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

(4 citation statements)

References 11 publications

(10 reference statements)

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

“…[11][12][13][14][15] This massive dataset gives researchers from a wide range of fields the ability to develop useful machine learning (ML) algorithms for improving red raspberry quality in the industry. [16] These algorithms can do this by recognising various diseases and defects in the fruit, as well as by overcoming limitations such as increasing the performance detection rate accuracy and decreasing the computation time. [17] This database is available for free download in its entirety as two separate packages from the repository maintained by the Laboratory of Technological Research in Pattern Recognition located on the campus of the Catholic University of Maule.…”

Section: Literature Surveymentioning

confidence: 99%

Construction of binary classification model by ML with IP on the CIFAR10 dataset

Madhanmohan¹,

E.²

2022

INDJCSE

View full text Add to dashboard Cite

Learning through machines is currently considered to be one of the most popular topics on a global scale. It is even possible to say this about the modern electricity that is used in the world today. To be more specific about what machine learning is, however, we can say that it is just one method of teaching the machine by providing it with a significant amount of data. Machine Learning algorithms allow you to do image processing at scale, and with great detail. This work finds that both the ASC and the J48 have a high level, in addition to the same level of accuracy, which is 90%; both the ASC and the J48 have a high level, in addition to the same level of precision, which is 0.92. The ASC and J48 both have a high level of performance as well as the same recall level, which is 0.90; the ASC and J48 both have a high level of performance as well as the same ROC level, which is 0.98; and the ASC and J48 both have a high level of performance as well as the same PRC level, which is 0.97. The ASC and J48 both have the same high F-Measure value, which is 0.90; the ASC and J48 both have the same high Kappa value, which is 0.80; the ASC and J48 both have the same high MCC value, which is 0.82; and the ASC and J48 both have the same best performance, which is 0.10 of MAE. Both the ASC and the J48 have achieved the same level of performance, which is RMSE of 0.29. Both the ASC and the J48 have achieved the same best performance, which is equal to 20% of RAE. Both the ASC and the J48 have achieved the same level of performance, which is 57.27% of RRSE. Low-level accuracy, which is 60%, is possessed by the IBK. The precision of the FLDA is only at a low level, which is 0.65. Low level recall, which is 0.60, is exhibited by the IBK. The PRC for the IBK is quite low, coming in at 0.60. IBK has a PRC that is relatively low, coming in at 0.57. The F-Measure for the FLDA is the lowest possible, coming in at 0.55. The Kappa level of the IBK is quite low, coming in at 0.20. The MCC level in the IBK is the lowest possible, coming in at 0.25. The worst performance level for the IBK is 0.41 of MAE; the worst performance level for the IBK is 0.60 of RMSE; the worst performance level for the IBK is 82% of RAE; and the worst performance level for the IBK is 120.42% of RRSE.

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

Construction of binary classification model by ML with IP on the CIFAR10 dataset

Contact Info

Product

Resources

About