YMYasushi Makihara

Yasushi Makihara

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yasushi Makihara has a total of 70 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    GaitAGE: Gait Age and Gender Estimation Based on an Age- and Gender-Specific 3D Human Model

    by Xiang Li, Yasushi Makihara, Chi Xu, Yasushi Yagi

    Gait-based human age and gender estimation has potential applications in visual surveillance, such as searching for specific pedestrian groups and automatically counting customers by different ages/genders. Unlike most existing methods that exploit widely used appearance-based gait features (e.g., gait energy image and silhouettes) or simple model-based gait features (e.g., leg length, stride width/frequency, and head-to-body ratio), we explore a recently popular 3D human mesh model (i.e., skinned multi-person linear model (SMPL)), which is more robust to various covariates (e.g., view angles). Furthermore, instead of the commonly used gender-neutral SMPL model, we propose a simple yet effective method to generate more realistic age- and gender-specific human mesh models by interpolating among male, female, and infant SMPL models using two learned age and gender weights. The age weight controls the proportion of importance between male/female and infant models, which is learned in a data-driven scheme by considering the paired relation between ground-truth ages and age weights. The gender weight controls the proportion of importance between male and female models, which indicates the gender probability. Then, we explore the use of generated realistic mesh models for age and gender estimation. Finally, the human mesh reconstruction and age and gender estimation modules are integrated into a unified end-to-end framework for training and testing. The experimental results on the OU-MVLP and FVG datasets demonstrated that the proposed method achieved both good mesh reconstruction and state-of-the-art age and gender estimation results.


  • Open Access

    PPGCN: Phase-Aligned Periodic Graph Convolutional Network for Dual-Task-Based Cognitive Impairment Detection

    by Ákos Godó, Shuqiong Wu, Fumio Okura, Yasushi Makihara, Manabu Ikeda, Shunsuke Sato, Maki Suzuki, Yuto Satake, Daiki Taomoto, Yasushi Yagi

    Early detection methods for cognitive impairment are crucial for its effective treatment. Dual-task-based pipelines that rely on skeleton sequences can detect cognitive impairment reliably. Although such pipelines achieve state-of-the-art results by analyzing skeleton sequences of periodic stepping motion, we propose that their performance can be improved by decomposing the skeleton sequence into representative phase-aligned periods and focusing on them instead of the entire sequence. We present the phase-aligned periodic graph convolutional network, which is capable of processing phase-aligned periodic skeleton sequences. We trained it with a cross-modality feature fusion loss using a representative dataset of 392 samples annotated by medical professionals. As part of a dual-task cognitive impairment detection pipeline that relies on two-dimensional skeleton sequences extracted from RGB images to improve its general usability, our proposed method outperformed existing approaches and achieved a mean sensitivity of 0.9231 and specificity of 0.9398 in a four-fold cross-validation setup.


  • Online Model-based Gait Age and Gender Estimation

    by Allam Shehata, Ammar Alsherfawi, Levin Gäher, Xiang Li, Yasushi Makihara, Yasushi Yagi

    This paper presents an online human model-based framework for gait-based age and gender estimation from a sequence of monocular frames. More specifically, we fine-tune a human mesh recovery model (i.e., HMR) to estimate the shape and pose parameters of a predefined 3D human model (i.e., SMPL). We then utilize the estimated parameters to predict the age and gender of the walking subject. To make the age and gender estimation task more favorable for real-time applications, we consider estimating the corresponding probability distributions of age and gender, which preserve the prediction uncertainty. Experiments on the world’s largest multi-view gait age and gender estimation dataset showed the superiority of the proposed method compared to the existing appearance-based baseline. We implement online standalone and client-server systems based on the proposed framework to demonstrate the performance of real-time estimation. We further propose a geometric correction step to the input gait sequence for a more generalization capability of the online system.


  • Analysis of resist images with pattern defects by Hough transform

    by Yuqing Jin, Takahiro Kozawa, Kota Aoki, Tomoya Nakamura, Yasushi Makihara, Yasushi Yagi

    EUV technology has led to smaller device features, emphasizing the importance of minimizing defects in production. Research has focused on improving resist material uniformity to address variability in resulting patterns caused by stochastic factors, with attention paid to the underlying chemistry. In this study, we developed an automated method for analyzing resist patterns with defects using image recognition techniques. This method involves the analysis of line-and-space resist patterns using image processing technologies, comparison using established standards, and the identification of patterns with defects. A modified version of Hough transform technique was employed to automatically analyze approximately 2500 scanning electron microscopy images. Using our method, we can identify defective and deformed patterns by comparing the detected line-and-space resist patterns with the established standard. The indices that characterize the resist patterns with defects are proposed. Finally, simulated images were also used to uncover the chemical information underlying defective resist patterns.


  • Natural Image Matting with Attended Global Context

    by Yi-Yi Zhang, Li Niu, Yasushi Makihara, Jian-Fu Zhang, Wei-Jie Zhao, Yasushi Yagi, Li-Qing Zhang

  • Chemical information extraction from scanning electron microscopy images on the basis of image recognition

    by Yuqing Jin, Takahiro Kozawa, Kota Aoki, Tomoya Nakamura, Yasushi Makihara, Yasushi Yagi

    Traditional resist materials have faced challenges as the extreme ultraviolet (EUV) light source with a wavelength of 13.5 nm brought the evolution of lithography to the semiconductor industry. A significant issue in the development of resist materials or the discovery of new type resists is that numerous parameters involved in the resist pattern printing process cause the generation of defects. Meanwhile, the inherent chemical variation in resist materials and processes causes the stochastic defects. In addition, the stochastic defects caused by the inherent chemical variation in resist materials and processes become increasingly significant as feature scales continue to shrink. Consequently, the number of pattern data with failures is much greater than those without defects. However, by utilizing the information contained in pattern failures, chemical parameters can be adjusted to improve resist resolution. In this study, a new method is proposed for evaluating resist patterns with defects by fitting the experimental scanning electronic microscopy (SEM) images of line-and-space patterns with defects to simulated images.

  • Open Access

    Annotator-dependent uncertainty-aware estimation of gait relative attributes

    by Allam Shehata, Yasushi Makihara, Daigo Muramatsu, Atiqur Rahman Ahad, Yasushi Yagi


  • Individuality-Preserving Silhouette Extraction for Gait Recognition and Its Speedup

    by Masakazu Iwamura, Shunsuke Mori, Koichiro Nakamura, Takuya Tanoue, Yuzuko Utsumi, Yasushi Makihara, Daigo Muramatsu, Koichi Kise, Yasushi Yagi

    Most gait recognition approaches rely on silhouette-based representations due to high recognition accuracy and computational efficiency. A fundamental problem for those approaches is how to extract individuality-preserved silhouettes from real scenes accurately. Foreground colors may be similar to background colors, and the background is cluttered. Therefore, we propose a method of individuality-preserving silhouette extraction for gait recognition using standard gait models (SGMs) composed of clean silhouette sequences of various training subjects as shape priors. The SGMs are smoothly introduced into a well-established graph-cut segmentation framework. Experiments showed that the proposed method achieved better silhouette extraction accuracy by more than 2.3% than representative methods and better identification rate of gait recognition (improved by more than 11.0% at rank 20). Besides, to reduce the computation cost, we introduced approximation in the calculation of dynamic programming. As a result, without reducing the segmentation accuracy, we reduced 85.0% of the computational cost.