2013 12th International Conference on Document Analysis and Recognition 2013
DOI: 10.1109/icdar.2013.87
|View full text |Cite
|
Sign up to set email alerts
|

Whole is Greater than Sum of Parts: Recognizing Scene Text Words

Abstract: Abstract-Recognizing text in images taken in the wild is a challenging problem that has received great attention in recent years. Previous methods addressed this problem by first detecting individual characters, and then forming them into words. Such approaches often suffer from weak character detections, due to large intra-class variations, even more so than characters from scanned documents. We take a different view of the problem and present a holistic word recognition framework. In this, we first represent… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
44
0
1

Year Published

2013
2013
2022
2022

Publication Types

Select...
6
2
1

Relationship

1
8

Authors

Journals

citations
Cited by 85 publications
(45 citation statements)
references
References 13 publications
0
44
0
1
Order By: Relevance
“…This benchmark measures wordspotting, a simplified OCR problem in which each image is annotated with a lexicon of about 50 words, of which one is Algorithm Word Recognition Rate (%) PhotoOCR 90.39 Goel et al [9] 77.28 Mishra et al [15] 73.26 Novikova et al [20] 72.9 Wang et al [26] 70.0 Baseline (ABBYY) [9] 35.0 Table 2: Cropped word recognition accuracy on the Street View Text dataset (with lexicon) [25].…”
Section: Resultsmentioning
confidence: 99%
“…This benchmark measures wordspotting, a simplified OCR problem in which each image is annotated with a lexicon of about 50 words, of which one is Algorithm Word Recognition Rate (%) PhotoOCR 90.39 Goel et al [9] 77.28 Mishra et al [15] 73.26 Novikova et al [20] 72.9 Wang et al [26] 70.0 Baseline (ABBYY) [9] 35.0 Table 2: Cropped word recognition accuracy on the Street View Text dataset (with lexicon) [25].…”
Section: Resultsmentioning
confidence: 99%
“…Character based methods first recognize single characters, then form words [32], [33], [40]. Recent work [1], [14], [18] shows that entire-word recognition performs better than recognizing characters first and then forming words. In this work, we follow the state-of-the-art word recognition approach [18] to encode the textual cues.…”
Section: Related Workmentioning
confidence: 99%
“…In light of this, many attempts have been made to recognize scene text [1][2][3][4][5][6]. Scene text recognition is a challenging problem and its recent success is mostly limited to the small lexicon setting, where an image-specific lexicon containing the ground truth word is provided.…”
Section: Introductionmentioning
confidence: 99%
“…The problem of cropped word recognition has been looked at in two broad settings: with an image-specific lexicon [3][4][5][6]10] and without the help of lexicon [1,7,8]. Approaches for scene text recognition typically follow a two-step process (i) A set of potential character locations are detected either by binarization [1,2] or sliding windows [3,4], (ii) Inference on crf model [4,7], semi Markov model [1,8], finite automata [9] or beam search [2] in a graph (representing the character locations and their neighborhood relations) is performed.…”
Section: Introductionmentioning
confidence: 99%