• Indranil Datta

It is imperative for researchers, botanists having inquisitive mind for flower species of given unknown flower. Petals of flowers detected through an automated process will be an exciting advantage for them. There were many studies conducted to classify flowers based on hand-crafted methodologies and recently machine learning and deep learning techniques through computers. In this work, few novel ideas are attempted to find out the petals from the flower images using machine learning methods irrespective of its colour, shape or orientation. This information is augmented as a description during flower classification by using deep learning models like ResNet50 and LSTM. The models are trained using images collected from Oxford University’s flower image database. Among many different attempts to perceive flower petal counts like k Means algorithm, region based, edge based, watershed transformation and hue based image segmentation, the last one has better accuracy in finding the correct numbers of petals. A robust convolution neural network classifier is built to classify the flowers thereafter. The predicted result includes petals count information derived by the above said method.

Petals count, flower identification, flower classification

"ATTEMPT TO FIND NUMBER OF PETALS OF FLOWER IMAGES AND CLASSIFY FLOWERS USING COMPUTER VISION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 1, page no.1019-1044, January-2021, Available :http://www.jetir.org/papers/JETIR2101131.pdf

"ATTEMPT TO FIND NUMBER OF PETALS OF FLOWER IMAGES AND CLASSIFY FLOWERS USING COMPUTER VISION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 1, page no. pp1019-1044, January-2021, Available at : http://www.jetir.org/papers/JETIR2101131.pdf