English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This study proposes a method based on lightweight convolutional neuralnetworks (CNN) and generative adversarial networks (GAN) for apple ripeness anddamage level detection tasks. Initially, a lightweight CNN model is designed byoptimizing the model's depth and width, as well as employing advanced modelcompression techniques, successfully reducing the model's parameter andcomputational requirements, thus enhancing real-time performance in practicalapplications. Simultaneously, attention mechanisms are introduced, dynamicallyadjusting the importance of different feature layers to improve the performancein object detection tasks. To address the issues of sample imbalance andinsufficient sample size, GANs are used to generate realistic apple images,expanding the training dataset and enhancing the model's recognition capabilitywhen faced with apples of varying ripeness and damage levels. Furthermore, byapplying the object detection network for damage location annotation on damagedapples, the accuracy of damage level detection is improved, providing a moreprecise basis for decision-making. Experimental results show that in appleripeness grading detection, the proposed model achieves 95.6\%, 93.8\%, 95.0\%,and 56.5 in precision, recall, accuracy, and FPS, respectively. In apple damagelevel detection, the proposed model reaches 95.3\%, 93.7\%, and 94.5\% inprecision, recall, and mAP, respectively. In both tasks, the proposed methodoutperforms other mainstream models, demonstrating the excellent performanceand high practical value of the proposed method in apple ripeness and damagelevel detection tasks.

Efficient Apple Maturity and Damage Assessment: A Lightweight Detection Model with GAN and Attention Mechanism