In recent years, deep learning (DL) has been widely studied using various methods across the globe, especially with respect to training methods and network structures, proving highly effective in a wide range of tasks and applications, including image, speech, and text recognition. One important aspect of this advancement is involved in the effort of designing and upgrading neural architectures, which has been consistently attempted thus far. However, designing such architectures requires the combined knowledge and know-how of experts from each relevant discipline and a series of trial-and-error steps. In this light, automated neural architecture search (NAS) methods are increasingly at the center of attention; this paper aimed at summarizing the basic concepts of NAS while providing an overview of recent studies on the applications of NAS. It is worth noting that most previous survey studies on NAS have been focused on perspectives of hardware or search strategies. To the best knowledge of the present authors, this study is the first to look at NAS from a computer vision perspective. In the present study, computer vision areas were categorized by task, and recent trends found in each study on NAS were analyzed in detail.

Recently, real-time human age estimation based on facial images has been applied in various areas. Underneath this phenomenon lies an awareness that age estimation plays an important role in applying big data to target marketing for age groups, product demand surveys, consumer trend analysis, etc. However, in a real-world environment, various optical and motion blurring effects can occur. Such effects usually cause a problem in fully capturing facial features such as wrinkles, which are essential to age estimation, thereby degrading accuracy. Most of the previous studies on age estimation were conducted for input images almost free from blurring effect. To overcome this limitation, we propose the use of a deep ResNet-152 convolutional neural network for age estimation, which is robust to various optical and motion blurring effects of visible light camera sensors. We performed experiments with various optical and motion blurred images created from the park aging mind laboratory (PAL) and craniofacial longitudinal morphological face database (MORPH) databases, which are publicly available. According to the results, the proposed method exhibited better age estimation performance than the previous methods.

The present study describes the development of a wearable device designed to assist those who work in an unstructured posture. In the manufacturing sector, industrial accidents have been steadily on the rise due to poor work environments and excessive workloads imposed on workers. Against this backdrop, the present study aimed to analyze various types of work, especially those performed in unstructured postures by heavy industry workers, who are frequently exposed to high workloads and poor work environments. Based on the analysis results, an attempt was made to develop a shoulder muscle-assistive wearable device capable of assisting a wearer who is working using their shoulder muscles. Various types of unstructured posture work are performed in heavy industries, including activities such as the welding and grinding of ship components and plant structures. They are typically conducted in narrow spaces with limited postures, causing many workers to suffer muscle fatigue. In the present study, as the first step of developing a shoulder muscle-assistive wearable device, different working scenarios were simulated, and the corresponding motion data and required torque values were estimated using motion capture devices. The obtained motion data and required torque values were reflected in the design of the wearable device. The main structural body of the shoulder muscle-assistive wearable device was made of a carbon fiber-reinforced composite to be lightweight. This shoulder muscle-assistive wearable device was designed to fully cover the range of motion for workers working in unstructured postures while generating the torque required for a given job, thereby enhancing the muscular endurance of the workers. The gravity compensation module of the designed shoulder muscle-assistive wearable device generates a support force of 4.47 Nm per shoulder. The shoulder muscle assistive wearable device was developed to provide support for approximately 30% of the shoulder joint’s maximum torque generated in overhead tasks. This shoulder muscle-assistive wearable device is expected to contribute to improving the productivity of field workers, while reducing the occurrence of musculoskeletal injuries arising from the aging of the working-age population.

RipenessGAN is a novel Generative Adversarial Network (GAN) designed to generate synthetic images across different ripeness stages of jujubes (green fruit, white ripe fruit, semi-red fruit, and fully red fruit), aiming to provide balanced training data for diverse applications beyond classification accuracy. This study addresses the problem of data imbalance by augmenting each ripeness stage using our proposed Growth Day Embedding mechanism, thereby enhancing the performance of downstream classification models. The core innovation of RipenessGAN lies in its ability to capture continuous temporal transitions among discrete ripeness classes by incorporating fine-grained growth day information (0–56 days) in addition to traditional class labels. The experimental results show that RipenessGAN produces synthetic data with higher visual quality and greater diversity compared to CycleGAN. Furthermore, the classification models trained on the enriched dataset exhibit more consistent and accurate performance. We also conducted comprehensive comparisons of RipenessGAN against CycleGAN and class-conditional diffusion models (DDPM) under strictly controlled and fair experimental settings, carefully matching model architectures, computational resources, training conditions, and evaluation metrics. The results indicate that although diffusion models yield highly realistic images and CycleGAN ensures stable cycle-consistent generation, RipenessGAN provides superior practical benefits in training efficiency, temporal controllability, and adaptability for agricultural applications. This research demonstrates the potential of RipenessGAN to mitigate data imbalance in agriculture and highlights its scalability to other crops.

This paper presents a novel method in the field of robotic vision, specifically designed to operate effectively under various lighting conditions. We propose an Image Enhancement Method for parcel loading status recognition, which addresses the challenge of insufficient lighting inside freight trucks without requiring lighting adjustments. Our approach integrates GAN and YOLO v5 into an end-to-end structure, where the detection network’s outputs influence the training of the generative network. Unlike traditional methods that focus solely on enhancing low-light image visibility, our method is optimized to maximize detection accuracy. To demonstrate the superiority of our approach, we constructed a setup resembling a freight truck, collected a dataset under varying lighting conditions, and conducted extensive experiments. The latter sections of the paper review relevant studies on vision data control in computer vision, provide a detailed explanation of our method, describe the experimental setup and database acquisition process, and discuss the results and analyses. The conclusion is presented in Section 6.