Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

371013 · Jun 202019922001200920182026
48 results for Persian handwritten letters

Study improves Persian handwritten letter recognition using ECOC ensemble method.

problem Improving accuracy in identifying Persian handwritten letters.
method ECOC ensemble method with feature selection and Support Vector Machine (SVM).
result ECOC ensemble method outperforms other methods in identifying Persian handwritten letters.

The paper presents a recognition system for Pashto letters using KNN and ANN.

problem Challenging handwritten character recognition, especially for Pashto letters.
method Designed a database of 4488 images, used zoning feature extractor, KNN, and ANN classifiers.
result Achieved overall classification accuracy of 70.05% using KNN and 72% using ANN.

Paper builds a Persian wordnet using supervised learning.

problem Creating an accurate Persian wordnet.
method Used a Persian corpus and bi-lingual dictionary to generate initial links. Trained a classification system on a set of correct instances to discriminate correct from incorrect links.
result Achieved state-of-the-art results with a precision of 91.18%.

Pars-ABSA dataset for Persian aspect-based sentiment analysis.

problem Lack of public dataset for Persian aspect-based sentiment analysis.
method Manually annotated dataset with 5,114 positive, 3,061 negative, and 1,827 neutral samples.
result State-of-the-art performance of deep learning methods on Pars-ABSA compared to similar English datasets.

Study classifies Persian speech acts for better understanding of text intent.

problem Understanding the intended function of Persian texts.
method Dictionary-based statistical technique using WordNet for SA recognition.
result Proposed method achieved state-of-the-art accuracy of 0.95 for Persian SA classification.

Paper proposes a deep learning method to measure domain similarity in Persian texts.

problem Measuring the similarity between different domains of Persian text descriptions.
method Built a dataset of paired texts, used word embeddings and deep neural networks to score similarity, trained on GPU.
result Best model achieved an F1 score of 0.9865.

Deep transfer learning from Persian handwriting improves offline signature verification.

problem Challenges in offline signature verification, especially with skilled forgeries and limited training data.
method Transfer learning approach from Persian handwriting to multi-language OSV, using Residual CNNs for feature learning and SVMs for verification.
result Significant improvement in Equal Error Rate (EER) on UT-Sig dataset (9.80% EER), surpassing state-of-the-art methods.

Deep learning improves handwriting style transfer and extraction.

problem Improving handwriting style transfer and extraction using deep neural networks.
method Used a deep conditioned autoencoder on IRON-OFF handwriting data-set to explore style transfer and extraction.
result Improved metrics of state-of-the-art methods by a large margin in style transfer and extraction experiments.

HW2MP-GAN tackles ancient handwritten text recognition.

problem Automatic text recognition from ancient handwritten records.
method Conditional Generative Adversarial Network (HW2MP-GAN) with Sliced Wasserstein distance and U-Net architectures.
result HW2MP-GAN outperforms state-of-the-art models in image-to-image translation and handwritten recognition.

New model enhances SPIM for solving low-rank combinatorial optimization and statistical learning problems.

problem Solving large-scale combinatorial optimization problems efficiently.
method Proposed a new computing model for SPIM that can handle low-rank interaction matrices.
result Demonstrated efficient learning, classification, and sampling of MNIST images using the model.

We show that the predictability of letters in written English texts depends strongly on their position in the word. The first letters are usually the least easy to predict. This agrees with the intuitive notion that words are well defined subunits in written languages, with much weaker correlations across these units t…

2007-10-24abs ↗pdf ↗

Paper tackles handwritten annotation recognition in historic documents using FCNN.

problem Recognizing handwritten annotations in challenging historic German documents.
method End-to-end semantic segmentation using Fully Convolutional Neural Networks (FCNN).
result Best model achieves 95.6% IoU score on test documents.

A criterion is given for cutting out disks with ribbons from a Möbius strip.

problem Determining which hieroglyphs can be realized as disks with ribbons on a Möbius strip.
method Developed a criterion based on Mohar's realizability criterion, leading to a quadratic algorithm.
result A criterion for weak realizability of disks with ribbons on a Möbius strip.

A new method aligns spatial and temporal data, improving on Dynamic Time Warping.

problem Comparing data over space and time, accounting for both spatial and temporal variability.
method Spatio-Temporal Alignments (STA) using regularized optimal transport (OT) and soft-DTW.
result Soft-DTW increases quadratically with time shifts, effectively handling spatio-temporal data.

Optimal ANN pre-training with SDA reduces handwritten Bengali digit recognition error to 2.34%

problem Optimizing ANN architecture for Bengali handwritten digit recognition
method Pre-training ANN with stacked denoising autoencoder (SDA)
result Minimum validation error of 2.34% on handwritten Bengali dataset

The paper predicts TSE stocks using social media sentiment and volume.

problem Predicting Tehran Stock Exchange (TSE) variables using social media data.
method Hybrid sentiment analysis combining lexicon-based and learning-based methods; built a sentiment lexicon for Persian language.
result Sentiment and volume of online comments are useful for predicting TSE stocks.

