Haiti earthquake photo tagging: Lessons on crowdsourcing in-depth image classifications

Facilitated by the latest advances of information technologies, online human computing resources provide researchers unprecedented opportunities to resolve a class of real-world problems that are challenging even to the computer algorithms, and yet manageable to human intelligence if working units are well organized. A problem in this category is image labeling, recognizing and categorizing targets in the images. In this paper, we describe an online platform that leverages human computation resources to resolve an image labeling task - classifying damage patterns in post-disaster photos. The underlying information valuable to us is not only the existence of damage in the image, but also its patterns and severity. We hope this study can provide new perspectives to enhance the design of crowdsourcing projects in future.