EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Comprehensive Review of Artificial Intelligence Techniques for Black Pepper and Spice Identification Using Computer Vision and Deep Learning

Deep Kamle, Dr. Satyendra Sharma, Dr. Hemang Shrivastava

Interdisciplinary Journal of AI, Machine Learning & Data Science · 2026

DOI: 10.66261/805c6c91 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Interdisciplinary Journal of AI, Machine Learning & Data Science, 2026. Verfasst von Deep Kamle und 2 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The identification and classification of spices, particularly black pepper represent a significant challenge in food quality assurance supply chain management and adulteration detection. Conventional analytical methods, including chromatography and spectroscopy although precise are time-consuming expensive, and require expert knowledge limiting their applicability in field and industrial settings. Recent advancements in artificial Intelligence (AI), Computer Vision, and deep learning have opened transformative avenues for automated, non-destructive, and real-time spice identification systems. This comprehensive review critically examines the evolution and current state of AI-based techniques for black pepper and spice identification, encompassing traditional machine learning methods, convolutional neural network (CNN) architectures, and advanced deep learning models including ResNet, EfficientNet, Vision Transformers (ViT), and hybrid architectures. The review systematically covers image preprocessing pipelines, feature extraction strategies, publicly available benchmark datasets, and evaluation methodologies used in the field. A comparative analysis of recent studies highlights the superiority of transformer-based models over classical CNNs in multi-class spice recognition tasks, while lightweight architectures such as MobileNet and SqueezeNet demonstrate viability for edge deployment in resource-constrained environments. This paper identifies critical research gaps, including the scarcity of large-scale annotated spice datasets, model interpretability limitations, and the need for standardized evaluation benchmarks. This review concludes by delineating future research directions, including federated learning, explainable AI (XAI), and multi-model fusion frameworks, to advance the field toward robust, deployable, and industry-ready spice identification solutions.

Zitieren

APA

Kamle, D., Sharma, D. S., & Shrivastava, D. H. (2026). A Comprehensive Review of Artificial Intelligence Techniques for Black Pepper and Spice Identification Using Computer Vision and Deep Learning. Interdisciplinary Journal of AI, Machine Learning & Data Science. https://doi.org/10.66261/805c6c91

Vancouver

Kamle D, Sharma DS, Shrivastava DH. A Comprehensive Review of Artificial Intelligence Techniques for Black Pepper and Spice Identification Using Computer Vision and Deep Learning. Interdisciplinary Journal of AI, Machine Learning & Data Science. 2026. doi:10.66261/805c6c91

BibTeX
@article{Kamle2026,
  author = {Kamle, Deep and Sharma, Dr. Satyendra and Shrivastava, Dr. Hemang},
  title = {A Comprehensive Review of Artificial Intelligence Techniques for Black Pepper and Spice Identification Using Computer Vision and Deep Learning},
  journal = {Interdisciplinary Journal of AI, Machine Learning & Data Science},
  year = {2026},
  doi = {10.66261/805c6c91}
}
Kostenlos starten →