Wild edible plants play a significant role in the socio-economic conditions of various communities by enhancing food security, providing economic benefits and supporting sustainable livelihoods. Proper identification of these plants is crucial in preserving cultural heritage and promoting environmental conservation. With the popularity of AI, automatic plant identification has gained much attention in the last decade. Machine learning, especially, deep learning has proven its efficiency in identifying these plants successfully. However, due to the requirement of massive amounts of data, transfer learning is often preferred over traditional deep learning algorithms. Our study demonstrates the use of transfer learning for the identification of wild edible vegetables in Bodoland Territorial Region (BTR). BTR, an autonomous region in Assam, Northeast India is extremely rich in plant resources. Pre-trained models Xception, VGG16 and Resnet50 are fine-tuned as well as used as feature extractors to develop 12 classification models. A new dataset is created comprising of 21 species of wild edible vegetables of BTR and is used for training our models. An in-depth analysis is done to investigate the performance of these models on the above classification task. By developing an automatic plant identification system, this study aims to shed light on the available plant resources of BTR and contribute to the enhancement of the quality of life of its rural communities.