Rendering automatic bokeh recommendation engine for photos using deep learning algorithm

Abstract Automatic bokeh is one of the smartphone’s essential photography effects. This effect enhances quality image where subject background gets out focus by providing a soft (i.e., diverse) background. Most smartphones have single rear camera that lacking to provide which effects need be applied kind images. To do same, depend on different software generate Blur, Color-point, Zoom, Spin, Big Bokeh, Color Picker, Low-key, High-Key, and Silhouette are popular With this wide range types available, it difficult for user choose suitable their Deep Learning (DL) models MobileNetV2, InceptionV3, VGG16) used in work recommend high-quality Four thousand five hundred images collected from online resources such as Google images, Unsplash, Kaggle examine model performance. 85% accuracy has been achieved recommending using proposed exceeds many existing models.