26:
189:
Lucas, Simon M.; Panaretos, Alex; Sosa, Luis; Tang, Anthony; Wong, Shirley; Young, Robert; Ashida, Kazuki; Nagai, Hiroki; Okamoto, Masayuki; Yamamoto, Hiroaki; Miyao, Hidetoshi; Zhu, Junmin; Ou, Wuwen; Wolf, Christian; Jolion, Jean-Michel; Todoran, Leon; Worring, Marcel; Lin, Xiaofan (2005). "S. M.
102:
In word recognition, the text is assumed to be already detected and located and the rectangular bounding box containing the text is available. The word present in the bounding box needs to be recognized. The methods available to perform word recognition can be broadly classified into top-down and
106:
In the top-down approaches, a set of words from a dictionary is used to identify which word suits the given image. Images are not segmented in most of these methods. Hence, the top-down approach is sometimes referred as segmentation free recognition.
41:
which became important after smart phones with good cameras became ubiquitous. The text in scene images varies in shape, font, colour and position. The recognition of scene text is further complicated sometimes by non-uniform illumination and focus.
49:(ICDAR) conducts a robust reading competition once in two years. The competition was held in 2003, 2005 and during every ICDAR conference. International association for pattern recognition (IAPR) has created a list of datasets as Reading systems.
88:(DWT) are used to extract the high frequency coefficients. It is assumed that the text present in an image has high frequency components and selecting only the high frequency coefficients filters the text from the non-text regions in an image.
57:
Text detection is the process of detecting the text present in the image, followed by surrounding it with a rectangular bounding box. Text detection can be carried out using image based techniques or frequency based techniques.
467:
Kumar, Deepak; Anil Prasad, M. N.; Ramakrishnan, A. G. (2013). "NESP: Nonlinear enhancement and selection of plane for optimal segmentation and recognition of scene word images". In
Zanibbi, Richard; Coüasnon, Bertrand (eds.).
65:
into multiple segments. Each segment is a connected component of pixels with similar characteristics. The statistical features of connected components are utilised to group them and form the text.
46:
288:"J. J. Weinmann, E. Learned-Miller, and A. R. Hanson. Scene text recognition using similarity and a lexicon with sparse belief propagation. IEEE Trans. PAMI, 31(10):1733–1746, 2009"
110:
In the bottom-up approaches, the image is segmented into multiple components and the segmented image is passed through a recognition engine. Either an off the shelf
352:
Novikova, Tatiana; Barinova, Olga; Kohli, Pushmeet; Lempitsky, Victor (2012). "Large-Lexicon
Attribute-Consistent Text Recognition in Natural Images".
412:
379:
152:
397:
D. Kumar and A. G. Ramakrishnan. Power-law transformation for enhanced recognition of born-digital word images. In Proc. 9th SPCOM, 2012
395:
Kumar, Deepak; Ramakrishnan, A. G. (2012). "Power-law transformation for enhanced recognition of born-digital word images".
336:"A. Mishra, K. Alahari, and C. V. Jawahar. Scene Text Recognition using Higher Order Language Priors. In Proc. BMVC, 2012"
111:
74:
190:
Lucas. ICDAR 2003 Robust
Reading Competitions: Entries, Results, and Future Directions. IJDAR, 7(2):105–122, June 2005".
97:
176:
85:
81:
546:
541:
436:
D. Kumar; M. N. Anil Prasad; A. G. Ramakrishnan. "MAPS: Midline analysis and propagation of segmentation".
357:
199:
70:
362:
204:
481:
449:
418:
217:
158:
62:
29:
The image displays the coach category in text format. We can observe that the coach belongs to
408:
375:
335:
317:
273:
148:
473:
441:
400:
367:
307:
299:
209:
140:
66:
38:
312:
287:
535:
137:
S. M. Lucas. Text
Locating Competition Results. In Proc. 8th ICDAR, pages 80–85, 2005
485:
453:
422:
221:
177:
http://www.iapr-tc11.org/mediawiki/index.php/ICDAR_2005_Robust_Reading_Competitions
162:
30:
371:
22:
is text that appears in an image captured by a camera in an outdoor environment.
404:
260:
213:
25:
132:
445:
37:
The detection and recognition of scene text from camera captured images are
523:
321:
144:
303:
477:
356:. Lecture Notes in Computer Science. Vol. 7577. pp. 752–765.
114:(OCR) engine or a custom-trained one is used to recognise the text.
24:
292:
IEEE Transactions on
Pattern Analysis and Machine Intelligence
248:
47:
International
Conference on Document Analysis and Recognition
16:
Text captured as part of outdoor surroundings in a photograph
77:
are used to classify the components into text and non-text.
274:
http://www.iapr-tc11.org/mediawiki/index.php?title=Datasets
235:
192:
International
Journal of Document Analysis and Recognition
511:
499:
286:
Weinman, J.J.; Learned-Miller, E.; Hanson, A.R. (2009).
133:"ICDAR 2005 text locating competition results"
8:
261:http://www.cvc.uab.es/icdar2011competition/
361:
311:
272:IAPR TC11 Reading Systems-Datasets List.
