EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

COLOR RECOGNITION UNDER ILLUMINATION SHIFT: A CNN STUDY WITH LOIO EVALUATION AND RELIABILITY ANALYSIS ON SADACOLORDATASET (SCD)

Paras Mangi, Sadaf Bibi, Sadia Bibi

Kashf Journal of Multidisciplinary Research · 25.04.2026 · 3 (04) · 97-115

DOI: 10.71146/kjmr898 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Kashf Journal of Multidisciplinary Research, online erschienen am 25.04.2026. Verfasst von Paras Mangi und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Color recognition looks easy on paper, yet it often breaks in practice because illumination spectra, autowhite balance, exposure, and in-camera processing shift the observed color distributions. To study this failure mode in a controlled but realistic setting, we use SadaColorDataset (SCD), a color-paper dataset with 9 classes (Black, Blue, Gray, Orange, Pink, Purple, Sky Blue, White, Yellow) captured under four illuminations (Fluorescent_Light, Indoor, Indoor_Night, Sunlight), totaling 10,843 images. We benchmark lightweight CNNs (MobileNet/ResNet family) with two input variants: RAW images and a simple SEG pipeline intended to suppress background influence. Evaluation is reported under standard RandomSplit/SEGSplit as well as a strict leave-one-illumination-out (LOIO) protocol where the test domain is an unseen lighting condition. While in-domain splits are near-saturated, LOIO exposes a clear robustness gap: performance drops substantially when illumination changes, and segmentation is not uniformly beneficial SEG improves Fluorescent LOIO but degrades Indoor and Indoor_Night LOIO, revealing an illumination-dependent tradeoff. We further analyze prediction confidence and show that calibration worsens under shift; reliability diagrams and ECE indicate frequent overconfident errors in LOIO settings. Beyond reporting accuracy, we provide a reproducible pipeline, split protocol, and error analyses that clarify which color pairs fail under specific lighting. On LOIO, we obtain 0.903/0.893 (Acc/Macro-F1) for Fluorescent with SEG, 0.947/0.912 for Indoor with RAW, and 0.888/0.879 for Indoor_Night with RAW.

Zitieren

APA

Mangi, P., Bibi, S., & Bibi, S. (2026). COLOR RECOGNITION UNDER ILLUMINATION SHIFT: A CNN STUDY WITH LOIO EVALUATION AND RELIABILITY ANALYSIS ON SADACOLORDATASET (SCD). Kashf Journal of Multidisciplinary Research, 3(04), 97-115. https://doi.org/10.71146/kjmr898

Vancouver

Mangi P, Bibi S, Bibi S. COLOR RECOGNITION UNDER ILLUMINATION SHIFT: A CNN STUDY WITH LOIO EVALUATION AND RELIABILITY ANALYSIS ON SADACOLORDATASET (SCD). Kashf Journal of Multidisciplinary Research. 2026;3(04):97-115. doi:10.71146/kjmr898

BibTeX
@article{Mangi2026,
  author = {Mangi, Paras and Bibi, Sadaf and Bibi, Sadia},
  title = {COLOR RECOGNITION UNDER ILLUMINATION SHIFT: A CNN STUDY WITH LOIO EVALUATION AND RELIABILITY ANALYSIS ON SADACOLORDATASET (SCD)},
  journal = {Kashf Journal of Multidisciplinary Research},
  year = {2026},
  volume = {3},
  number = {04},
  pages = {97--115},
  doi = {10.71146/kjmr898}
}
Kostenlos starten →