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.
Scene Text Recognition is an extremely useful but challenging task and has drawn much attention in recent years. The best of previous model is CNN-LSTM model with attention mechanism, and it can recognize the whole text without character-level segmentation and recognition. Compared with LSTM, Recurrent Highway Networks (RHN), as a popular architecture because of its capability of training deep structure,...
In modern time, finger-vein recognition technology has become increasingly popular. Basically, the finger-vein recognition process involves finger-vein image acquisition, feature extraction and recognition. The recognition algorithm is the key research issue. Because of the differences between acquisition devices and individuals, the performance of the algorithm is affected by image rotation, translation...
Building a modern Optical Character Recognition (OCR) system for Chinese is hard due to the large Chinese vocabulary list. Training images for rare Chinese characters are extremely expensive to obtain. Radical-based OCR systems tackle this problem by first extracting and recognizing basic graphical components (i.e., radicals) of a Chinese character. However, how to reliably recognize radicals still...
At present, most medical sheet (such as medical report, laboratory sheet, medical cases, etc.) in the form of nonelectronic is easy to lose, and difficult to be integrated with other electronic health data. In order to fully utilize these valuable data, in this paper we propose a deep learning approach, named k-CNN, which can intelligently recognize the contents of medical sheet. The main advantages...
This paper describes a web-based system for page segmentation and text recognition of historical documents. The system is organised following a pipeline of 4 steps : 1) digitisation, 2) preprocessing, 3) textline extraction, and 4) handwritten text recognition based on hidden Markov models. In this study we used to evaluate the system the “Statuti del Doge Tiepolo”, a 14th century manuscript written...
In this paper, a font size independent Optical Character Recognition (OCR) system for Urdu document images is presented. Urdu documents are written using Noori Nastalique writing style with different font sizes of normal text and headings. Most of current state of the art techniques of Urdu OCRs support recognition of text having single font size. The presented study deals with the recognition of...
The technological advancement and sophistication in cameras and gadgets prompt researchers to have focus on image analysis and text understanding. The deep learning techniques demonstrated well to assess the potential for classifying text from natural scene images as reported in recent years. There are variety of deep learning approaches that prospects the detection and recognition of text, effectively...
Feature extraction is the process of mapping input signal to informative representation that can easily be handled by the classifier systems to build decision boundary in between the participating pattern classes. Scattering representation build invariant signal representation by applying a cascade of wavelet decompositions and complex modulus, followed by low-pass filtering. The objective of this...
Optical Character Recognition is the process of converting an input text image into a machine encoded format. Different methods are used in OCR for different languages. The main steps of optical character recognition are pre-processing, segmentation and recognition. Recognizing handwritten text is harder than recognizing printed text. Convolutional Neural Network has shown remarkable improvement in...
This paper presents a methodology for recognition of handwritten Marathi and English Characters-Numerals using shape context descriptor. During pre-processing an algorithm is developed to extract the Marathi and English Characters-Numerals form grid formatted datasheets. The corresponding sample points around the boundary of a character are computed. This is followed by obtaining the centroid of the...
Trademark retrieval systems have been a well researched field however majority of these researches have been done on device trademarks and do not consider the presence of text embedded within trademark images as in case of composite marks. In this work a unified retrieval system has been proposed and implemented for composite trademarks. The technique is invariant to font size, font style and orientations,...
With the rapid increase of multimedia data, textual content in an image has become a very important source of information for several applications like navigation, image search and retrieval, image understanding, captioning, machine translation and several others. Scene text localization is the first step towards such applications and most current methods focus on generating a small set of high precision...
Most research in image classification has focused on applications such as face, object, scene and character recognition. This paper examines a comparative study between deep convolutional neural networks (CNNs) and bag of visual words (BOW) variants for recognizing animals. We developed two variants of the bag of visual words (BOW and HOG-BOW) and examine the use of gray and color information as well...
This paper focuses in particular on the problem of Chinese characters recognition in natural scenes. Due to large variation in fonts, sizes, illumination, cluttered backgrounds, geometric distortions, etc., scene text recognition in the wild is a challenging problem. We proposed a novel method which based on Integral Channel Feature and pooling technology to extract informative features from scenes...
The aim of this paper is to develop a system that involves character recognition of Brahmi, Grantha and Vattezuthu characters from palm manuscripts of historical Tamil ancient documents, analyzed the text and machine translated the present Tamil digital text format. Though many researchers have implemented various algorithms and techniques for character recognition in different languages, ancient...
Considering the characteristic of Mongolian words where all letters of one Mongolian word are conglutinated together, the segmentation-free strategy is more suitable for Mongolian word recognition. This paper presents a novel recognition method based on MWRCNN and position maps for online handwritten Mongolian word. Firstly, the incorporation of position maps and aspect ratio is used to construct...
Paper describes an investigation of simplified neocognitron neural network model as a tool for practical recognition of handwritten mark images. Simplification of neocognitron structure from only two stages and fixed number of feature-extraction planes is proposed, the overall stages of solving practical image processing problem are described. Recognition properties of simplified net are investigated,...
Sign language is widely used by individuals with hearing impairment to communicate with each other conveniently using hand gestures. However, non-sign-language speakers find it very difficult to communicate with those with speech or hearing impairment since it interpreters are not readily available at all times. Many countries have their own sign language, such as American Sign Language (ASL) which...
Due to the rapid increase of different digitized documents, the development of a system to automatically retrieve document images from a large collection of structured and unstructured document images is in high demand. Many techniques have been developed to provide an efficient and effective way for retrieving and organizing these document images in the literature. This paper provides an overview...
Indoor scene recognition is a multi-faceted and challenging problem due to the diverse intra-class variations and the confusing inter-class similarities that characterize such scenes. This paper presents a novel approach that exploits rich mid-level convolutional features to categorize indoor scenes. Traditional convolutional features retain the global spatial structure, which is a desirable property...
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.