scispace - formally typeset
Search or ask a question
Topic

Optical character recognition

About: Optical character recognition is a research topic. Over the lifetime, 7342 publications have been published within this topic receiving 158193 citations. The topic is also known as: OCR & optical character reader.


Papers
More filters
Proceedings ArticleDOI
01 Sep 2001
TL;DR: A system for the automatic generation of synthetic databases for the development or evaluation of Arabic word or text recognition systems (Arabic OCR) is presented and special problems caused by specific features of Arabic, such as printing from right to left, many diacritical points, variation in the height of characters, and changes in the relative position to the writing line are suggested.
Abstract: A system for the automatic generation of synthetic databases for the development or evaluation of Arabic word or text recognition systems (Arabic OCR) is presented. The proposed system works without any scanning of printed paper. Firstly Arabic text has to be typeset using a standard typesetting system. Secondly a noise-free bitmap of the document and the corresponding ground truth (GT) is automatically generated. Finally, an image distortion can be superimposed to the character or word image to simulate the expected real world noise of the intended application. All necessary modules are presented together with some examples. Special problems caused by specific features of Arabic, such as printing from right to left, many diacritical points, variation in the height of characters, and changes in the relative position to the writing line, are suggested. The synthetic data set was used to train and test a recognition system based on hidden Markov model (HMM), which was originally developed for German cursive script, for Arabic printed words. Recognition results with different synthetic data sets are presented.

37 citations

Book ChapterDOI
16 Jul 1996
TL;DR: Improvements in using subspace classifiers in recognition of handwritten digits are presented and it is indicated that these additions to the subspace classification scheme noticeably reduce the classification error.
Abstract: We present recent improvements in using subspace classifiers in recognition of handwritten digits. Both non-trainable CLAFIC and trainable ALSM methods are used with four models for initial selection of subspace dimensions and their further error-driven refinement. The results indicate that these additions to the subspace classification scheme noticeably reduce the classification error.

37 citations

Proceedings ArticleDOI
31 Aug 2005
TL;DR: A novel approach to accurately detect text in color images possibly with a complex background is presented and is robust in text detection with respect to different character size, orientation, color and language and can provide reliable text binarization result.
Abstract: Text detection in color images has become an active research area since recent decades. In this paper, we present a novel approach to accurately detect text in color images possibly with a complex background. First, we use an elaborate edge detection algorithm to extract all possible text edge pixels. Second connected component analysis is employed to construct text candidate region and classify part non-text regions. Third each text candidate region is verified with texture features derived from wavelet domain. Finally, the expectation maximization algorithm is introduced to binarize text regions to prepare data for recognition. In contrast to previous approach, our algorithm combines both the efficiency of connected component based method and robustness of texture based analysis. Experimental results show that our algorithm is robust in text detection with respect to different character size, orientation, color and language and can provide reliable text binarization result.

37 citations

Proceedings ArticleDOI
03 Aug 2003
TL;DR: A new approach to extracting the target text line from a document image captured by a pen scanner by using a geometric feature based score function and fed to an OCR engine for character recognition.
Abstract: In this paper, we present a new approach to extracting the target text line from a document image captured by a pen scanner. Given the binary image, a set of possible text lines are first formed by nearest-neighbor grouping of connected components (CC). They are then refined by text line merging and adding the missed CCs. The possible target text line is identified by using a geometric feature based score function and fed to an OCR engine for character recognition. If the recognition result is confident enough, the target text line is accepted. Otherwise, all the remaining text lines are fed to the OCR engine to verify whether an alternative target text line exists or the whole image should be rejected. The effectiveness of the above approach is confirmed by experiments on a testing database consisting of 117 document images captured by C-Pen and ScanEye pen scanners.

36 citations

Proceedings ArticleDOI
01 Oct 2018
TL;DR: This work proposes a technique that is able to perform ALPR using only two deep networks, the first performs license plate detection (LPD) and the second performslicense plate recognition (LPR), which does not execute explicit character segmentation, which reduces significantly the error propagation.
Abstract: With the increasing number of cameras available in the cities, video traffic analysis can provide useful insights for the transportation segment. One of such analysis is the Automatic License Plate Recognition (ALPR). Previous approaches divided this task into several cascaded subtasks, i.e., vehicle location, license plate detection, character segmentation and optical character recognition. However, since each task has its own accuracy, the error propagation between each subtask is detrimental to the final accuracy. Therefore, focusing on the reduction of error propagation, we propose a technique that is able to perform ALPR using only two deep networks, the first performs license plate detection (LPD) and the second performs license plate recognition (LPR). The latter does not execute explicit character segmentation, which reduces significantly the error propagation. As these deep networks need a large number of samples to converge, we develop new data augmentation techniques that allow them to reach their full potential as well as a new dataset to train and evaluate ALPR approaches. According to experimental results, our approach is able to achieve state-of-the-art results in the SSIG-SegPlate dataset, reaching improvements up to 1.4 percentage point when compared to the best baseline. Furthermore, the approach is also able to perform in real time even in scenarios where many plates are present at the same frame, reaching significantly higher frame rates when compared with previously proposed approaches.

36 citations


Network Information
Related Topics (5)
Feature extraction
111.8K papers, 2.1M citations
87% related
Feature (computer vision)
128.2K papers, 1.7M citations
85% related
Image segmentation
79.6K papers, 1.8M citations
85% related
Convolutional neural network
74.7K papers, 2M citations
84% related
Deep learning
79.8K papers, 2.1M citations
83% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023186
2022425
2021333
2020448
2019430
2018357