The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Noise is common phenomenon in every data. Non-text components in binarized text images, which are the results of the text extraction, are considered as noise. It degrades the performance of character recognition module. In this paper, a robust algorithm is proposed to detect text in the binarized text image with noise by extracting a new feature, called stroke width. Firstly, stroke width feature...
In many chemical industries, the metallurgy, a number of digital real-time monitoring instruments are used. The manual method will bring the problems of inefficient and misjudge. To recognize digital display instrument's real-time reading, a BP neural network is designed, an improved BP algorithm and fifteen feature extraction method is proposed. The image of instrument board is obtained by an digital...
This paper presents the simplified chain code (SCC) from our concept of basic shape to recognize the characters of Batak Toba alphabet. The proposed chain code is based on the eight-direction Freeman chain code from which the horizontal and vertical directions are omitted. Hence we focus on shapes with dominant diagonal contours which characterize the recognized alphabet. Our implementation shows...
This paper provides an overview of the OCR (optical character recognition) research in South Indian languages. OCR reading technology is benefited by the evolution of high-powered desktop computing allowing for the development of more powerful recognition software that can read a variety of common printed fonts and handwritten texts. But still it remains a highly challenging task to implement an OCR...
Text detection for video sequences has played an important role in real world applications. In the paper, new text detectors based on text intrinsic structures were proposed. Temporal information was employed to remove false positive features. And density-based method was introduced as post-processing step to filter out noises. Experimental results show that proposed approach could obtain challenging...
Different strategies for combination of complementary features in an HMM-based method for handwritten character recognition are evaluated. In addition, a noise reduction method is proposed to deal with the negative impact of low probability symbols in the training database. New sequences of observations are generated based on the original ones, but considering a noise reduction process. The experimental...
Currently few people focus on the research of printed unconnected point numeric recognition, this paper, extract this kind of number from the table number of electric energy meter (EEM). We have designed a system to recognize this kind of numeric based on neural network. Using the normalized unconnected point number image (28x20) as the neural network input. Experiment results show that the system...
OCR reading technology is benefited by the evolution of high-powered desktop computing allowing for the development of more powerful recognition software that can read a variety of common printed fonts and handwritten texts. But still it remains a highly challenging task to implement an OCR that works under all possible conditions and gives highly accurate results. This paper describes an OCR system...
To recognize digital display instrumentpsilas reading, a BP neutral network is designed, an improved BP algorithm and 15-feature extraction method is proposed. The image of instrument plate is obtained by an digital camera and transmitted to PC firstly, then an image preprocessing is carried through. The image preprocessing includes gray processing, binarization, grads sharp, vertical tilt correction,...
Global gray-level thresholding techniques such as Otsupsilas method, and local gray-level thresholding techniques such as adaptive thresholding method are powerful in extracting character objects from simple or slowly varying backgrounds. However, they are found to be insufficient when the backgrounds include sharply varying contours or fonts in different sizes. In this paper, we propose a double-edge...
Both graphic text and scene text detection in video images with complex background and low resolution is still a challenging and interesting problem for researchers in the field of image processing and computer vision. In this paper, we present a novel technique for detecting both graphic text and scene text in video images by finding segments containing text in an input image and then using statistical...
At present, the widely applied OCR system has a high recognition for printed texts, however it doesn't have a good recognition schema for formulas. In order to locate and recognize printed formulas accurately, this paper conducted researches according to the following several aspects: use Adaboost method to locate formulas automatically, image processing to obtain thinned formula area, moment method...
In the automated license plate recognition system, many reading errors are caused by inadequate character recognition method. This paper presents a novel character recognition method of license plate number based on parallel BP neural networks. This will enhance the accuracy of the recognition system that aims to read automatically the Chinese license plate. In the proposed methodology, the character...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.