Hironori Takimoto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hironori Takimoto has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
Akihiro Kanagawa
Okayama Prefectural University
9 shared publications- Atsushi J. Nagano
Bioscience and Biotechnology Center, Nagoya University , Nagoya, Aichi, 464-8601
3 shared publications Hitoshi Yamauchi
Faculty of Computer Science and Systems Engineering, Okayama Prefectural University, Okayama, Japan
2 shared publicationsKatsumi Yamamoto
Faculty of Computer Science and Systems Engineering Okayama Prefectural University 111 Kuboki, Soja‐Shi, Okayama, 719‐1197 Japan
2 shared publicationsKensuke Okubo
Faculty of Computer Science and Systems Engineering Okayama Prefectural University 111 Kuboki, Soja‐Shi, Okayama, 719‐1197 Japan
2 shared publications- Kentaro K. Shimizu
Department of Evolutionary Biology and Environmental Studies, University of Zürich, Zürich, Switzerland
2 shared publications
Latest Publications
- 1 September 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 35 (05) , 1-15
Lost-saliency-guided targeted recoloring with a resolution-calibrated few-shot saliency evaluation
Recoloring (daltonization) helps observers with color-vision deficiency (CVD) distinguish colors they would otherwise confuse, but a single global transform changes the whole image and tends to look unnatural. We propose targeted recoloring, which concentrates the color change where it is needed. A learned lost-saliency map, the positive part of the difference between normal-vision and dichromat saliency, marks the regions that are salient in normal vision but lose attention under dichromacy, and recoloring is concentrated on those regions by weighting the optimization with that map, in CIELAB with lightness fixed and only the chromatic channels free. The dichromat saliency needed to build the map is predicted from about 100 images by adapting a frozen DINOv2 backbone with low-rank adaptation. On the EToCVD benchmark, measured by predictor-independent color metrics, targeted recoloring improves both naturalness and distinguishability over full daltonization and a simplified Kuhn-style baseline, with the color change concentrated in the target region. Because the benchmark provides only fixations, a saliency-map target has to be made by smoothing, and we show that a fixed-pixel Gaussian on variable-resolution images is mis-calibrated and can reverse predictor rankings; we demonstrate this on the independent Toronto benchmark and remove it by calibrating to one degree of visual angle. The learned predictors are trained out of fold, and we report the limits of the predictor honestly.
- 1 September 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 35 (05) , 1-15
Lost-saliency-guided targeted recoloring with a resolution-calibrated few-shot saliency evaluation
Recoloring (daltonization) helps observers with color-vision deficiency (CVD) distinguish colors they would otherwise confuse, but a single global transform changes the whole image and tends to look unnatural. We propose targeted recoloring, which concentrates the color change where it is needed. A learned lost-saliency map, the positive part of the difference between normal-vision and dichromat saliency, marks the regions that are salient in normal vision but lose attention under dichromacy, and recoloring is concentrated on those regions by weighting the optimization with that map, in CIELAB with lightness fixed and only the chromatic channels free. The dichromat saliency needed to build the map is predicted from about 100 images by adapting a frozen DINOv2 backbone with low-rank adaptation. On the EToCVD benchmark, measured by predictor-independent color metrics, targeted recoloring improves both naturalness and distinguishability over full daltonization and a simplified Kuhn-style baseline, with the color change concentrated in the target region. Because the benchmark provides only fixations, a saliency-map target has to be made by smoothing, and we show that a fixed-pixel Gaussian on variable-resolution images is mis-calibrated and can reverse predictor rankings; we demonstrate this on the independent Toronto benchmark and remove it by calibrating to one degree of visual angle. The learned predictors are trained out of fold, and we report the limits of the predictor honestly.
- Open Access
- 1 June 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Advances in Applied Sciences
- Vol. 15 (2) , 451-461
Comparison of thermal and non-thermal images for tomato fruit detection
Farmers use manual observation to sort, grade, and estimate tomato production results to meet market demands. However, this method requires a lot of energy and time, making it unsuitable for large-scale tomato cultivation utilizing the detection process. This study aims to develop the automatic tomato detection technology in an industrial environment based on a conveyor belt by using thermal or non-thermal imaging and you only look once version 8 (YOLOv8). The dataset consists of 570 images obtained from each thermal and non-thermal camera and has undergone augmentation techniques to enrich the data variety. The model was trained and validated using 640×640-pixel images for 40 epochs. In this paper, we conduct a comparative analysis of the tomato detection result using YOLOv8 on thermal and non-thermal imaging. The results indicate that the model trained with thermal data significantly outperformed the non-thermal model, achieving 99% precision, 98% recall, 98% F1-score, and 99% mean average precision (mAP)50 during validation. The thermal model received a 99% accuracy rate during validation, while the non-thermal model attained 94% accuracy, exhibiting a slightly poorer performance and committing several mistakes in detection. The use of thermal cameras on moving automation systems has demonstrated its capability and effectiveness, making it more optimal for application in the agricultural industry.