203:
524:http://code.google.com/p/tesseract-ocr/
259:ICDAR 2011 Robust Reading Competition.
123:
61:In image based techniques, an image is
45:To improve scene text recognition, the
470:Document Recognition and Retrieval XX
7:
472:. Vol. 8658. p. 865806.
14:
80:In frequency based techniques,
1:
112:Optical character recognition
75:convolutional neural networks
372:10.1007/978-3-642-33783-3_54
98:intelligent word recognition
354:Computer Vision – ECCV 2012
249:http://u-pat.org/ICDAR2017/
563:
405:10.1109/SPCOM.2012.6290009
95:
86:discrete wavelet transform
82:discrete Fourier transform
510:Nuance Omnipage Reader.
214:10.1007/s10032-004-0134-3
175:ICDAR 2005 Competitions.
139:. pp. 80–84 Vol. 1.
236:http://www.icdar2013.org
446:10.1145/2425333.2425348
522:Tesseract OCR Engine.
512:http://www.nuance.com/
438:Proc. 8th ICVGIP, 2012
145:10.1109/ICDAR.2005.231
103:bottom-up approaches.
71:support vector machine
34:
500:http://www.abbyy.com/
304:10.1109/TPAMI.2009.38
39:computer vision tasks
28:
131:Lucas, S.M. (2005).
498:Abbyy Fine Reader.
69:approaches such as
478:10.1117/12.2008519
35:
414:978-1-4673-2014-6
381:978-3-642-33782-6
298:(10): 1733–1746.
154:978-0-7695-2420-7
554:
547:Image processing
526:
520:
514:
508:
502:
496:
490:
489:
464:
458:
457:
433:
427:
426:
399:. pp. 1–5.
392:
386:
385:
365:
349:
343:
342:
340:
332:
326:
325:
315:
283:
277:
270:
264:
257:
251:
245:
239:
232:
226:
225:
207:
198:(2–3): 105–122.
186:
180:
173:
167:
166:
128:
92:Word recognition
67:Machine learning
562:
561:
557:
556:
555:
553:
552:
551:
542:Computer vision
532:
531:
530:
529:
521:
517:
509:
505:
497:
493:
466:
465:
461:
435:
434:
430:
415:
394:
393:
389:
382:
363:10.1.1.296.4807
351:
350:
346:
338:
334:
333:
329:
285:
284:
280:
271:
267:
258:
254:
246:
242:
233:
229:
205:10.1.1.104.1667
188:
187:
183:
174:
170:
155:
130:
129:
125:
120:
100:
94:
55:
17:
12:
11:
5:
560:
558:
550:
549:
544:
534:
533:
528:
527:
515:
503:
491:
459:
428:
413:
387:
380:
344:
327:
278:
265:
252:
240:
227:
181:
168:
153:
122:
121:
119:
116:
93:
90:
54:
53:Text detection
51:
15:
13:
10:
9:
6:
4:
3:
2:
559:
548:
545:
543:
540:
539:
537:
525:
519:
516:
513:
507:
504:
501:
495:
492:
487:
483:
479:
475:
471:
463:
460:
455:
451:
447:
443:
439:
432:
429:
424:
420:
416:
410:
406:
402:
398:
391:
388:
383:
377:
373:
369:
364:
359:
355:
348:
345:
337:
331:
328:
323:
319:
314:
309:
305:
301:
297:
293:
289:
282:
279:
275:
269:
266:
262:
256:
253:
250:
244:
241:
237:
231:
228:
223:
219:
215:
211:
206:
201:
197:
193:
185:
182:
178:
172:
169:
164:
160:
156:
150:
146:
142:
138:
134:
127:
124:
117:
115:
113:
108:
104:
99:
91:
89:
87:
83:
78:
76:
72:
68:
64:
59:
52:
50:
48:
43:
40:
32:
27:
23:
21:
518:
506:
494:
469:
462:
437:
431:
396:
390:
353:
347:
330:
295:
291:
281:
268:
255:
247:ICDAR 2017.
243:
234:ICDAR 2013.
230:
195:
191:
184:
171:
136:
126:
109:
105:
101:
79:
60:
56:
44:
36:
19:
18:
536:Categories
118:References
96:See also:
20:Scene text
358:CiteSeerX
200:CiteSeerX
84:(DFT) or
63:segmented
33:category.
486:13848101
454:13303734
423:13876092
322:19696446
313:3021989
222:2250003
163:1842569
31:Sleeper
484:
452:
421:
411:
378:
360:
320:
310:
220:
202:
161:
151:
482:S2CID
450:S2CID
419:S2CID
339:(PDF)
218:S2CID
159:S2CID
409:ISBN
376:ISBN
318:PMID
149:ISBN
73:and
474:doi
442:doi
401:doi
368:doi
308:PMC
300:doi
210:doi
141:doi
538::
480:.
448:.
440:.
417:.
407:.
374:.
366:.
316:.
306:.
296:31
294:.
290:.
216:.
208:.
194:.
157:.
147:.
135:.
488:.
476::
456:.
444::
425:.
403::
384:.
370::
341:.
324:.
302::
276:.
263:.
238:.
224:.
212::
196:7
179:.
165:.
143::
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.