Letters discuss results on Courant algebroids, including classification and reduction.

problem Understanding and classifying Courant algebroids.
method Analyzes properties of Courant algebroids, including exact and transitive ones, and describes them in terms of symplectic dg manifolds.
result Provides a canonical generating Dirac operator and relates CAs to Poisson-Lie T-duality.

The paper uses attention networks for character-based handwritten text transcription.

problem Handwritten text recognition with improved character-level alignment.
method Attentional encoder-decoder networks trained on character sequences, comparing different activation functions.
result Softmax attention provides more precise character alignment than sigmoid attention.

A diverse system combines CNNs and meta-nets for handwritten digit recognition.

problem Handwritten digit recognition using diverse classification hypotheses.
method Generate diverse classification hypotheses using CNNs and other techniques, then combine them with Meta-Nets.
result Achieved state-of-the-art performance in handwritten digit recognition.

End-to-end solution for recognizing handwritten numerals, avoiding traditional preprocessing steps.

problem Handwritten numeral string recognition with traditional preprocessing steps.
method YoLo-based model for automatic detection and recognition, avoiding heuristic-based preprocessing and segmentation.
result Proposed method reduces complexity and is a feasible end-to-end solution for numeral string recognition.

A new framework for averaging spatio-temporal signals using optimal transport and soft alignments.

problem Averaging complex datasets with time and spatial components.
method Inspired by DTW, OT, and UOT, a new loss function is proposed to address shifts in time, space, and population size.
result The proposed loss function can be used to compute spatio-temporal barycenters efficiently.

Machine learning identifies historical graffiti letters with high accuracy.

problem Identifying historical graffiti letters carved on stone walls.
method Pre-processed a dataset of 4000 images of carved letters, applied MLR and CNN models.
result CNN model achieved AUC values close to 0.99 for both notMNIST and CGCL.

A tailored HTR system improves CER to 0.015 for medieval Latin.

problem Digitizing handwritten medieval Latin records for a low-resource language.
method End-to-end pipeline using image segmentation and transformer-based models with extensive data augmentation.
result Best-performing setup achieved CER of 0.015, superior to commercial models.

In the era of deep learning several unsupervised models have been developed to capture the key features in unlabeled handwritten data. Popular among them is the Restricted Boltzmann Machines RBM. However, due to the novelty in handwritten multidialect data, the RBM may fail to generate an efficient representation. In t…

2015-08-17abs ↗pdf ↗

The paper proves group actions on spheres with odd fixed points.

problem Finite group actions on homology six-spheres with odd Euler characteristics.
method Analyzes smooth actions and fixed point sets of finite groups.
result The group is one of three specific types, and the fixed point set is a single point.

New algorithm uses random matrices for neural network training without synaptic weight symmetries.

problem Training neural networks efficiently and without synaptic weight symmetries.
method Contrastive Hebbian learning with random feedback weights.
result Random contrastive Hebbian learning achieves better computational models for learning.

Capsule network improves handwriting recognition of historical graffiti.

problem Recognizing historical graffiti letters carved on stone walls.
method Used capsule deep neural network on a challenging dataset of 4000 images of 34 letters.
result Validation accuracy and AUC values were significantly higher for capsule network than for CNN.

Improved CNN for HCCR with new loss function and ranking method.

problem Loss of inter-class information in traditional CNN models for HCCR.
method Combining cross entropy with a new similarity ranking function (Average variance similarity) as loss function.
result New loss function (SoftMax cross entropy with Average variance similarity) achieves highest accuracy in HCCR.

The sequence (xn)nN=(2,5,15,51,187,)(x_n)_{n\in\mathbb N} = (2,5,15,51,187,\dots) given by the rule xn=(2n+1)(2n1+1)/3x_n=(2^n+1)(2^{n-1}+1)/3 appears in several seemingly unrelated areas of mathematics. For example, xnx_n is the density of a language of words of length nn with four different letters. It is also the cardinality of the quotient of $(\math…

2014-09-06abs ↗pdf ↗

EASTER improves OCR efficiency and scalability.

problem Efficient and scalable Optical Character Recognition (OCR) for machine printed and handwritten text.
method 1-D convolutional layers without recurrence, parallel training, synthetic dataset generation.
result EASTER achieves comparable performance to complex RNN models with less data and outperforms them on benchmark datasets.

Paper generalizes path signature using fractional calculus for improved machine learning.

problem Improving path signature for machine learning applications.
method Introduces two new signatures inspired by fractional calculus and machine learning considerations.
result Significant accuracy improvements in handwritten digit recognition.

Hybrid model learns novel handwritten characters better than neural or symbolic models alone.

problem Generating novel yet structured concepts.
method Neuro-symbolic model combining neural networks and probabilistic programs.
result Hybrid model outperforms alternative models in learning and generalizing novel handwritten characters.

This study examines how hidden layers affect CNN performance on handwritten digit recognition.

problem Impact of hidden layers on CNN performance in handwritten digit recognition.
method Applied CNN with varying hidden layers on MNIST dataset, trained with stochastic gradient and backpropagation, tested with feedforward.
result Variations in accuracies for different hidden layers and epochs.