QuinceSet: Dataset of annotated Japanese quince images for object detection

Kaufmane, E.; Sudars, Kaspars; Namatēvs, Ivars; Kalniņa, Ieva; Judvaitis, Jānis; Balašs, Rihards; Strautina, S.

doi:10.1016/j.dib.2022.108332

Cited by 9 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Annotations are saved as XML files in PASCAL VOC format. Moreover, it also supports YOLO and CreateML formats [ 58 , 59 ]. During the labelling process, the area of object and its class belonging will be determined.…”

Section: Resultsmentioning

confidence: 99%

Deep Learning for Clothing Style Recognition Using YOLOv5

Chang

Zhang

2022

Micromachines

View full text Add to dashboard Cite

With the rapid development of artificial intelligence, much more attention has been paid to deep learning. However, as the complexity of learning algorithms increases, the needs of computation power of hardware facilities become more crucial. Instead of the focus being on computing devices like GPU computers, a lightweight learning algorithm could be the answer for this problem. Cross-domain applications of deep learning have attracted great interest amongst researchers in academia and industries. For beginners who do not have enough support with software and hardware, an open-source development environment is very helpful. In this paper, a relatively lightweight algorithm YOLOv5s is addressed, and the Google Colab is used for model training and testing. Based on the developed environment, many state-of-art learning algorithms can be studied for performance comparisons. To highlight the benefits of one-stage object detection algorithms, the recognition of clothing styles is investigated. The image samples are selected from datasets of fashion clothes and the web crawling of online stores. The image data are categorized into five groups: plaid; plain; block; horizontal; and vertical. Average precison, mean average precison, recall, F1-score, model size, and frame per second are the metrics used for performance validations. From the experimental outcomes, it shows that YOLOv5s is better than other learning algorithms in the recognition accuracy and detection speed.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep Learning for Clothing Style Recognition Using YOLOv5

Chang

Zhang

2022

Micromachines

View full text Add to dashboard Cite

show abstract

“…A large amount of annotated data are needed when training the deep learning model. In this study, the worms in each image were annotated manually using the image annotation software LabelImg, which supports the Visual Object Classes (VOC) format [ 65 , 66 ]. This software can generate Extensible Markup Language (XML) files for the model.…”

Section: Methodsmentioning

confidence: 99%

Deep Learning for Microfluidic-Assisted Caenorhabditis elegans Multi-Parameter Identification Using YOLOv7

et al. 2023

View full text Add to dashboard Cite

The Caenorhabditis elegans (C. elegans) is an ideal model organism for studying human diseases and genetics due to its transparency and suitability for optical imaging. However, manually sorting a large population of C. elegans for experiments is tedious and inefficient. The microfluidic-assisted C. elegans sorting chip is considered a promising platform to address this issue due to its automation and ease of operation. Nevertheless, automated C. elegans sorting with multiple parameters requires efficient identification technology due to the different research demands for worm phenotypes. To improve the efficiency and accuracy of multi-parameter sorting, we developed a deep learning model using You Only Look Once (YOLO)v7 to detect and recognize C. elegans automatically. We used a dataset of 3931 annotated worms in microfluidic chips from various studies. Our model showed higher precision in automated C. elegans identification than YOLOv5 and Faster R-CNN, achieving a mean average precision (mAP) at a 0.5 intersection over a union (mAP@0.5) threshold of 99.56%. Additionally, our model demonstrated good generalization ability, achieving an mAP@0.5 of 94.21% on an external validation set. Our model can efficiently and accurately identify and calculate multiple phenotypes of worms, including size, movement speed, and fluorescence. The multi-parameter identification model can improve sorting efficiency and potentially promote the development of automated and integrated microfluidic platforms.

show abstract

“…Following the completion of data augmentation processing, it is necessary to assign labels to these data. The authors employed labelImg, a tool for image annotation, to assign labels to data [12]. Afterward, the dataset was divided into training and testing sets for the cargo hold recognition model.…”

Section: Collection and Data Processing Of The Cargo Hold Imagementioning

confidence: 99%

Design of an AI Model for a Fully Automatic Grab-Type Ship Unloader System

Ngo,

Lee,

Kim

et al. 2024

JMSE

View full text Add to dashboard Cite

In seaports, the automatic Grab-Type Ship Unloader (GTSU) stands out for its ability to automatically load and unload materials, offering the potential for substantial productivity improvement and cost reduction. Developing a fully automatic GTSU, however, presents a unique challenge: the system must autonomously determine the position of the cargo hold and the coordinates of the working point and identify potential hazards during material loading and unloading. This paper proposes AI models designed to detect cargo holds, extract working points, and support collision risk warnings, utilizing both the LiDAR sensor and the camera in the GTSU system. The model for cargo hold detection and collision warning was developed using image data of the cargo hold and grab, employing the You Only Look Once model. Concurrently, the model responsible for extracting the coordinates of working points for the GTSU system was designed by integrating the cargo hold detection and point cloud processing models. After testing the AI models for the lab-scale GTSU, the results show that the cargo hold detection and collision warning models achieve an accuracy of approximately 96% and 90%, respectively. Additionally, the working point coordinates extracted from the sensor system show a deviation of 5–10% compared to traditional measurements.

show abstract

QuinceSet: Dataset of annotated Japanese quince images for object detection

Cited by 9 publications

References 11 publications

Deep Learning for Clothing Style Recognition Using YOLOv5

Deep Learning for Clothing Style Recognition Using YOLOv5

Deep Learning for Microfluidic-Assisted Caenorhabditis elegans Multi-Parameter Identification Using YOLOv7

Design of an AI Model for a Fully Automatic Grab-Type Ship Unloader System

Contact Info

Product

Resources

About