Date of Award
Social events, promoted in print media using posters, flyers and banners often fail to attract an audience because we frequently forget the details of the event when we pass-by the promotion on the street. Smaller venues or artists often rely on low-cost, street-level marketing campaigns in areas of high foot traffic areas to develop interest in an event. These venues or artist are often without a budget for online marketing or have a target demographic outside the typical Social Media consumer which makes attracting an audience difficult.
This project aimed to solve the problem of storing and reminding the user of upcoming events, advertised in print media, by developing a mobile app to automatically identify and event information from an image taken by the user. The project is an N-tier system comprising: a front-end using AngularJS, Ionic and Cordova; a cloud Firebase database to store the user's registration and logon credentials; Google Vision API to automatically segment and identify event information and the Google Calendar API to store and remind the user of upcoming events. The project was managed using the Agile Development methodology Scrum. The challenge of this project was in developing a solution to automatically and reliably identify event information from print media which often contains a wide variety of layouts, orientations, font types, colours and contrast variations between the information and any graphics present. In addition, the solution needed to understand the semantics of the text relating to the event name and location. The development frameworks and APIs chosen were unfamiliar to the team but were used because of their technical suitability and their ongoing and increasing popularity in the industry.
Functional testing was based on a set of over 50 test images. Testing concluded that the solution retrieves date and time information consistently, however, more work is required to successfully segment and recognise event location and title. User Experience (UX) was measured in a cross-sectional survey of 75 participants. The results were positive and are discussed here.
Chandran, Akhill; Ortiz, Ana Julia; Barbosa, Eliezer Maia; Tangara, Maura Carola; and Martini, Raquel, "The Wall: A mobile app to identify and store social events from a digital image using computer vision" (2020). ICT. 23.