Skip to main navigation Skip to search Skip to main content

An enhanced MobileNetV4 architecture with CBAM for accurate classification mushroom toxicity

  • Alexandrio Kharisma Putra Marasin*
  • , Fitri Utaminingrum
  • , Mochammad Ali Fauzi
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The morphological resemblance between edible and toxic mushroom species presents significant public health challenges, contributing to thousands of annual poisoning incidents globally through visual classification errors. This study proposes an enhanced MobileNetV4 architecture integrating Convolutional Block Attention Module (CBAM) with optimized reduction ratio for accurate mushroom toxicity classification on mobile devices. Using a dataset of 2,000 mushroom images across two classes (edible and poisonous), we systematically evaluated six model variants combining MobileNetV4 Small/Large with CBAM at different reduction ratios. Results demonstrate that MobileNetV4 Large+CBAM 16 achieves 96.90% accuracy with only 13.27M parameters, while maintaining real-time inference speed of 29.7 ms per image. The integration of CBAM with reduction ratio 16 effectively enhances feature representation for distinguishing morphologically similar species, outperforming baseline MobileNetV4 and existing lightweight architectures. This work enables practical deployment of accurate mushroom toxicity classification systems on resource-constrained devices for food safety applications.

Original languageEnglish
Title of host publicationInternational Conference on Pattern Recognition and Image Analysis, PRIA 2025
EditorsJixin Ma, Philippe Fournier-Viger, Qian Zheng, Deepak Kumar Jain
PublisherSPIE
ISBN (Electronic)9798902323983
DOIs
Publication statusPublished - 15 Apr 2026
Event2025 International Conference on Pattern Recognition and Image Analysis, PRIA 2025 - Zhengzhou, China
Duration: 26 Dec 202528 Dec 2025

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume14172
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2025 International Conference on Pattern Recognition and Image Analysis, PRIA 2025
Country/TerritoryChina
CityZhengzhou
Period26/12/2528/12/25

Keywords

  • Convolutional Block Attention Module (CBAM)
  • Deep Learning
  • Food Safety
  • MobileNetV4
  • Mushroom Toxicity Classification

Fingerprint

Dive into the research topics of 'An enhanced MobileNetV4 architecture with CBAM for accurate classification mushroom toxicity'. Together they form a unique fingerprint.

Cite this