ICDAR 2003 robust reading competitions
Citations
1,531 citations
1,224 citations
Cites background from "ICDAR 2003 robust reading competiti..."
...The competition dates back to 2003[1] [2] [3], and was substantially revised in 2011 and 2013 [4] [5] [6], creating a comprehensive reference framework for robust reading pipelines evaluation [7]....
[...]
1,191 citations
1,074 citations
Cites background or methods from "ICDAR 2003 robust reading competiti..."
...We used data from the Chars74K4 dataset, introduced in [6] for cropped character classification; the ICDAR Robust Reading Competition dataset [13], discussed in Section 1; and Street View Text (SVT), a full image lexicon-driven scene text dataset introduced in [20]5....
[...]
...The ICDAR Robust Reading challenge [13] was the first public dataset collected to highlight the problem of detecting and recognizing scene text....
[...]
...We follow the evaluation guidelines outlined in [13], which are essentially the same as the evaluation guidelines of other object recognition competitions, like PASCAL VOC [8]....
[...]
1,054 citations
Cites methods from "ICDAR 2003 robust reading competiti..."
...ICDAR, pp. 1491–1496....
[...]
...ICDAR 2003 (IC03) [1], ICDAR 2011 (IC11) [52], and ICDAR 2013 (IC13) [33] are scene text recognition datasets consisting of 251, 255, and 233 full scene images respectively....
[...]
...Shahab, A., Shafait, F., Dengel, A.: ICDAR 2011 robust reading competition challenge 2: Reading text in scene images....
[...]
...Interestingly, when the overlap threshold is reduced to 0.3 (last row of Table 5), we see a small improvement across ICDAR datasets and a large +8% improvement on SVT-50....
[...]
...The clusters are formed by k-means clustering the RGB components of each image of the training datasets of [36] into three clus-...
[...]
References
815 citations
"ICDAR 2003 robust reading competiti..." refers methods in this paper
...We aimed to broadly follow the principles and procedures used to run the Fingerprint Verification 2000 (and 2002) competitions [6]....
[...]
700 citations
635 citations
"ICDAR 2003 robust reading competiti..." refers background in this paper
...In recent years there has been some significant research into these general reading systems that are able to locate and/or read text in scene images [11, 2, 3, 4, 1, 10]....
[...]
478 citations
"ICDAR 2003 robust reading competiti..." refers background in this paper
...In recent years there has been some significant research into these general reading systems that are able to locate and/or read text in scene images [11, 2, 3, 4, 1, 10]....
[...]
262 citations
"ICDAR 2003 robust reading competiti..." refers background in this paper
...In recent years there has been some significant research into these general reading systems that are able to locate and/or read text in scene images [11, 2, 3, 4, 1, 10]....
[...]