Content-based image retrievalImage retrieval is useful only if it can save the earth . In other words, it must satisfy the human end-users. Hence, we first focus on developing a groundtruth data . This ground truth data could also help the computer vision community in the task of general object recognition . After having collected ground-truth data, we develop statistical methods to calibrate systems and vision algorithms used in image retrieval applications.
The data was collected using an on-line evaluation strategy. The on-line interface was developed and is being maintained by Nikhil Shirahatti (nvs@CS.arizona.edu) The data is due to the collective effort of 32 students and we are thankful for their help. paper.
The inputs to Retrieval Analyzer are a vector of computer scores (your image retrieval scores for the image pairs we have provided in our ground truth data) and corresponding human scores (our ground truth data). The outputs consist of a correlation score and an estimated precision-recall curve. We provide an option for chosing from any of the three mapping methods, but we recommend using the method that maximizes the correlation score.