Unsupervised anomaly detection for pome fruit quality inspection using X-ray radiography

[Display omitted] •X-ray radiographs were used to identify apple and pear fruit with internal disorders.•Classification was achieved by a fully convolutional autoencoder.•We evaluated our model on both simulated and real data.•Our model outperforms the traditional autoencoder architecture. A novel f...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers and electronics in agriculture Ročník 226; s. 109364
Hlavní autoři: Tempelaere, Astrid, He, Jiaqi, Van Doorselaer, Leen, Verboven, Pieter, Nicolai, Bart, Valerio Giuffrida, Mario
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.11.2024
Témata:
Anomaly detection
Autoencoder
Deep learning
Food quality inspection
X-ray imaging
Deep learning
Food quality inspection
Autoencoder
Anomaly detection
X-ray imaging
ISSN:0168-1699
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:[Display omitted] •X-ray radiographs were used to identify apple and pear fruit with internal disorders.•Classification was achieved by a fully convolutional autoencoder.•We evaluated our model on both simulated and real data.•Our model outperforms the traditional autoencoder architecture. A novel fully convolutional autoencoder (convAE) was introduced to analyze X-ray radiography images of ‘Braeburn’ apples and ‘Conference’ pears with and without disorders for online sorting purposes. The model was solely trained on either apple or pear samples without disorders and outperformed a traditional autoencoder (AE) across multiple test sets. We evaluated our approach using the area under the curve (AUC) as an evaluation metric. A cross-test experiment further demonstrated consistent performance between a model trained on apple data for classifying pear fruit (accuracy: 71 %) and a pear-specific model (accuracy: 70 %). We also evaluated models trained on simulated X-ray radiographs with real ones, and vice versa. For instance, under scenario of training on real data and testing on simulated X-ray radiographs, an accuracy of 80 % for detecting disordered non-consumable pear was achieved. This work provides valuable insights into anomaly detection for apples and pears with several disorders.
ISSN:0168-1699
DOI:10.1016/j.compag.2024.109364