- 1 June 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Advances in Applied Sciences
- Vol. 15 (2) , 451-461
Open AccessComparison of thermal and non-thermal images for tomato fruit detection
Farmers use manual observation to sort, grade, and estimate tomato production results to meet market demands. However, this method requires a lot of energy and time, making it unsuitable for large-scale tomato cultivation utilizing the detection process. This study aims to develop the automatic tomato detection technology in an industrial environment based on a conveyor belt by using thermal or non-thermal imaging and you only look once version 8 (YOLOv8). The dataset consists of 570 images obtained from each thermal and non-thermal camera and has undergone augmentation techniques to enrich the data variety. The model was trained and validated using 640×640-pixel images for 40 epochs. In this paper, we conduct a comparative analysis of the tomato detection result using YOLOv8 on thermal and non-thermal imaging. The results indicate that the model trained with thermal data significantly outperformed the non-thermal model, achieving 99% precision, 98% recall, 98% F1-score, and 99% mean average precision (mAP)50 during validation. The thermal model received a 99% accuracy rate during validation, while the non-thermal model attained 94% accuracy, exhibiting a slightly poorer performance and committing several mistakes in detection. The use of thermal cameras on moving automation systems has demonstrated its capability and effectiveness, making it more optimal for application in the agricultural industry.
- 2 December 2025
- Published by Springer Nature
- p. 354-365
Saliency Retargeting Considering Aesthetics Quality Based on Deep Learning
- 2 December 2025
- Published by Springer Nature
- p. 354-365
Saliency Retargeting Considering Aesthetics Quality Based on Deep Learning
- 1 January 2023
- Published by Japan Society of Mechanical Engineers in Proceedings of International Conference on Design and Concurrent Engineering & Manufacturing Systems Conference
- Vol. 2023, 21
Cross-Cultural Teamwork Program for Japanese and Malaysian University Students
Concurrent Engineering (CE) is a methodology aimed at reducing costs and time in production processes. To achieve this goal, collaboration among various activities is essential, including design, manufacturing and assembly, marketing and distribution, and customer relations. Collaboration among individuals from different activities is particularly crucial for the success of CE, not only in industry but also in academia, where global research and educational collaboration are highly valued. In 2014, TMAC or Tokushima University (TU)-Universiti Teknikal Malaysia Melaka (UTeM) Academic Centre, was established to promote academic collaboration between the two universities. Among its various activities, the TMAC Design Workshop (TDW) series plays a central role in facilitating student exchanges between the two universities and enhancing student education. This year, TDW series has expanded to include participation from Okayama Prefectural University (OPU), further strengthening the collaboration among the three universities. This paper presents the educational program of the TMAC Design Workshop (TDW) 2023, which is designed to cultivate teamwork skills within the context of Concurrent Engineering (CE). The primary objective of this program is to enable students from Japan and Malaysia to comprehend the significance of productive collaboration in a multicultural setting. The paper specifically concentrates on TDW2023, an event that transpired in February of the present year. It presents an overview of the global teamwork activities carried out by students from Japan and Malaysia during the workshop, elucidating their accomplishments, evaluations, and outlining potential avenues for future study.
- 1 January 2023
- Published by Japan Society of Mechanical Engineers in Proceedings of International Conference on Design and Concurrent Engineering & Manufacturing Systems Conference
- Vol. 2023, 21
Cross-Cultural Teamwork Program for Japanese and Malaysian University Students
Concurrent Engineering (CE) is a methodology aimed at reducing costs and time in production processes. To achieve this goal, collaboration among various activities is essential, including design, manufacturing and assembly, marketing and distribution, and customer relations. Collaboration among individuals from different activities is particularly crucial for the success of CE, not only in industry but also in academia, where global research and educational collaboration are highly valued. In 2014, TMAC or Tokushima University (TU)-Universiti Teknikal Malaysia Melaka (UTeM) Academic Centre, was established to promote academic collaboration between the two universities. Among its various activities, the TMAC Design Workshop (TDW) series plays a central role in facilitating student exchanges between the two universities and enhancing student education. This year, TDW series has expanded to include participation from Okayama Prefectural University (OPU), further strengthening the collaboration among the three universities. This paper presents the educational program of the TMAC Design Workshop (TDW) 2023, which is designed to cultivate teamwork skills within the context of Concurrent Engineering (CE). The primary objective of this program is to enable students from Japan and Malaysia to comprehend the significance of productive collaboration in a multicultural setting. The paper specifically concentrates on TDW2023, an event that transpired in February of the present year. It presents an overview of the global teamwork activities carried out by students from Japan and Malaysia during the workshop, elucidating their accomplishments, evaluations, and outlining potential avenues for future study.
