There is very little notable research on generating descriptions of the\nBengali language. About 243 million people speak in Bengali, and it is the 7th\nmost spoken language on the planet. The purpose of this research is to propose\na CNN and Bidirectional GRU based architecture model that generates natural\nlanguage captions in the Bengali language from an image. Bengali people can use\nthis research to break the language barrier and better understand each other's\nperspectives. It will also help many blind people with their everyday lives.\nThis paper used an encoder-decoder approach to generate captions. We used a\npre-trained Deep convolutional neural network (DCNN) called InceptonV3image\nembedding model as the encoder for analysis, classification, and annotation of\nthe dataset's images Bidirectional Gated Recurrent unit (BGRU) layer as the\ndecoder to generate captions. Argmax and Beam search is used to produce the\nhighest possible quality of the captions. A new dataset called BNATURE is used,\nwhich comprises 8000 images with five captions per image. It is used for\ntraining and testing the proposed model. We obtained BLEU-1, BLEU-2, BLEU-3,\nBLEU-4 and Meteor is 42.6, 27.95, 23, 66, 16.41, 28.7 respectively.\n