Reconnaissance optique de caractères

vignette|Vidéo montrant un processus de reconnaissance optique de caractères effectué en direct grâce à un scanner portable. La reconnaissance optique de caractères (ROC, ou OCR pour l'anglais optical character recognition), ou océrisation, désigne les procédés informatiques pour la traduction d'images de textes imprimés ou dactylographiés en fichiers de texte. Un ordinateur réclame pour l'exécution de cette tâche un logiciel d'OCR. Celui-ci permet de récupérer le texte dans l'image d'un texte imprimé et de le sauvegarder dans un fichier pouvant être exploité dans un traitement de texte pour enrichissement, et stocké dans une base de données ou sur un autre support exploitable par un système informatique. Histoire La première machine d'OCR fut créée par Gustav Tauschek, un ingénieur allemand, en 1929. Elle contenait un détecteur photosensible qui pointait une lumière sur un mot lorsqu’il correspondait à un gabarit contenu dans sa mémoire. En 1950, Frank Rowlett, qui avait

ASYMMETRIC FILTER FOR TEXT RECOGNITION IN VIDEO

Datong Chen

Stripes are a common sub-structure of text characters, and the scale of the stripes does not vary significantly within a character. In this paper a new form of filter is derived from the Gabor filter which can efficiently estimate the scales of such stripes. The contrast of text in video can then be increased by enhancing the edges of those stripes found to have a suitable scale. The algorithm presented enhances the stripes in three selected scale ranges. Character recognition is then performed on the output of binarizing these enhanced images, and shows improvement over other methods.

IDIAP2000

Text detection and recognition in images and video sequences

Datong Chen

Text characters embedded in images and video sequences represents a rich source of information for content-based indexing and retrieval applications. However, these text characters are difficult to be detected and recognized due to their various sizes, grayscale values and complex backgrounds. This thesis investigates methods for building an efficient application system for detecting and recognizing text of any grayscale values embedded in images and video sequences. Both empirical image processing methods and statistical machine learning and modeling approaches are studied in two sub-problems: text detection and text recognition. Applying machine learning methods for text detection encounters difficulties due to character size, grayscale variations and heavy computation cost. To overcome these problems, we propose a two-step localization/verification approach. The first step aims at quickly localizing candidate text lines, enabling the normalization of characters into a unique size. In the verification step, a trained support vector machine or multi-layer perceptrons is applied on background independent features to remove the false alarms. Text recognition, even from the detected text lines, remains a challenging problem due to the variety of fonts, colors, the presence of complex backgrounds and the short length of the text strings. Two schemes are investigated addressing the text recognition problem: bi-modal enhancement scheme and multi-modal segmentation scheme. In the bi-modal scheme, we propose a set of filters to enhance the contrast of black and white characters and produce a better binarization before recognition. For more general cases, the text recognition is addressed by a text segmentation step followed by a traditional optical character recognition (OCR) algorithm within a multi-hypotheses framework. In the segmentation step, we model the distribution of grayscale values of pixels using a Gaussian mixture model or a Markov Random Field. The resulting multiple segmentation hypotheses are post-processed by a connected component analysis and a grayscale consistency constraint algorithm. Finally, they are processed by an OCR software. A selection algorithm based on language modeling and OCR statistics chooses the text result from all the produced text strings. Additionally, methods for using temporal information of video text are investigated. A Monte Carlo video text segmentation method is proposed for adapting the segmentation parameters along temporal text frames. Furthermore, a ROVER (Recognizer Output Voting Error Reduction) algorithm is studied for improving the final recognition text string by voting the characters through temporal frames.

École Polytechnique Fédérale de Lausanne2003

Text detection and recognition in images and video sequences

Datong Chen

2003

Text detection and recognition in images and video sequences

Datong Chen

École Polytechnique Fédérale de Lausanne2003

Text detection and recognition in images and video sequences

Datong Chen

2003