• E. Sri Hari Priya
• S. Jhansi Rani

Fritillaria cirrhosa has powerful therapeutic characteristics that can help treat pulmonary diseases. For thousands of years, the Fritillaria cirrhosa species has been utilized in traditional Chinese medicine. Deep residual convolutional neural networks were used to directly input the unprocessed raw image, and the characteristics of the image were retrieved via convolution and pooling. We used the classifier to classify the three Fritillaria cirrhosa species. We use the Inception v3 architecture to differentiate between images of three different species of Fritillaria cirrhosa. We are training the model to recognize the species of Fritillaria cirrhosa with a dataset of 3915 photos, while the validation dataset is 480. The ultimate recognition accuracy rate for the training set was 96.5%, the validation set was 96.04%, and the test set was 91.4%. Finally, our research results indicate that deep learning, specifically the Inception v3 architecture, is effective at accurately recognizing Fritillaria cirrhosa species.

Fritillaria cirrhosa, Deep Learning, Convolutional neural networks, Inception v3.

"Classification of Images on three Fritillaria cirrhosa species using deep learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.b1-b8, June-2024, Available :http://www.jetir.org/papers/JETIR2406101.pdf

"Classification of Images on three Fritillaria cirrhosa species using deep learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. ppb1-b8, June-2024, Available at : http://www.jetir.org/papers/JETIR2406101.pdf