In this article, a system Smart Emergency Notification System (SENS) is proposed for both emergency responders and the community. SENS detects single/multiple emergency case(s) (i.e. road accident, fire, and injury) automatically from images sent by a smartphone via the Internet by the proposed promising approach; afterward, it notifies the police, fire brigade, and/or ambulance. The SENS has three modules: the mobile application SENSdroid, the Web application WebSENS, and the software agent NotiSENS, which uses the proposed approach. This approach is as follows. First, a dataset that contains accident, fire, and injury images was constructed; their labels were obtained for training; the trained results, Google Cloud Vision API, and cosine similarity measurement were used to detect the emergency case(s) for an input image. Based on the test results, the approach has 84% sensitivity, 92% specificity, and 88% accuracy. It is possible to say that SENS would have a positive effect on helping the harmed person, supporting the staff on duty, protecting the person who can be harmed, and/or saving Nature. Additionally, this system would have high usability because of its easy-to-use features and high rates of smartphone and Internet users. It is believed that SENS could be an efficient and useful system.