Indonesian Journal of Multidisciplinary Science
Vol. 4 No. 7 (2025): Indonesian Journal of Multidisciplinary Science

Comparative Analysis of ROI Segmentation and Cropping for Apple Fruit Disease Classification Using MobileNetV2

Vriska Frisiliya (STMIK IKMI Cirebon)



Article Info

Publish Date
27 Oct 2026

Abstract

Background: Image-based apple fruit disease classification can support consistent inspection, but its performance may depend on preprocessing and class imbalance. Objective: This study examined whether cropping or region of interest (ROI) segmentation improves MobileNetV2 classification of Blotch, Normal, Rot, and Scab apple images. Method: A comparative experiment evaluated five preprocessing scenarios (original images, center cropping, HSV ROI segmentation, GrabCut ROI segmentation, and hybrid ROI plus cropping) under identical training settings. The 5,246 cleaned images were split into 3,672 training, 787 validation, and 787 test images and evaluated using accuracy, macro-precision, macro-recall, macro-F1, per-class F1-scores, and a confusion matrix. Results: In a single run, center cropping produced the highest scores (85.01% accuracy; 84.91% macro-F1), followed by the original images (83.86%; 83.64%), with overlapping 95% confidence intervals. HSV, GrabCut, and hybrid preprocessing did not exceed the baseline. Scab was the most difficult class, and Rot and Scab were most often misclassified as Blotch. Conclusion: Complex preprocessing did not necessarily improve classification; center cropping is an efficient option for lightweight apple inspection systems, pending confirmation through repeated runs.

Copyrights © 2025






Journal Info

Abbrev

ijoms

Publisher

Subject

Humanities Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Public Health Social Sciences

Description

Indonesian Journal of Multidisciplinary Science (IJOMS) is a scientific journal in the form of research and can be accessed openly. This journal has e-ISSN 2808-6724 and p-ISSN 2808-5957. This journal is published monthly by International Journal Labs. The development of the company made the ...