- Open Access
- 7 August 2022
- Published by Taylor & Francis in Cogent Engineering
- Vol. 9 (1)
Study on relationship between composition and prediction of photo aesthetics using CNN
The purpose of image aesthetics assessment is to automatically predict the perceived quality of an image. Convolutional neural network (CNN) based on deep learning has been used for aesthetics assessment and has displayed potential results. Our final objective is to identify features that contribute to the estimation of aesthetic quality by using explainable AI. In this study, we focused on composition as the first step. By applying clustering to the attention maps obtained by CNN and Grad-CAM++, it was experimentally verified whether the CNN model considers composition for aesthetics assessment. In addition, we verified whether the aesthetic quality features that humans pay attention to differ according to photographic categories such as landscape or portrait.
- 7 August 2022
- Published by Taylor & Francis in Cogent Engineering
- Vol. 9 (1)
Open AccessStudy on relationship between composition and prediction of photo aesthetics using CNN
The purpose of image aesthetics assessment is to automatically predict the perceived quality of an image. Convolutional neural network (CNN) based on deep learning has been used for aesthetics assessment and has displayed potential results. Our final objective is to identify features that contribute to the estimation of aesthetic quality by using explainable AI. In this study, we focused on composition as the first step. By applying clustering to the attention maps obtained by CNN and Grad-CAM++, it was experimentally verified whether the CNN model considers composition for aesthetics assessment. In addition, we verified whether the aesthetic quality features that humans pay attention to differ according to photographic categories such as landscape or portrait.
- Open Access
- 11 July 2022
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 36 (1)
Anomaly Detection Using Siamese Network with Attention Mechanism for Few-Shot Learning
Automated inspection using deep-learning has been attracting attention for visual inspection at the manufacturing site. However, the inability to obtain sufficient abnormal product data for training deep- learning models is a problem in practical application. This study proposes an anomaly detection method based on the Siamese network with an attention mechanism for a small dataset. Moreover, attention branch loss (ABL) is proposed for Siamese network to render more task-specific attention maps from attention mechanism. Experimental results confirm that the proposed method with the attention mechanism and ABL is effective even with limited abnormal data.
- 11 July 2022
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 36 (1)
Open AccessAnomaly Detection Using Siamese Network with Attention Mechanism for Few-Shot Learning
Automated inspection using deep-learning has been attracting attention for visual inspection at the manufacturing site. However, the inability to obtain sufficient abnormal product data for training deep- learning models is a problem in practical application. This study proposes an anomaly detection method based on the Siamese network with an attention mechanism for a small dataset. Moreover, attention branch loss (ABL) is proposed for Siamese network to render more task-specific attention maps from attention mechanism. Experimental results confirm that the proposed method with the attention mechanism and ABL is effective even with limited abnormal data.
- Open Access
- 1 December 2021
- Published by Elsevier in Ecological Informatics
- Vol. 66
Using a two-stage convolutional neural network to rapidly identify tiny herbivorous beetles in the field
- 1 December 2021
- Published by Elsevier in Ecological Informatics
- Vol. 66
Open AccessUsing a two-stage convolutional neural network to rapidly identify tiny herbivorous beetles in the field
- Open Access
Integration of short- and long-term responses to environmental stimuli shape seasonal transcriptome dynamics
Plants must respond to various seasonally changing environmental stimuli. In a previous study, seasonally oscillating genes were identified by a massive time-series transcriptome analysis for the wild population of Arabidopsis halleri ssp. gemmifera , a sister species to Arabidopsis thaliana . It was not clear how environmental stimuli shaped the seasonal expression pattern of these seasonally oscillating genes. In this study we show that responses in different time-scales contributed to the formation of seasonal expression patterns for several genes. To analyze the seasonally oscillating genes, we established an experimental system to mimic seasonal expression trends using A. thaliana and a “smart growth chamber mini,” a hand-made low-cost small chamber. Arabidopsis thaliana plants were cultured under conditions that mimicked the average monthly temperatures and daylengths under different day-scale incubation. In total, the seasonal trends of 1627 seasonally oscillating genes were mimicked, and they showed varying temporal responses (constant, transient, and incremental) to environmental stimuli. Our results suggest that plants perceive and integrate information regarding environmental stimuli in the field by combining seasonally oscillating genes with different temporal responsiveness.
