Farsi Words Research Articles

Farsi document image recognition system using word layout signature

In this paper, a new representation of Farsi words is proposed to present the keyword spotting problems in Farsi document image retrieval. In this regard, we define a signature for each Farsi word based on the word connected component layout. The mentioned signature is shown as boxes, and then, by sketching vertical and horizontal lines, we construct a grid of each word to provide a new descriptor. One of the advantages of this method is that it can be used for both handwritten and machine-printed texts. Finally, to evaluate the performance of our system in comparison to other methods, a database that contains 19,582 printed Farsi words is examined, and after applying this approach, a recall rate of 98.1% and a precision rate of 94.3% are obtained.

Handwritten Farsi Word Recognition Using NN-Based Fusion of HMM Classifiers with Different Types of Features

In this paper, an off-line method, based on hidden Markov model, HMM, is used for holistic recognition of handwritten words of a limited vocabulary. Three feature sets based on image gradient, black–white transition and contour chain code are used. For each feature set an HMM is trained for each word. In the recognition step, the outputs of these classifiers are combined through a multilayer perceptron, MLP. High number of connections in this network causes a computational complexity in the training. To avoid this problem, a new method is proposed. In the experiments on 16000 images of 200 names of Iranian cities, from “Iranshahr 3” dataset, the results of the proposed method are presented and compared with some similar methods. An error analysis on these results is also provided.

Age of Acquisition Effect: Evidence From Single-Word Reading and Neural Networks.

Introduction:Many studies show that words learned early in life are read more easily than the ones learned later and are less vulnerable to brain damage.Methods:the first part of the current study, 25 primary school students in the 5th grade read the word groups learned initially during a previous grade. The words used in the experiments were 327 Farsi monosyllable words matched on the other factors involved in Farsi word naming.Results:The analysis of covariance (the consistency and frequency as covariates) showed that words learned in earlier grades were read more easily than the ones learned later, showing the known effect of the Age of Acquisition (AoA). In the second part of the study, it was tried to simulate AoA in word naming by a neural network model developed earlier based on connectionist approach. While previous studies used random patterns, in the current study words from primary school books were used. Likewise, words learned early by the model were read better than words learned later. However, there was a failure in replicating previous simulation of AoA in English reading by an algorithm called Quick prop for Farsi. In addition, the model was lesioned by removing some hidden units to see its effect on word reading. As a result, words learned earlier were less vulnerable to damage compared with the ones learned later.Conclusion:The findings showed that words learned earlier, compared to those learned later, were read better and were less vulnerable to damage. These effects are explained by considering the nature of learning in neural networks trained by error back-propagation.

Combining RtL and LtR HMMs to recognise handwritten Farsi words of small‐ and medium‐sized vocabularies

In this study, a method for holistic recognition of handwritten Farsi words is proposed, which fuses the outputs of right-to-left (RtL) and left-to-right (LtR) hidden Markov models (HMMs). The experimental results on 16,000 images of 200 names of Iranian cities, from the ‘Iranshahr 3’ are presented and compared with those methods using only RtL or LtR models. Experimental results show that the main sources of error are similar beginnings or similar endings of the words. Since RtL and LtR models when dealing with the words behave differently, there is notable error diversity between the two classifiers in such a way that their combination increases the recognition rate. Compared to the RtL-HMM, the product of output scores of the RtL and LtR-HMMs reduces the classification error to about 6, 6 and 3%, for three different feature sets. A subjective error analysis on the results is also provided.

Spacing effects in vocabulary learning: Young EFL learners in focus

This study used a novel method to explore different schedules of spacing in young EFL learners. In doing so, we taught young EFL learners English–Farsi word pairs using different spacing schedules ...

Sub-word-based Offline Handwritten Farsi Word Recognition Using Recurrent Neural Network

In this paper, we present a segmentation-based method for offline Farsi handwritten word recognition. Although most segmentation-based systems suffer from segmentation errors within the first stages of recognition, using the inherent features of the Farsi writing script, we have segmented the words into sub-words. Instead of using a single complex classifier with many (N) output classes, we have created N simple recurrent neural network classifiers, each having only true/false outputs with the ability to recognize sub-words. Through the extraction of the number of sub-words in each word, and labeling the position of each sub-word (beginning/middle/end), many of the sub-word classifiers can be pruned, and a few remaining sub-word classifiers can be evaluated during the sub-word recognition stage. The candidate sub-words are then joined together and the closest word from the lexicon is chosen. The proposed method was evaluated using the Iranshahr database, which consists of 17,000 samples of Iranian handwritten city names. The results show the high recognition accuracy of the proposed method.

