Visual Saliency Models for Text Detection in Real World

Abstract

This paper evaluates the degree of saliency of texts in natural scenes using visual saliency models. A large scale scene image database with pixel level ground truth is created for this purpose. Using this scene image database and five state-of-the-art models, visual saliency maps that represent the degree of saliency of the objects are calculated. The receiver operating characteristic curve is employed in order to evaluate the saliency of scene texts, which is calculated by visual saliency models. A visualization of the distribution of scene texts and non-texts in the space constructed by three kinds of saliency maps, which are calculated using Itti's visual saliency model with intensity, color and orientation features, is given. This visualization of distribution indicates that text characters are more salient than their non-text neighbors, and can be captured from the background. Therefore, scene texts can be extracted from the scene images. With this in mind, a new visual saliency architecture, named hierarchical visual saliency model, is proposed. Hierarchical visual saliency model is based on Itti's model and consists of two stages. In the first stage, Itti's model is used to calculate the saliency map, and Otsu's global thresholding algorithm is applied to extract the salient region that we are interested in. In the second stage, Itti's model is applied to the salient region to calculate the final saliency map. An experimental evaluation demonstrates that the proposed model outperforms Itti's model in terms of captured scene texts.

Characteristics of Visual Saliency Caused by Character Feature for Reconstruction of Saliency Map Model

“…The visual saliency map is used as an image segmentation, which indicates the classification between the foreground and background [ 21 ]. In addition, a saliency map is also adopted as text detection in natural scenes [ 22 ].…”

High Efficiency Video Coding Compliant Perceptual Video Coding Using Entropy Based Visual Saliency Model

“…Computer scientists have developed numerous computational visual saliency algorithms, which aim at detecting the salient regions in an image. Computational visual saliency models find their applications in a broad spectrum of domains including remote sensing [24], watermarking [25], privacy [26], text detection [27], object recognition [28], multi-camera calibration [29], binocular vision [30], and video coding [31]. Generally, saliency detection techniques are categorized into bottom-up and top-down approaches.…”

A Predictive Processing Account of Bottom-Up Visual Saliency Using Cross-Predicting Autoencoders

“…The channels are then averaged to create a salience map. Significant work has gone into developing this model, by adding channels such as a face channel (Cerf et al, 2008), and a text channel (Gao et al, 2014), or by learning the channel-combination function by least squares instead of a simple average (Zhao & Koch, 2013). Other models include those based on spectral analysis (Hou et al, 2012;Schauerte & Stiefelhagen, 2012;Hou & Zhang, 2007), information theory (Klein & Frintrop, 2011, 2012Bruce & Tsotsos, 2009) and Bayesian reasoning (Gao et al, 2009;Gao & Vasconcelos, 2007).…”