How Salient is Scene Text?

Shahab, Asif; Dengel, Andreas; Uchida, Seiichi

doi:10.1109/das.2012.42

Cited by 21 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning the unequal importance, we propose a weighting scheme based on visual saliency which is a value to measure visual attention that people give to particular areas of an image. There are many methods developed to estimate visual saliency [18] [19]. In this work, we apply Graph-Based Visual Saliency (GBVS) in [18] to find weight of the visual attention.…”

Section: A Feature Extractionmentioning

confidence: 99%

Saliency-weighted holistic scene text recognition for unseen place categorization

Thammasorn

Patanukhom

Pimup

2014

2014 11th International Joint Conference on Computer Science and Software Engineering (JCSSE)

View full text Add to dashboard Cite

an improvement in framework for unseen place categorization using scene text is proposed. Category score calculation using visual saliency weighting method is proposed to cope with problem of different importance of word locations on scene images. Additionally, a HOG feature extraction using sliding window is proposed to obtain better holistic word recognition on scene images. As the result, the proposed method outperforms PHOG baseline in unseen place categorization with greater than 10 % improvement in the accuracy.

show abstract

Section: A Feature Extractionmentioning

confidence: 99%

Saliency-weighted holistic scene text recognition for unseen place categorization

Thammasorn

Patanukhom

Pimup

2014

2014 11th International Joint Conference on Computer Science and Software Engineering (JCSSE)

View full text Add to dashboard Cite

show abstract

“…However, to be more realistic and compliant with the theoretical model, differently from [20], object likelihood is computed by using the output of Torralba's saliency [104] localised in the bounding box as given by the text region ground-truth. The motivation for this choice is that Torralba's saliency well correlates with text appearance [90] and it can be used as a rough but reliable estimate of its likelihood P (F|O = text). Further, the main reason for using a simulated text likelihood estimator (instead of a real one such as in [26]) is that one can exploit ad-hoc control of the number of true positive / false positive regions.…”

Section: Simulation: Gaze Shift Samplingmentioning

confidence: 99%

Modelling Task-Dependent Eye Guidance to Objects in Pictures

et al. 2014

View full text Add to dashboard Cite

We introduce a model of attentional eye guidance based on the rationale that the deployment of gaze is to be considered in the context of a general actionperception loop relying on two strictly intertwined processes: sensory processing, depending on current gaze position, identifies sources of information that are most valuable under the given task; motor processing links such information with the oculomotor act by sampling the next gaze position and thus performing the gaze shift. In such a framework, the choice of where to look next is task-dependent and oriented to classes of objects embedded within pictures of complex scenes. The dependence on task is taken into account by exploiting the value and the payoff of gazing at certain image patches or proto-objects that provide a sparse representation of the scene objects. The different levels of the actionperception loop are represented in probabilistic form and eventually give rise to a stochastic process that generates the gaze sequence. This way the model also accounts for statistical properties of gaze shifts such as individual scan path variability. Results of the simulations are compared either with experimental data

show abstract

“…Uchida et al [28] showed that using both SURF and saliency features achieved superior character recognition performance over using SURF features alone. More recently, Shahab et al [26] compared the performance of four different saliency detection models at scene text detection. Meng and Song [27] also adopted the saliency framework of [11] for scene text detection.…”

Section: Introductionmentioning

confidence: 99%

Characterness: An Indicator of Text in the Wild

Jia

Shen

et al. 2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Text in an image provides vital information for interpreting its contents, and text in a scene can aid a variety of tasks from navigation to obstacle avoidance and odometry. Despite its value, however, detecting general text in images remains a challenging research problem. Motivated by the need to consider the widely varying forms of natural text, we propose a bottom-up approach to the problem, which reflects the characterness of an image region. In this sense, our approach mirrors the move from saliency detection methods to measures of objectness. In order to measure the characterness, we develop three novel cues that are tailored for character detection and a Bayesian method for their integration. Because text is made up of sets of characters, we then design a Markov random field model so as to exploit the inherent dependencies between characters. We experimentally demonstrate the effectiveness of our characterness cues as well as the advantage of Bayesian multicue integration. The proposed text detector outperforms state-of-the-art methods on a few benchmark scene text detection data sets. We also show that our measurement of characterness is superior than state-of-the-art saliency detection models when applied to the same task.

show abstract

How Salient is Scene Text?

Cited by 21 publications

References 13 publications

Saliency-weighted holistic scene text recognition for unseen place categorization

Saliency-weighted holistic scene text recognition for unseen place categorization

Modelling Task-Dependent Eye Guidance to Objects in Pictures

Characterness: An Indicator of Text in the Wild

Contact Info

Product

Resources

About