Learners’ Perceptions of the Effectiveness of Spaced Learning Schedule in L2 Vocabulary Learning

The spacing effect is a ubiquitous phenomenon, whereby memory is enhanced for the information that is learned across different points in time rather than being learned at once. A considerable amount of research has focused on the nature of the spacing effect, and there is general acceptance that spacing learning events out in time promotes learning. However, fewer studies have been conducted in educational settings. The aim of this study is to explore learners’ perceptions of different spacing schedules (massed vs. spaced). To achieve the purpose of the study, we taught 30 children 24 English–Farsi word pairs utilizing different spacing schedules. Later, we administered a questionnaire to explore leaarners’ perceptions of both massed and spaced schedules. The results revealed that the children percieved spaced practice to be more effective than massed practice.

Transsexuality as a Window on and a Metaphor for Contemporary Iran

Transsexuality as a Window on and a Metaphor for Contemporary Iran

Coping with Lexical Gaps: Use of Compensatory Strategies by Iranian EFL Students

Learners of English as a non-native anguage unavoidably confront situations in which insufficiency of their linguistic knowledge presents them with difficulties. There are also case in which the absence of some native-language lexical items in the target language is the source of problems the learners have to grapple with. This study focused on the phenomenon known as ˜lexical gap .The aim was to identify and examine the use of compensatory strategies employed by Iranian EFL students in coping with lexical gaps.To this end, number of Iranian undergraduate EFL students were selected and then split into two groups of intermediate-level and advanced-level. Both groups were given two written tasks requiring them to introduce eight Farsi words with no English counterparts to a typical native speaker of English. The analysis of data revealed well as the existence of some surprising differences between the frequencies of strategy use by the two groups.

Farsi Word Spotting and Font Size Recognition

This paper is the first paper about Farsi word spotting and font size recognition. In this work using some font size independent features such as the number, aspect ratio, and mesh features of sub words, a Farsi keyword is described, searched and found. Also font size of document image is recognized. This approach has been evaluated on a dataset consisting of 500 Farsi document images where font size recognition rate of 94.2%. Retrieval precision rate of 92.3% at recall rate of 76.5% has been obtained. This approach with little adaptation is applicable on Arabic and Urdu documents.

Lost in translation? Culture, language and the role of the translator in international business

PurposeIssues of language in international business have been the focus of a growing body of theoretical and empirical work. This paper aims to contribute to this literature, focusing specifically on issues of translation. The role of translator will vary depending on the language strategy adopted, with strategies linked to differing perspectives on language in international business – mechanical, cultural and political. The paper examines these perspectives through the lens of a specific problem for transnational communication – “untranslatable” words and concepts.Design/methodology/approachInterviews were conducted with professional linguists (translators and interpreters) to explore how they dealt with issues of untranslatable but cultural salient words in their day‐to‐day work with international businesses, using the problems of translating the Farsi word tarouf into English as a case in point.FindingsThe linguists agreed that tarouf was an untranslatable word, and described their strategies to deal with this problem. The commonest strategy was avoidance, stemming from linguists' concern to maintain their professional standing with clients, a finding which reflects an emerging emphasis on the importance of context and relationships for understanding inter‐cultural communication.Practical implicationsThe study highlights the crucial role of the translator in international business, and draws attention to the potential for cross‐cultural communication problems arising from mutual lack of awareness of culturally‐salient but inherently untranslatable words or phrases.Social implicationsEffective inter‐cultural communication is an issue of great importance to wider society, and business has historically been the commonest site of such communication. The study highlights an issue of considerable importance for improving inter‐cultural communications, contributing to a growing inter‐disciplinary literature in this area.Originality/valueMuch of the research on language in international business has focused on the emergence of English as a lingua franca, but the present study focuses on specific issues of translation and does so in an under‐researched location, Iran. It draws attention to a problem of translation not widely discussed, and shows how important this issue can be for international business.

