Tamil is one of the ancient Indian languages which has a vast collection of literature in the form of palm leaf, stones, metal plates, and other materials. Palm leaf manuscript was a broad tool to narrate medicines, literature, drama, and many more. Recognition of the characters written in palm leaf manuscripts is still an open task because of the need for digitization and transcription. In this paper, the recurrent neural network (RNN) is used to train the features of the characters extracted from the palm leaf. This method contains a preprocessing method to eliminate noise; then the character is segmented from the image and trained using the bidirectional long short-term memory (BLSTM) network. A feature vector with nine zones of character strokes is used to train and test the characters. A rich set of characters are used to train the features of the characters. This method provides better recognition accuracy than the other neural network-based character recognition.

Recurrent Neural Network-Based Character Recognition System for Tamil Palm Leaf Manuscript Using Stroke Zoning

We propose a novel generative approach for face recognition, in which sparse facial features are extracted from high resolution color face images using predefined landmark topologies which mark discriminative locations on face images, unlike the appearance-based approach, in which low resolution grayscale face images are used, reducing the computational complexity. By adopting a common landmark topology, the dissimilarity between distinct face images can be scored in terms of the dissimilarities between their corresponding landmarks, which are obtained by proposed geodesic distance approximations between multivariate normal distributions which represent the color intensities in the vicinities of each landmark location. The classification process of new face samples occurs by the determination of the face image sample present in the training set which minimizes the dissimilarity score. The proposed method was compared with representative current state-of-the-art methods using color or grayscale face images and presented the higher recognition rates. Moreover, these results also support a trend in which color information is relevant in face recognition.

/pdf/face-recognition-based-on-geodesic-distance-approximations-4wgthcpbvv.pdf

Face recognition based on geodesic distance approximations between multivariate normal distributions

Geodesic distance is a natural dissimilarity measure between
probability distributions of a specific type, and can be used to
discriminate texture in image-based measurements Furthermore, since
there is no known closed-form solution for the geodesic distance
between general multivariate normal distributions, we propose two
efficient approximations to be used as texture dissimilarity metrics
in the context of face recognition A novel face recognition
approach based on texture discrimination in high-resolution color
face images is proposed, unlike the typical appearance-based
approach that relies on low-resolution grayscale face images In our
face recognition approach, sparse facial features are extracted
using predefined landmark topologies, that identify discriminative
image locations on the face images Given this landmark topology,
the dissimilarity between distinct face images are scored in terms
of the dissimilarities between their corresponding face landmarks,
and the texture in each one of these landmarks is represented by
multivariate normal distributions, expressing the color distribution
in the vicinity of each landmark location The classification of new
face image samples occurs by determining the face image sample in
the training set which minimizes the dissimilarity score, using the
nearest neighbor rule The proposed face recognition method was
compared to methods representative of the state-of-the-art, using
color or grayscale face images, and presented higher recognition
rates Moreover, the proposed texture dissimilarity metric also is
efficient in general texture discrimination (eg, texture
recognition of material images), as our experiments suggest

/pdf/face-recognition-based-on-texture-information-and-geodesic-4b4nyhm1by.pdf

Face recognition based on texture information and geodesic distance approximations between multivariate normal distributions

Geodesic distances are a natural dissimilarity measure between
probability distributions of a fixed type, and are used to discriminate texture in
several image-based measurements. Besides, since there is no known
closed-form solution for the geodesic distance between general
multivariate normal distributions, we propose two efficient
approximations to discriminate textures in the context of face
recognition. Unlike the typical appearance-based approach that uses
low-resolution grayscale face images, we propose a novel generative
approach for face recognition based on texture discrimination. In
the proposed approach, sparse facial features are extracted from
high-resolution color face images using predefined landmark
topologies, in which landmarks are in discriminative locations of
face images. By adopting a common landmark topology, the
dissimilarity between distinct face images can be scored in terms of
the dissimilarities between the texture in their corresponding
landmark vicinities. The proposed multivariate normal distributions
represent the color intensities around each landmark location. The
classification of new face samples occurs by determining the face
image sample in the training set which minimizes the dissimilarity
score. The proposed face recognition method was compared to methods
representative of the state-of-the-art using color and grayscale
face images, and presented higher recognition rates. Moreover, the
proposed measures to discriminate textures tend to be efficient in
face recognition and in general texture discrimination (e.g.,
texture recognition of material images), as our experiments suggest

Face Recognition Based on Texture Discrimination by Using Geodesic Distance Approximations Between Multivariate Normal Distributions

Large AI-based language models are changing how we work with language. They are becoming increasingly popular because they allow us to create complex linguistic structures without requiring a lot of resources. A language model must have access to a large corpus of linguistic data (e.g., word frequencies) to learn and generate new words. GPT-2, a language model, can generate coherent paragraphs independently, without any input on what to write about or guidance on grammar rules. Although multiple pre-trained GPT-2 models exist for English and other high-resource languages, there are few to no such models for Indic languages like Kannada. In this study, we propose GPT-K, a GPT-2 based model for language modeling in Kannada. GPT-K has been trained on a large corpus of Kannada text and can effectively perform language modeling tasks in Kannada. The model generated syntactically correct text in most cases.

GPT-K: A GPT-based model for generation of text in Kannada

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.

http://iopscience.iop.org/article/10.1088/1757-899X/263/5/052035/pdf

Handwritten recognition of Tamil vowels using deep learning

Automatic text summarization plays a significant role in natural language processing to extract the useful information from the huge amount of online contents. Especially in human's day-to-day life, the online news article provides the information about current events around the world through the various media to the public. The research work focuses on addressing the problem of Tamil text summarization for online Tamil news article to create the summary for news data. In this research work, transliteration based Generative Pre-trained Transformer 2 (GPT-2) model is proposed to summarize the online news articles for Tamil language by extracting the great number of relevant features namely sentence position, one hot encoding, number of entities, term frequency, and inverse document frequency. We proposed Attention based LSTM- NMT Transliteration model for performing translation between Tamil and English Languages and it is compared with other transliteration models for analyzing the performance of the model. In addition, the comparative study is made between three pre trained transformer models known as fine-tuned Generative Pre-trained Transformer 2 (GPT-2) model, Text-To-Text Transfer Transformer (T-5) model and Bidirectional Encoder Representations from Transformers (BERT) model. To evaluate the performance of all models, the dataset is created for Tamil language by gathering the data from various online sources. The experiments are done to evaluate the enhanced transliteration model based on Bilingual Evaluation Understudy Score and also to assess the GPT-2 based text summarization model based on the ROUGE evaluation measures. The performance analysis shows that the transliteration based Generative Pre-trained Transformer 2 (GPT-2) model achieves better summarization performance by reducing the occurrence of repetition.

N Ram Prashanth

Papers

Handwritten recognition of Tamil vowels using deep learning

Transliteration based Generative Pre-trained Transformer 2 Model for Tamil Text Summarization