Open AccessIntegration of short- and long-term responses to environmental stimuli shape seasonal transcriptome dynamics
Plants must respond to various seasonally changing environmental stimuli. In a previous study, seasonally oscillating genes were identified by a massive time-series transcriptome analysis for the wild population of Arabidopsis halleri ssp. gemmifera , a sister species to Arabidopsis thaliana . It was not clear how environmental stimuli shaped the seasonal expression pattern of these seasonally oscillating genes. In this study we show that responses in different time-scales contributed to the formation of seasonal expression patterns for several genes. To analyze the seasonally oscillating genes, we established an experimental system to mimic seasonal expression trends using A. thaliana and a “smart growth chamber mini,” a hand-made low-cost small chamber. Arabidopsis thaliana plants were cultured under conditions that mimicked the average monthly temperatures and daylengths under different day-scale incubation. In total, the seasonal trends of 1627 seasonally oscillating genes were mimicked, and they showed varying temporal responses (constant, transient, and incremental) to environmental stimuli. Our results suggest that plants perceive and integrate information regarding environmental stimuli in the field by combining seasonally oscillating genes with different temporal responsiveness.
- Open Access
Using a two-stage convolutional neural network to rapidly identify tiny herbivorous beetles in the field
Recently, deep convolutional neural networks (CNN) have been adopted to help beginners identify insect species from field images. However, the application of these methods on the identification of tiny congeneric species moving across heterogeneous background remains difficult. To enable rapid and automatic identification in the field, we customized a method involving real-time object detection of two Phyllotreta beetles. We first performed data augmentation using transformations, syntheses, and random erasing of the original images. We then proposed a two-stage method for the detection and identification of small insects based on CNN, where YOLOv4 and EfficientNet were used as a region proposal network and a re-identification method, respectively. Evaluation of the model revealed that one-step object detection by YOLOv4 alone was not precise (Precision = 0.55) when classifying two species of flea beetles and background objects. In contrast, the two-step CNNs improved the precision (Precision = 0.89) with moderate accuracy (F-measure = 0.55) and acceptable speed (ca. 5 frames per second for full HD images) of detection and identification of insect species in the field. Although real-time identification of tiny insects remains a challenge in the field, our method aids in improving small object detection on a heterogeneous background.
Open AccessUsing a two-stage convolutional neural network to rapidly identify tiny herbivorous beetles in the field
Recently, deep convolutional neural networks (CNN) have been adopted to help beginners identify insect species from field images. However, the application of these methods on the identification of tiny congeneric species moving across heterogeneous background remains difficult. To enable rapid and automatic identification in the field, we customized a method involving real-time object detection of two Phyllotreta beetles. We first performed data augmentation using transformations, syntheses, and random erasing of the original images. We then proposed a two-stage method for the detection and identification of small insects based on CNN, where YOLOv4 and EfficientNet were used as a region proposal network and a re-identification method, respectively. Evaluation of the model revealed that one-step object detection by YOLOv4 alone was not precise (Precision = 0.55) when classifying two species of flea beetles and background objects. In contrast, the two-step CNNs improved the precision (Precision = 0.89) with moderate accuracy (F-measure = 0.55) and acceptable speed (ca. 5 frames per second for full HD images) of detection and identification of insect species in the field. Although real-time identification of tiny insects remains a challenge in the field, our method aids in improving small object detection on a heterogeneous background.
- 3 November 2020
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 35 (1) , 25-40
Image Aesthetics Assessment Based on Multi-stream CNN Architecture and Saliency Features
In this paper, we explore how higher-level perceptual information based on visual attention can be used for aesthetic assessment of images. We assume that visually dominant subjects in a photograph influence stronger aesthetic interest. In other words, visual attention may be a key to predicting photographic aesthetics. Our proposed aesthetic assessment method, which is based on multi-stream and multi-task convolutional neural networks (CNNs), extracts global features and saliency features from an input image. These provide higher-level visual information such as the quality of the photo subject and the subject–background relationship. Results from our experiments support the effectiveness of our approach.
- 3 November 2020
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 35 (1) , 25-40
Image Aesthetics Assessment Based on Multi-stream CNN Architecture and Saliency Features
In this paper, we explore how higher-level perceptual information based on visual attention can be used for aesthetic assessment of images. We assume that visually dominant subjects in a photograph influence stronger aesthetic interest. In other words, visual attention may be a key to predicting photographic aesthetics. Our proposed aesthetic assessment method, which is based on multi-stream and multi-task convolutional neural networks (CNNs), extracts global features and saliency features from an input image. These provide higher-level visual information such as the quality of the photo subject and the subject–background relationship. Results from our experiments support the effectiveness of our approach.