Alphabet Recognition Research Articles

Siamese Convolutional Neural Network for ASL Alphabet Recognition

American sign language is an important communication way to convey information among the deaf community in North America and is primarily used by people who have hearing or speech impairments. The deaf community faces a struggle in schools and other institutions because they usually consist primarily of hearing people. Besides, deaf people often feel misunderstood by people who do not knowsign language, for example, family members. In the last two decades, researchers have been proposing automatic sign language recognition systems to facilitate the learning of sign language, and nowadays, computer scientists have focused on using artificial intelligence in order to develop a system capable of reducing the communication gap between hearing and deaf people. In this paper, it is proposed a siamese convolutional neural network for American sign language alphabet recognition. This siamese architecture allows the computer to reduce the high interclass similarity and high intraclass variations. The results show that the proposed method outperforms the state of the art systems.

AI at the Edge for Sign Language Learning Support

In the field of multimodal communication, sign language is and continues to be, one of the most understudied areas. Thanks to the recent advances in the field of deep learning, there are far-reaching implications and applications that neural networks can have for sign language mastering. This paper describes a method for ASL alphabet recognition using Convolutional Neural Networks (CNN), which allows to monitor user’s learning progress. American Sign Language (ASL) alphabet recognition by computer vision is a challenging task due to the complexity in ASL signs, high interclass similarities, large intraclass variations, and constant occlusions. We produced a robust model that classifies letters correctly in a majority of cases. The experimental results encouraged us to investigate the adoption of AI techniques to support learning of a sign language, as a natural language with its own syntax and lexicon. The challenge was to deliver a mobile sign language training solution that users may adopt during their everyday life. To satisfy the indispensable additional computational resources to the locally connected end- user devices, we propose the adoption of a Fog-Computing Architecture.

Emergent Literacy Instruction in Acquisition of Reading Readiness Skills Among Primary School Pupils in Ikom Education Zone, Cross River State, Nigeria

This study investigated emergent literacy instruction in acquisition of reading readiness skills among primary school pupils’ in Ikom Education Zone, Cross River State, Nigeria. Five research questions and five corresponding null hypotheses were formulated to guide the study. Ex-post facto research design was used for the study. The population of the study was twenty one thousand, eight hundred and one (21,801) pupils. Stratified random sampling technique was used to select three hundred and sixty (360) pupils as sample for the study. A structured and validated 30-item questionnaire was used for data collection. Data was analyzed using population t-test and Independent t-test to test the null hypotheses at .05 level of significance. The result of the analysis showed that Primary school pupils’ acquisition of reading readiness skills in Ikom Education Zone, with respect to, phonological awareness, knowledge of alphabets activities, oral language activities, and story book reading, is significantly high; there is a significant mean difference in phonological awareness, alphabet recognition skills, oral skills, and print awareness skills mean achievement scores of private and public school children exposed to emergent literacy instruction. Based on the findings, the following recommendations were made among others, teachers in public primary schools should cultivate preschool children’s willingness to listen to stories, desire to be read to, curiosity about words and letters, exploration of print forms, playfulness with words, enjoyment of songs, poems, rhymes, jingles, books, and dramatic play.

Hand gesture recognition-based non-touch character writing system on a virtual keyboard

The non-touch system is a modern approach of computer-interface technology capable of revolutionizing human-computer interaction. The interface allows the user to input data and interact with a human, machine or robot in an uncontrolled environment, treatment or industrial life. However, it is challenging to input data into the machine and interact with man and machine with a variety of complexities such as cluttered environment, gesture tracking, and speed. There are many evolving systems, for example, aerial handwriting, sign language recognition, and finger alphabet recognition require substantial effort for all character learning and overhead processing, thence the accuracy of the classification is reduced. Therefore, this paper proposes a non-touch character writing system that allows users to interact and manage the on-screen virtual keyboards in a secure and healthy way by recognizing few hand gestures. We divide this work into two parts: a) hand gesture recognition; and b) gestural flick input using a virtual keyboard. A user-friendly keyboard interface is displayed on the monitor, which uses a flick input method. A deep learning method with CNN is used to extract the features of a gesture. To determine these features, color segmentation is used to detect the hand; color pixels can be obtained by extracting a particular HSV (hue, saturation, value) and applying threshold masking to the input image. Finally, a support vector machine is used to give a more accurate classification of the hand gestures. The user uses a gestural flick input system to perform non-touch character input and enters the character by viewing the virtual keyboard. The character input is executed based on the recognition of the user’s hand gestures. Character input is evaluated based on the average classification accuracy of hand gestures and character recognition, and the accuracy and speed of input. Then, the system is compared with the state-of-the-art algorithms. The experimental results show that the proposed system can recognize seven typical gesture functions and input characters with 97.93% accuracy, which demonstrate the superiority compared to the state-of-the-art algorithms.

