User reactions as access mechanism: an exploration based on captions for images
Journal of the American Society for Information Science
Image retrieval: Ideas, influences, and trends of the new age
ACM Computing Surveys (CSUR)
| Hi-index | 0.00 |
This preliminary study, as a part of a broader study about the medical image use by experts and novices, examines the differences in image describing behavior between these two categories of users. Eye tracking technique was used to capture the image users' eye movement on the Area of Interests (AOIs). This study found that a domain expert was capable of employing nine levels of image attributes in the descriptions, while a novice was able to use only six levels. Furthermore, the expert showed stronger capability in expressing the image information needs by generating more image attributes in the descriptions than the novice, especially in terms of employing significantly more high-level (semantic levels) image attributes. We also found that the novice attended to more AOIs on every image than the expert.