Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 16, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

A Deep Learning Model for Chili Pepper Fruit Shape Classification Using DenseNet-121 and CBAM.

Zongjun Li¹, Yinghua Li¹, Hu Zhao¹

¹Guangxi Academy of Agricultural Sciences, Nanning 530007, China.

Plants (Basel, Switzerland)

|July 15, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

eDNA-qPCR Reveals Spatial Biomass and Habitat Associations of the Endangered <i>Brachymystax lenok tsinlingensis</i> in Zhouzhi Heihe River.

Animals : an open access journal from MDPI·2026

Same author

Generalization of negative memories drives the development of psychological distress-related behaviors.

Innovation (Cambridge (Mass.))·2026

Same author

Aging Resistance Performance and Mechanisms of SBS-Modified Bitumen Enhanced with Carbon Nanomaterials.

Langmuir : the ACS journal of surfaces and colloids·2026

Same author

The quintessential high-risk profile: advanced management strategies for placenta accreta spectrum in patients with advanced maternal age and IVF conception.

BMC pregnancy and childbirth·2026

Same author

Differentiating hemorrhagic shock and organophosphate poisoning through integrated skin microbiome-metabolome signatures.

BMC microbiology·2026

Same author

Size-dependent electrobending in piezoceramics mediated by gradient defect dipoles.

Materials horizons·2026

This study introduces an improved DenseNet-121 model for intelligent chili pepper grading, enhancing machine vision in agriculture. The model achieves high accuracy and efficiency for automated sorting equipment.

Area of Science:

Agricultural Engineering
Computer Vision
Machine Learning

Background:

Manual grading of chili peppers lacks efficiency and consistency.
Accurate fruit shape recognition is crucial for post-harvest agricultural sorting.
Existing methods struggle with the demands of modern agricultural automation.

Purpose of the Study:

To develop an intelligent recognition method for chili pepper grading using machine vision.
To improve the accuracy and efficiency of agricultural sorting equipment.
To enable real-time deployment on resource-constrained edge devices.

Main Methods:

An improved DenseNet-121 network was utilized as the backbone.
The Convolutional Block Attention Module (CBAM) was integrated for enhanced feature focus.

Keywords:

CBAM DenseNet-121 chili pepper deep learning fruit shape

Related Experiment Videos

Last Updated: Jul 16, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Regularization strategies (Dropout, weight decay) and label smoothing were applied to optimize the model.

Main Results:

The model achieved 90.09% precision, 89.60% recall, and 89.74% overall accuracy.
It demonstrated a low inference time of 7.35 ms with 7.09 M parameters.
The model showed robustness to environmental noise and high classification accuracy.

Conclusions:

The proposed model offers an optimal balance of accuracy, robustness, and computational efficiency.
It has strong potential for real-time deployment in agricultural optical sorting equipment.
This intelligent recognition method addresses the need for automated, high-precision agricultural grading.