A Design of a Hybrid Algorithm for Optical Character Recognition of Online Hand-Written Arabic Alphabets

The growing relevance of printed and digitalized hand-written characters has necessitated the need for convalescent automatic recognition of characters in Optical Character Recognition (OCR). Among the handwritten characters, Arabic is one of those with special attention due to its distinctive nature, and the inherent challenges in its recognition systems. This distinctiveness of Arabic characters, with the difference in personal writing styles and proficiency, are complicating the effectiveness of its online handwritten recognition systems. This research, based on limitations and scope of previous related studies, studied the recognition of Arabic isolated characters through the identification of its features and dots in view of producing an efficient online Arabic handwriting isolated character recognition system. It proposes a hybrid of decision tree and Artificial Neural Network (ANN), as against being combined with other algorithms as found in previous studies. The proposed recognition process has four main steps with associated sub-steps. The results showed that the proposed method achieved the highest performance at 96.7%, whereas the benchmark methods which are EDMS and Naeimizaghiani had 68.88% and 78.5 % respectively. Based on this, ANN has the best performance recognition rate at 98.8%, while the best rate for decision tree was obtained at 97.2%.

СROSS PLATFORM TOOLS FOR MODELING AND RECOGNITION OF THE FINGERSPELLING ALPHABET OF GESTURE LANGUAGE

A solution for the problems of the finger spelling alphabet of gesture language modelling and recognition based on cross-platform technologies is proposed. Modelling and recognition performance can be flexible and adjusted, based on the hardware it operates or based on the availability of an internet connection. The proposed approach tunes the complexity of the 3D hand model based on the CPU type, amount of available memory and internet connection speed. Sign recognition is also performed using cross-platform technologies and the tradeoff in model size and performance can be adjusted. the methods of convolutional neural networks are used as tools for gestures of alphabet recognition. For the gesture recognition experiment, a dataset of 50,000 images was collected, with 50 different hands recorded, with almost 1,000 images per each person. The experimental researches demonstrated the effectiveness of proposed approaches.

Recognition of similar characters using gradient features of discriminative regions

One important and challenging issue in handwritten character recognition is the discrimination of visually similar characters. In this paper, we propose a character recognition method for distinguishing similar characters by augmenting commonly used image feature with gradient features from potentially discriminative image regions. The discriminative regions of similar characters sets are automatically detected by analysing the weight vectors of the sparsity promoting logistic fused Lasso method. The histogram of oriented gradients is adopted to compactly represent the gradient features. Additionally, the locality preserving projection method is employed to alleviate the high dimensional nature of the resulting feature vectors. Experimental results on handwritten Lanna Dhamma and Thai characters datasets demonstrate the capability of the proposed method in discriminating visually similar characters. The method also outperforms existing character recognition methods by considerable margins. It has a great potential for character recognition of other alphabets.

Some aspects of reading difficulties in the stage of kindergarten in Arab and foreign studies and ways of treatment: A theoretical study

The present study aimed to identify some of the difficulties of reading in the stage of kindergarten in Arab and foreign studies. In her study, the researcher followed the theoretical approach. The tool was used to collect information from the results of previous studies, which were applied to a sample of kindergarten children. The present study concluded that pre-academic skills (character recognition skills, phonological recognition skills, numeracy skills, color recognition skills, shape recognition skills) are essential skills for predicting reading difficulties in children in the future. The study focused on the results of the study (the skill of recognition of alphabets, and the skill of perception of the phonological), which affects the reading clearly and significantly for teachers, which helps to discover children early at risk of reading. The results of the present study also confirm the relationship between pre-academic skills deficiencies, predicting future reading difficulties for the child, and a close and important correlation between cognitive skill, phonological cognition, and character recognition skills and their impact on subsequent reading. These skills are indicators of reading difficulties later, Training in phonological cognition greatly helps to improve character recognition and reading skills. The researcher recommended preparing teachers for the difficulties of learning the kindergarten stage well, paying attention to the early detection of children with learning disabilities in the kindergarten stage, preparing standardized measures to identify the children who predicted difficulty, In the development and application of intervention programs.

