter enhancement methods as basic pseudo-image generation methods for data enhancement; (b) an improved Multi-Channel Convolutional Neural Network (MCCNN) was adopted as the main network, making it possible to accept multiple preprocessed data individually, obtain feature maps, and extract attention maps; (c) as a first ingenuity in training the main network, we augmented the data using weakly supervised learning methods to add attention cropping and dropping to the data; (d) as a second ingenuity in training the main network, we trained it in two steps. In the first step, we used a binary classification loss function to ensure that known fake facial features generated by known GAN networks were filtered out. In the second step, we used a one-class classification loss function to deal with the various types of GAN networks or unknown fake face generation methods. We compared our proposed method with four recent methods. Our experiments demonstrate that the proposed method improves cross-domain detection efficiency while maintaining source-domain accuracy. These studies show one possible direction for improving the correct answer rate in judging facial image authenticity, thereby making a great contribution both academically and practically.

Asunto(s)

RESUMEN

The purpose of this paper is to introduce and discuss the following two functions that are considered to be important in human-coexistence robots and human-symbiotic robots: the method of generating emotional movements, and the method of transmitting behavioral intentions. The generation of emotional movements is to design the bodily movements of robots so that humans can feel specific emotions. Specifically, the application of Laban movement analysis, the development from the circumplex model of affect, and the imitation of human movements are discussed. However, a general technique has not yet been established to modify any robot movement so that it contains a specific emotion. The transmission of behavioral intentions is about allowing the surrounding humans to understand the behavioral intentions of robots. Specifically, informative motions in arm manipulation and the transmission of the movement intentions of robots are discussed. In the former, the target position in the reaching motion, the physical characteristics in the handover motion, and the landing distance in the throwing motion are examined, but there are still few research cases. In the latter, no groundbreaking method has been proposed that is fundamentally different from earlier studies. Further research and development are expected in the near future.

Asunto(s)

RESUMEN

This paper introduces a system that can estimate the deformation process of a deformed flat object (folded plane) and generate the input data for a robot with human-like dexterous hands and fingers to reproduce the same deformation of another similar object. The system is based on processing RGB data and depth data with three core techniques: a weighted graph clustering method for non-rigid point matching and clustering; a refined region growing method for plane detection on depth data based on an offset error defined by ourselves; and a novel sliding checking model to check the bending line and adjacent relationship between each pair of planes. Through some evaluation experiments, we show the improvement of the core techniques to conventional studies. By applying our approach to different deformed papers, the performance of the entire system is confirmed to have around 1.59 degrees of average angular error, which is similar to the smallest angular discrimination of human eyes. As a result, for the deformation of the flat object caused by folding, if our system can get at least one feature point cluster on each plane, it can get spatial information of each bending line and each plane with acceptable accuracy. The subject of this paper is a folded plane, but we will develop it into a robotic reproduction of general object deformation.

RESUMEN

This paper introduces an object model and an interaction method for a simulated experience of pottery on a potter's wheel. Firstly, we propose a layered cylinder model for a 3D object of the pottery on a potter's wheel. Secondly, we set three kinds of deformation functions to form the object model from an initial state to a bowl shape: shaping the external surface, forming the inner shape (deepening the opening and widening the opening), and reducing the total height. Next, as for the interaction method between a user and the model, we prepare a simple but similar method for hand-finger operations on pottery on a potter's wheel, in which the index finger movement takes care of the external surface and the total height, and the thumb movement makes the inner shape. Those are implemented in the three-dimensional aerial image interface (3DAII) developed in our laboratory to build a simulated experience system. We confirm the operation of the proposed object model (layered cylinder model) and the functions of the prepared interaction method (a simple but similar method to actual hand-finger operations) through a preliminary evaluation of participants. The participants were asked to make three kinds of bowl shapes (cylindrical, dome-shaped, and flat-type) and then they answered the survey (maneuverability, visibility, and satisfaction). All participants could make something like three kinds of bowl shapes in less than 30 min from their first touch.