ICDAR 2003 robust reading competitions

This paper describes the robust reading competitions forICDAR 2003. With the rapid growth in research over thelast few years on recognizing text in natural scenes, thereis an urgent need to establish some common benchmarkdatasets, and gain a clear understanding of the current stateof the art. We use the term robust reading to refer to text imagesthat are beyond the capabilities of current commercialOCR packages. We chose to break down the robust readingproblem into three sub-problems, and run competitionsfor each stage, and also a competition for the best overallsystem. The sub-problems we chose were text locating,character recognition and word recognition.By breaking down the problem in this way, we hope togain a better understanding of the state of the art in eachof the sub-problems. Furthermore, our methodology involvesstoring detailed results of applying each algorithm toeach image in the data sets, allowing researchers to study indepth the strengths and weaknesses of each algorithm. Thetext locating contest was the only one to have any entries.We report the results of this contest, and show cases wherethe leading algorithms succeed and fail.