Patent
Low resolution optical character recognition for camera acquired documents
TLDR
This article proposed a global optimization framework for optical character recognition (OCR) of low-resolution photographed documents that combines a binarization-type process, segmentation, and recognition into a single process.Abstract:
A global optimization framework for optical character recognition (OCR) of low-resolution photographed documents that combines a binarization-type process, segmentation, and recognition into a single process. The framework includes a machine learning approach trained on a large amount of data. A convolutional neural network can be employed to compute a classification function at multiple positions and take grey-level input which eliminates binarization. The framework utilizes preprocessing, layout analysis, character recognition, and word recognition to output high recognition rates. The framework also employs dynamic programming and language models to arrive at the desired output.read more
Citations
More filters
Patent
Text detection method and device and text detection training method and device
TL;DR: In this article, a convolutional neural network is used to extract a feature map from an image with a text area, and a number of anchor rectangles are used to transversely intercept the feature map to acquire a set of recommendation areas.
Patent
Method for automatically reading a utility meter, retrofittable meter reader and automatic meter reading system using the same
TL;DR: In this article, the authors proposed a method for reading a utility meter having a display including one or more digits, characterized in that it comprises the steps of: a) capturing (1006, 1022) an image of the display by means of an image sensor (192); b) if the type of utility meter has to be detected (1004), detecting (1008), and c) segmenting the image into as many single-digit images as there are digits on the display of the detected type, setting up a pattern recognition algorithm with configuration parameters specific to a
Patent
Acoustic event detecting method under hospital noise environment
TL;DR: In this paper, an acoustic event detection method under the hospital noise environment was proposed, in which voice is accurately recognized to be text, the recognition rate of an electronic medical record input through the voice is increased, and the false recognition rate is decreased.
Patent
Mobilgerät zum Erfassen eines Textbereiches auf einem Identifikationsdokument
TL;DR: In this paper, the authors find an Erfindung of a Mobilgerat (100) zum Erfassen eines Textbereiches auf einem Identifikationsdokument, wobei der textbereich eine Mehrzahl von Textzeichen in einer vorbestimmten Anordnung gemas einem vor bestimmten A-MSA aufweist, with einer Bildkamera (101), welche ausgebildet ist, ein Bild
Patent
Lip shape recognition character input method based on cloud analysis and model match
TL;DR: In this paper, a lip shape recognition character input method based on cloud analysis and model match is proposed, where a lip image of a target person shot by a camera is uploaded to a cloud server by a computer on spot through internet; the cloud server automatically analyzes the lip image, extracts a characteristic value of the lip shape, and matches the lip shapes with lip shape models in a cloud lip shape model base.
References
More filters
Book
Neural networks for pattern recognition
TL;DR: This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Proceedings ArticleDOI
Best practices for convolutional neural networks applied to visual document analysis
TL;DR: A set of concrete bestpractices that document analysis researchers can use to get good results with neural networks, including a simple "do-it-yourself" implementation of convolution with a flexible architecture suitable for many visual document problems.
Journal ArticleDOI
Character segmentation in handwritten words — An overview
Yi Lu,Malayappan Shridhar +1 more
TL;DR: This paper presents an overview on the most important techniques used in segmenting characters from handwritten words, and summarizes the terms and measurements commonly used in handwritten character segmentation.