Toward Integrated Scene Text Reading

Abstract

The growth in digital camera usage combined with a worldly abundance of text has translated to a rich new era for a classic problem of pattern recognition, reading. While traditional document processing often faces challenges such as unusual fonts, noise, and unconstrained lexicons, scene text reading amplifies these challenges and introduces new ones such as motion blur, curved layouts, perspective projection, and occlusion among others. Reading scene text is a complex problem involving many details that must be handled effectively for robust, accurate results. In this work, we describe and evaluate a reading system that combines several pieces, using probabilistic methods for coarsely binarizing a given text region, identifying baselines, and jointly performing word and character segmentation during the recognition process. By using scene context to recognize several words together in a line of text, our system gives state-of-the-art performance on three difficult benchmark data sets.

Toponym Recognition in Historical Maps by Gazetteer Alignment

“…Each annotated word image is normalized to a linear baseline by a thin plate spline. The normalized word image is given to a word recognition system [13], which produces a list of word hypotheses-lexical and non-lexicalwith their associated probabilities. We use both a standard American English lexicon of 82,000 words and a map-specific lexicon generated from the appropriate gazetteer.…”

Scene Text Recognition and Retrieval for Large Lexicons

“…There are two popular methods for character extraction based on: (i) sliding window [4,7], (ii) binarization [1,2]. We follow the binarization based approach as it results in fewer potential character locations, in the form of connected components (CCs), than those generated by the sliding window based method.…”

“…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.…”

“…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. Fig.…”

Scene text detection and recognition: recent advances and future trends

“…To tackle these challenges, a rich body of approaches have been proposed and substantial progresses have been achieved in recent years [8][9][10][11][12][13][14][15][16][17][18][19][20]. In almost all these methods, the study on representation is the main research subject, since representation is the key to the effectiveness and robustness of these algorithms.…”