earticle

영어

Visual object recognition has been growing quickly in the field of computer science, as it can be applied to such diverse areas as robotics, smartphones, and artificial intelligence. Although there have been a countless number of researches and methods to develop an effective visual object recognition software, there have been only few attempts to combine visual object recognition with data science. Data science analyzes large volumes of data in different forms and derives useful information from the results. In the experiment, this study developed a specific method to generate sentences that describe what’s happening in a picture by combining visual object recognition software with text mining technologies. This study utilizes CamFind to identify a number of objects in a picture and applies NodeXL from Microsoft Excel to obtain online data from Twitter, a social network service. Information from the analysis of texts induced from objects is used to make stories for the whole image.