Convolutional Neural Network and Deep Learning Approach for Image Detection and Identification

Abstract There are many different varieties of clouds, each with a unique set properties. As result this variability, it is difficult to discern these sorts clouds. A database’s objects must be categorized using data categorization in order organized into multiple categories. This study made use the Cirrus Cumulus Stratus Nimbus (CCSN) dataset, which falls under low cloud category and includes photos (182 images), Cumulonimbus (242 photographs), images) (202 images). fast R-CNN detector feature extraction = Resnet50 was used create system for classifying kinds. significant amount training time saved by quicker due its lack selective search algorithm. Training loss values images had an average 0.9030 from first epoch through last one. Using Faster object detection method architecture, were added accuracy 94.12 precision 0.76. - R-advantages CNN affect architecture utilized marginally influenced algorithm choice, however superior overall where advantages held.