EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CRASA: Chili Pepper Disease Diagnosis via Image Reconstruction Using Background Removal and Generative Adversarial Serial Autoencoder

Jongwook Si iD, Sungyoung Kim

Sensors · 2024

DOI: 10.3390/s24216892 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Jongwook Si und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer AI Convergence Engineering, Kumoh National Institute of Technology, Gumi 39177, Republic of Korea. Hauptthemen laut MEDLINE: Capsicum, Image Processing, Computer-Assisted, Neural Networks, Computer, Algorithms. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute for Advancement of Technology, Korea Government (MOTIE).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the recent development of smart farms, researchers are very interested in such fields. In particular, the field of disease diagnosis is the most important factor. Disease diagnosis belongs to the field of anomaly detection and aims to distinguish whether plants or fruits are normal or abnormal. The problem can be solved by binary or multi-classification based on a Convolutional Neural Network (CNN), but it can also be solved by image reconstruction. However, due to the limitation of the performance of image generation, SOTA’s methods propose a score calculation method using a latent vector error. In this paper, we propose a network that focuses on chili peppers and proceeds with background removal through GrabCut. It shows a high performance through an image-based score calculation method. Due to the difficulty of reconstructing the input image, the difference between the input and output images is large. However, the serial autoencoder proposed in this paper uses the difference between the two fake images, instead of the actual input, as a score. We propose a method of generating meaningful images using the GAN structure and classifying three results simultaneously by one discriminator. The proposed method showed a higher performance than previous research, and image-based scores showed the best performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CapsicumImage Processing, Computer-AssistedNeural Networks, ComputerAlgorithmsPlant Diseases

Stichwörter der Autor:innen

GANGrabCutanomaly detectionautoencoderdisease diagnosisimage reconstructionsmart farm

Autor:innen und Institutionen

  • Department of Computer AI Convergence Engineering, Kumoh National Institute of Technology, Gumi 39177, Republic of Korea.
  • Department of Computer Engineering, Kumoh National Institute of Technology, Gumi 39177, Republic of Korea.

ORCID-Profile: Jongwook Si

Förderung

  • Korea Institute for Advancement of Technology
  • Korea Government (MOTIE)

Zitieren

APA

Si, J., & Kim, S. (2024). CRASA: Chili Pepper Disease Diagnosis via Image Reconstruction Using Background Removal and Generative Adversarial Serial Autoencoder. Sensors. https://doi.org/10.3390/s24216892

Vancouver

Si J, Kim S. CRASA: Chili Pepper Disease Diagnosis via Image Reconstruction Using Background Removal and Generative Adversarial Serial Autoencoder. Sensors. 2024. doi:10.3390/s24216892

BibTeX
@article{Si2024,
  author = {Si, Jongwook and Kim, Sungyoung},
  title = {CRASA: Chili Pepper Disease Diagnosis via Image Reconstruction Using Background Removal and Generative Adversarial Serial Autoencoder},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24216892}
}
Kostenlos starten →