Development of an Alphabetic Character Recognition System Using Matlab for Bangladesh

Development of an Alphabetic Character Recognition System Using Matlab for Bangladesh

Recognition of Indian Sign Language Alphabets for Hearing and Speech Impaired People using Deep Learning

A large portion of the hearing and speech impaired are deprived of any education and just around 1-2% of the hearing and speech impaired get schooling in Indian sign language. The large portion of them is incapable of using theoretical languages, having difficult issues to express themselves or understanding printed texts. So, there is need to build an auto- mated translation system with innovations for helping hearing and speech impaired people in communicating among them. Sign language recognition is an evolving research area in computer vision and machine learning. In this paper, recognition of Indian sign language alphabets will be carried out using deep learning and machine learning. A large database of images of sign language alphabets will be captured through web camera. The network is train by providing input and expected outputs. The project will explore the various deep learning algorithms such as AlexNet and GoogLeNet will be used for training the images. The trained model using various architectures will be used for testing the other Indian sign language alphabets. The comparative study of accuracy of various architecture will be carried out.

User-Independent American Sign Language Alphabet Recognition Based on Depth Image and PCANet Features

Sign language is the most natural and effective way for communications among deaf and normal people. American Sign Language (ASL) alphabet recognition (i.e. fingerspelling) using marker-less vision sensor is a challenging task due to the difficulties in hand segmentation and appearance variations among signers. Existing color-based sign language recognition systems suffer from many challenges such as complex background, hand segmentation, large inter-class and intra-class variations. In this paper, we propose a new user independent recognition system for American sign language alphabet using depth images captured from the low-cost Microsoft Kinect depth sensor. Exploiting depth information instead of color images overcomes many problems due to their robustness against illumination and background variations. Hand region can be segmented by applying a simple preprocessing algorithm over depth image. Feature learning using convolutional neural network architectures is applied instead of the classical hand-crafted feature extraction methods. Local features extracted from the segmented hand are effectively learned using a simple unsupervised Principal Component Analysis Network (PCANet) deep learning architecture. Two strategies of learning the PCANet model are proposed, namely to train a single PCANet model from samples of all users and to train a separate PCANet model for each user, respectively. The extracted features are then recognized using linear Support Vector Machine (SVM) classifier. The performance of the proposed method is evaluated using public dataset of real depth images captured from various users. Experimental results show that the performance of the proposed method outperforms state-of-the-art recognition accuracy using leave-one-out evaluation strategy.

Indian Sign Language Alphabets Recognition from Static Images Using Correlation-Coefficient Algorithm with Neuro-Fuzzy Approach

Sign Language is a language used by mute people to communicate with other person by expressing their thoughts in the form of signs. Signs are expressed by hand and face movement. This paper describes proposed methodology for design and implementation of Alphabets recognition system of Indian sign language where static images of hand gesture are used as an input. Methodology includes various image processing techniques to remove unnecessary noise and to make images smooth. This Paper describe Correlation-coefficient algorithm which has been used for feature extraction and Neuro-fuzzy algorithm which has been applied as recognition algorithm. Proposed technique has been implemented on database of 100 images for testing. Implementation has been done on Matlab. Average accuracy of proposed methodology is 92.30%.

American Sign Language alphabet recognition using Convolutional Neural Networks with multiview augmentation and inference fusion

American Sign Language (ASL) alphabet recognition by computer vision is a challenging task due to the complexity in ASL signs, high interclass similarities, large intraclass variations, and constant occlusions. This paper describes a method for ASL alphabet recognition using Convolutional Neural Networks (CNN) with multiview augmentation and inference fusion, from depth images captured by Microsoft Kinect. Our approach augments the original data by generating more perspective views, which makes the training more effective and reduces the potential overfitting. During the inference step, our approach comprehends information from multiple views for the final prediction to address the confusing cases caused by orientational variations and partial occlusions. On two public benchmark datasets, our method outperforms the state-of-the-arts.

