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

Goel, Vibhor; Mishra, Anand; Alahari, Karteek; Jawahar, C. V.

doi:10.1109/icdar.2013.87

Cited by 85 publications

(45 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

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%

PhotoOCR: Reading Text in Uncontrolled Conditions

Bissacco

Cummins

Netzer

et al. 2013

2013 IEEE International Conference on Computer Vision

417

284

View full text Add to dashboard Cite

We describe PhotoOCR, a system for text extraction from images. Our particular focus is reliable text extraction from smartphone imagery, with the goal of text recognition as a user input modality similar to speech recognition. Commercially available OCR performs poorly on this task. Recent progress in machine learning has substantially improved isolated character classification; we build on this progress by demonstrating a complete OCR system using these techniques. We also incorporate modern datacenter-scale distributed language modelling. Our approach is capable of recognizing text in a variety of challenging imaging conditions where traditional OCR systems fail, notably in the presence of substantial blur, low resolution, low contrast, high image noise and other distortions. It also operates with low latency; mean processing time is 600 ms per image. We evaluate our system on public benchmark datasets for text extraction and outperform all previously reported results, more than halving the error rate on multiple benchmarks. The system is currently in use in many applications at Google, and is available as a user input modality in Google Translate for Android.

show abstract

Section: Resultsmentioning

confidence: 99%

PhotoOCR: Reading Text in Uncontrolled Conditions

Bissacco

Cummins

Netzer

et al. 2013

2013 IEEE International Conference on Computer Vision

417

284

View full text Add to dashboard Cite

show abstract

“…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%

Words Matter: Scene Text for Image Classification and Retrieval

Karaoğlu

Tao

Gevers

et al. 2017

IEEE Trans. Multimedia

110

View full text Add to dashboard Cite

Abstract-Text in natural images typically adds meaning to an object or scene. In particular, text specifies which business places serve drinks (e.g. cafe, teahouse) or food (e.g. restaurant, pizzeria), and what kind of service is provided (e.g. massage, repair). The mere presence of text, its words and meaning are closely related to the semantics of the object or scene. This paper exploits textual contents in images for fine-grained business place classification and logo retrieval. There are four main contributions. First, we show that the textual cues extracted by the proposed method are effective for the two tasks. Combining the proposed textual and visual cues outperforms visual only classification and retrieval by a large margin. Second, to extract the textual cues, a generic and fully unsupervised word box proposal method is introduced. The method reaches state-of-theart word detection recall with a limited number of proposals. Third, contrary to what is widely acknowledged in text detection literature, we demonstrate that high recall in word detection is more important than high f-score at least for both tasks considered in this work. Last, this paper provides a large annotated text detection dataset with 10K images and 27601 word boxes.

show abstract

“…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%

Scene Text Recognition and Retrieval for Large Lexicons

Roy

Mishra

Alahari

et al. 2015

Computer Vision – ACCV 2014

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper we propose a framework for recognition and retrieval tasks in the context of scene text images. In contrast to many of the recent works, we focus on the case where an image-specific list of words, known as the small lexicon setting, is unavailable. We present a conditional random field model defined on potential character locations and the interactions between them. Observing that the interaction potentials computed in the large lexicon setting are less effective than in the case of a small lexicon, we propose an iterative method, which alternates between finding the most likely solution and refining the interaction potentials. We evaluate our method on public datasets and show that it improves over baseline and state-of-the-art approaches. For example, we obtain nearly 15% improvement in recognition accuracy and precision for our retrieval task over baseline methods on the IIIT-5K word dataset, with a large lexicon containing 0.5 million words.

show abstract

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

Cited by 85 publications

References 13 publications

PhotoOCR: Reading Text in Uncontrolled Conditions

PhotoOCR: Reading Text in Uncontrolled Conditions

Words Matter: Scene Text for Image Classification and Retrieval

Scene Text Recognition and Retrieval for Large Lexicons

Contact Info

Product

Resources

About