Iranian health houses open the door to primary care

They have been described as an incredible masterpiece. Iranian health houses, conceived and introduced during the 1980-1988 war with Iraq, have been at the centre of a so-called master plan to bring health care to every district. Devised in 1981, the plan was informed by a health-care development programme from the Western Azerbaijan province that had focused strongly on what we now recognize to be primary health care. It emphasized community participation and intersectoral cooperation to serve the needs of the thinly distributed and rapidly swelling population. Locally sourced health workers or behvarzan from the Farsi words beh (good) and varz (skill) were originally trained to meet the basic health-care needs of people living in rural areas. female behvarz was responsible for, among other things, child and maternal health; a male behvarz for sanitation and environmental projects. Both worked out-of the health house, a rural medical post and the most basic unit of service delivery in the country's healthcare plan. health houses refer patients to rural health centres, which cover about 6000 to 10 000 people, and have up to two physicians and several health technicians. These centres are responsible for elective and emergency case management, supporting the health houses, and supervising both the health technicians and the behvarzan or community health workers. Dr Sirous Pileroudi, a retired former senior official with the Ministry of Health and one of the founders of the Iranian health-care system, describes the health houses as an incredible masterpiece. At the beginning, we could never imagine such a breakthrough, he says. We were at war and the country was in a miserable condition. There was strong opposition at the time of its inception from health experts who thought the infrastructure too ambitious and the scheme a regression in health care owing to the limited education of the behvarzan. Despite this opposition and the debilitating eight-year war with its neighbouring country, Iraq, the master plan to bring health to every district has been largely successful. According to Dr Mohammad Esmael Motlaq, the director of the Centre for Healthcare Promotion affiliated with the Ministry of Health, more than 90% of the Islamic Republic of Iran's 23 million rural population enjoys healthcare services through the health houses staffed by these community health workers. People enjoy primary health care services free of charge, Motlaq says. The health workers are well familiar with the culture and traditions and that is a big advantage. [ILLUSTRATION OMITTED] There are now about 17 000 health houses in the Islamic Republic of Iran, according to the most recent Ministry of Health statistics. Almost 30 000 community health workers are working in these health houses, more than 16 000 of them women. On average, each health house serves 1500 people in its village and surrounding settlements. Community health workers are often from the village they serve, their appointment confirmed by the local rural council. Their efforts have not gone unnoticed. In a speech made in September 2007 at a ceremony to pay tribute to their work, the health minister, Dr Kamran Baqeri Lankarani, said that these community workers had made a significant contribution to the sharp decline in mortality rates in the past three decades, helping to reduce deaths among infants and pregnant women, and curbing contagious diseases. Motlaq concurs, saying the behvarzan are the axis of the village. A community health worker is from the people and has their approval. These workers regularly supervise people's health. Indeed, community health workers often have an impressive knowledge of their patients' case histories. Log books on each household are kept at the health house. These contain the name, gender and age of all family members, sanitation conditions of the household, history of pregnancies, details of care for those aged under-five and dental-care records. …

Persian/arabic handwritten word recognition using M-band packet wavelet transform

The extraction of rotation and scale invariant features is an essential problem in document image analysis. This paper proposes an effective rotation and scale invariant holistic handwritten word recognition scheme. This approach utilizes M-band packet wavelet transform to extract feature vector of Farsi word image. The global and local features extracted are exploited in recognition of limited-size lexicon of handwritten words. The rotation and scale invariant feature of a word image involves applying a polar transform to eliminate rotation and scale effects, but this produces M-row shifted polar image, which is passed to a row shift invariant M-band wavelet packet transform to eliminate the row shift effects. The output wavelet coefficients are rotation and scale invariant. For each subband of these wavelet coefficients a set of local energy features are computed and we extract feature vectors from the subbands of wavelet coefficients. The proposed polar M-band wavelet features have been tested by employing Mahalanobis algorithm to classify a set of distinct natural handwriting Farsi words. We compared the proposed scheme with two well-known rotation invariant methods; Fourier-wavelet and Zernike moments. The experimental results show that the proposed algorithm improves the recognition rate about 12 percents.

Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMM

A holistic system for the recognition of handwritten Farsi/Arabic words using right–left discrete hidden Markov models (HMM) and Kohonen self-organizing vector quantization is presented. The histogram of chain-code directions of the image strips, scanned from right to left by a sliding window, is used as feature vectors. The neighborhood information preserved in the self-organizing feature map (SOFM), is used for smoothing the observation probability distributions of trained HMMs. Experiments carried out on test samples show promising performance results.

Priming Effects on Tip-of-the-Tongue States in Farsi-English Bilinguals

The tip-of-the-tongue (TOT) phenomenon, the inability to immediately retrieve a word one desires, was studied in bilingual Farsi-English-speaking adults. One question was whether insufficient activation or increased inhibition underlie TOT states in bilinguals. Another was whether bilinguals have common or separate lexicons for their two languages. Participants heard a definition in either Farsi or English, followed by either a Farsi or English prime word related in meaning or sound, or not at all related, to the target word. Participants supplied the target word that best fit the definition. Similar-sound primes increased TOTs for English definitions and targets, with a trend for more correct responses as well, suggesting that the similar-sound prime word facilitates rather than inhibits retrieval, supporting the transmission deficit hypothesis. Primes had the same effect for same and different language conditions, suggesting that both Farsi and English map onto a single lexicon, supporting the single-store model of bilingual memory.

The distribution of English dictionary word lengths

The distribution of English dictionary word lengths has been used by Bagnold (1983) to promote the proposition that distributions arising from natural processes are not Gaussian but skew distributions with exponential tails. This proposition is examined. The distribution of written English word lengths, obtained from a sample of about 2500 words from a dictionary, is reasonably well fitted by a shifted Poisson distribution with mean and variance equal to 6.94 and 5.80. The departure from the Poisson model is mainly due to the number of two, three and four letter words. The distribution of written word lengths in various languages constitutes an important part of Bagnold's thesis which also ascribes ubiquity to the negative exponential or some form of double negative exponential distribution. The results described in this paper require the rejection of this thesis. The mean word length of the spoken word is shorter than that of written word. Furthermore, the distribution of the former is lognormal whereas the latter is not. Some unpublished Arabic and Farsi word length distributions, both bimodal, are included.