Alphabet Recognition System Based on Artifical Neural Network

Alphabet Recognition System Based on Artifical Neural Network

Implementation and Performance Evaluation of Neural Network for English Alphabet Recognition System

Implementation and Performance Evaluation of Neural Network for English Alphabet Recognition System

Implementation and Performance Evaluation of Neural Network for English Alphabet Recognition System

Implementation and Performance Evaluation of Neural Network for English Alphabet Recognition System

Recognition of Sign Language Alphabets and Numbers based on Hand Kinematics using A Data Glove

This paper reports real-time recognition of Indian and American sign language alphabets and numbers based on hand kinematics assessment. The finger and wrist joint angles were acquired using an indigenously developed data glove. The data set was for single handed Indian sign language alphabets (C, I, J, L, O, U, Y, W), American sign language alphabets (A to Z) and sign numbers (0 to 9). The data were pre-processed through a moving average filter and standardized feature scaling methods. The glove was able to measure the finger joint angles with an accuracy±standard deviation for metacarpophalangeal (MCP) joint±2.14°, proximal inter phalangeal (PIP) joint± 1.73° and distal inter phalangeal (DIP) joint± 1.49°, during flexion/extension and abduction/adduction movements. A radial basis function kernel support vector machine with 10-fold cross validation was used for recognition. An average recognition rate of 96.7% was achieved. Using a label matching and speech data base, the recognized alphabets and numbers were translated into speech.

Shape Based Pakistan Sign Language Categorization Using Statistical Features and Support Vector Machines

All over the world, deaf use sign language to communicate each other. The signs are built and communicated through movements and the shapes of the hands. Pakistan sign language (PSL) is used by the deaf community of Pakistan. Automatic recognition of PSL alphabets into the predefined categories is presented here. The seven categories are defined using the visibility, shape, and the orientations of both the fingers and the hand. The histograms of the uniform local binary (lbp) for the neighboring distance of one, two, and three are computed and concatenated to form a single vector. At a later step, six statistical features of the combined histogram are computed, i.e., standard deviation, variance, skewness, kurtosis, entropy, and energy. The classification is achieved using support vector machines (SVMs). The modality of one-verses-one is used for the adoption of binary SVM into the multi-class SVM. The proposed technique is validated over the data set of 3414 PSL signs, taken through the help of seven native signers. The performance of the proposed technique is evaluated by precision, recall, accuracy, and f-measure, while it is elaborated through the classification matrix, tabular, and graph representations.

Hardware and Software Co-Design of Arabic Alphabets Recognition Platform for Blind and Visually Impaired Persons

Background:Optical character Recognition (OCR) is a technic that converts scanned or printed text images into editable text. Many OCR solutions have been proposed and used for Latin and Chinese alphabets.However not much can be found about OCRs for the handwriting scripts Arabic Alphabets, and especially to be used for blind and visually impaired persons.This paper has been an attempt towards the development of an OCR for Arabic Alphabets dedicated to blind and visually impaired persons.Method:The proposed Optical Arabic Alphabets Recognition algorithm includes binarization of the inputted image, segmentation, feature extraction and a classification based on neural networks to match read Arabic alphabets with trained pattern.The proposed algorithm has been developed using Matlab, and the solution was designed to be implemented on hardware platform and can be customized for mobile phones.Conclusion:The presented method has the benefit that the accuracy of recognition is comparable to other OCR algorithms.

Handwritten recognition of Tamil vowels using deep learning

We come across a large volume of handwritten texts in our daily lives and handwritten character recognition has long been an important area of research in pattern recognition. The complexity of the task varies among different languages and it so happens largely due to the similarity between characters, distinct shapes and number of characters which are all language-specific properties. There have been numerous works on character recognition of English alphabets and with laudable success, but regional languages have not been dealt with very frequently and with similar accuracies. In this paper, we explored the performance of Deep Belief Networks in the classification of Handwritten Tamil vowels, and conclusively compared the results obtained. The proposed method has shown satisfactory recognition accuracy in light of difficulties faced with regional languages such as similarity between characters and minute nuances that differentiate them. We can further extend this to all the Tamil characters.