Word spotting for historical documents
Citations
1,054 citations
Cites background or methods from "Word spotting for historical docume..."
...This is word detection – in an ideal scenario we would be able to generate word bounding boxes with high recall and high precision, achieving this by extracting the maximum amount of information from each bounding box candidate possible....
[...]
...Our process loosely follows the detection/recognition separation – a word detection stage followed by a word recognition stage....
[...]
681 citations
Cites background from "Word spotting for historical docume..."
...Authors have subsequently focused solely on text detection [7, 11, 16, 50, 51], or text recognition [31, 36, 41], or on combining both in end-to-end systems [40, 39, 49, 32–34, 45, 35, 6, 8, 48]....
[...]
522 citations
Cites background from "Word spotting for historical docume..."
...TEXT understanding in images is an important problemthat has drawn a lot of attention from the computer vision community since its beginnings....
[...]
...The final PHOC histogram is the concatenation of these partial histograms....
[...]
293 citations
Cites background or methods from "Word spotting for historical docume..."
...DTW-based keyword spotting was proposed in [28] for speech recognition and is also well-established in the field of handwritten word spotting [15, 16, 17, 18]....
[...]
...For more details on the DTW distance algorithm, we refer to [15]....
[...]
...The proposed system is compared with a well-established template matching method based on Dynamic Time Warping (DTW) [15]....
[...]
...The DTW distance DTW(X, Y) of the word images X and Y is then given by the minimum alignment cost that is found by means of dynamic programming [15]....
[...]
..., based on word profiles [15], closed contours [16], and local gradients [17, 18]....
[...]
283 citations
Cites background or methods from "Word spotting for historical docume..."
...Our DTW implementation, similarly to the one described in [4], makes use of a Sakoe-Chiba band [50] to speed up the computation....
[...]
...Comparing such sequences using dynamic time warping (DTW) is one of the most commonly used word spotting methods [21], [22] and is still widely used [4]....
[...]
...Certain efforts have already been put into word spotting for historical data [4], [5]....
[...]
References
27,271 citations
"Word spotting for historical docume..." refers methods in this paper
...The fitting was performed with the “Nelder-Mead” optimization procedure [20], which minimizes the sum of squared differences between the actual vocabulary sizes and the ones 26...
[...]
19,261 citations
10,549 citations
9,923 citations
6,693 citations