Deep Learning Approach for Classification and Efficacy Testing of Chhattisgarh Herbal Ingredients in Skincare

This study presents a deep learning–based framework for medicinal plant classification and skin disease detection, aimed at bridging the gap between traditional herbal knowledge and modern artificial intelligence techniques. The proposed system utilizes Convolutional Neural Networks (CNN) along with image processing techniques to accurately identify medicinal plants and skin conditions from input images. By leveraging models such as CNN-based architectures and lightweight deep learning frameworks, the system achieves a balance between classification accuracy and computational efficiency. The integration of medicinal plant recognition with skin disease analysis provides a comprehensive approach for supporting skincare-related decision-making. In addition, the incorporation of region-specific herbal knowledge, particularly medicinal plants from Chhattisgarh, enhances the relevance and applicability of the system in local healthcare contexts. The use of preprocessing techniques such as resizing, normalization, and data augmentation further improves model performance and generalization. Overall, the proposed framework demonstrates the potential of deep learning in advancing automated healthcare solutions. It not only supports accurate classification but also contributes to the preservation and utilization of indigenous medicinal knowledge. This work can serve as a foundation for future research in AI-driven ethnomedicinal applications, real-time healthcare systems, and intelligent decision-support tools for herbal skincare

[1].   J. Deng et al., “ImageNet: A large-scale hierarchical image database,” in Proc. CVPR, 2009. [2].  A. Krizhevsky, I. Sutskever, and G. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc.  NeurIPS, 2012. [3]. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015. [4].  O. Russakovsky et al., “ImageNet large scale visual recognition challenge,” International Journal of Computer Vision, vol. 115, pp. 211–252, 2015. [5].  K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Proc. ICLR, 2015. [6]. S. Mohanty et al., “Using deep learning for image-based plant disease detection,” Frontiers in Plant Science, 2016. [7].  J. Redmon et al., “You only look once: Unified, real-time object detection,” in Proc. CVPR, 2016. [8].  K. He et al., “Deep residual learning for image recognition,” in Proc. CVPR, 2016. [9].  S. Han et al., “Deep compression: Compressing deep neural networks,” in Proc. ICLR, 2016. [10].  G. Huang et al., “Densely connected convolutional networks,” in Proc. CVPR, 2017.