Handwritten signature verification remains challenging, especially offline.
problem Discriminate genuine from forged signatures in static scenarios.
method Review of past research and analysis of recent advancements in Deep Learning.
result Deep Learning has shown promise in feature representation learning from signature images.
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.
Improves signature verification accuracy using deep CNN features.
problem Handwritten signature verification accuracy.
method Deep CNN features combined with writer-independent SVM classifier.
result Proposed approach outperforms other WI-HSV methods.
Paper tackles fixed-size representation learning for variable-sized signatures.
problem Learning feature representations for signatures of varying sizes.
method Modified Spatial Pyramid Pooling to learn fixed-sized representations from variable-sized signatures.
result Comparable performance to state-of-the-art on GPDS dataset, removing size constraint.
Paper proposes an ensemble model for writer-independent offline signature verification using deep learning.
problem Difficulty in distinguishing genuine signatures from skilled forgeries in writer-independent offline signature verification.
method Used an ensemble model with two CNNs for feature extraction, RGBT for classification, and stacking for final prediction.
result Achieved state-of-the-art performance on various datasets.
Introduces signature method for machine learning data.
problem Transforming complex data into usable features.
method Signature method applied to data paths, capturing analytic and geometric properties.
result Signature method effectively transforms data for machine learning tasks.
Deep CNN learns writer-independent features for signature verification.
problem Building classifiers that can distinguish between genuine and forged signatures.
method Used Deep Convolutional Neural Networks to learn writer-independent features.
result Features learned from one set of users are discriminative for other users, including across different datasets.
Deep CNNs improve signature verification performance.
problem Improving signature verification against skilled forgeries.
method Used Deep Convolutional Neural Networks (CNNs) to learn features from signature images.
result Achieved an Equal Error Rate of 2.74% on GPDS-160 dataset, significantly better than previous literature.
Deep generative model for healthcare data identifies coherent substructures and mutational clusters.
problem Analytical challenges in healthcare data, including sparsity, missingness, and small sample sizes.
method Proposes a deep generative Bayesian model with collapsed Gibbs sampling for multinomial count data.
result Identifies coherent substructures and biologically meaningful mutational clusters in cancer data.
Research designs first model for Amharic handwritten character recognition.
problem No existing model for Amharic handwritten character recognition.
method Used a convolutional neural network and applied data augmentation and multi-task learning.
result Promising results observed from the enhanced model.
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.
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.
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.
Generative model MSM improves on handwritten multidialect data.
problem Inefficient representation of multidialect handwritten data.
method Two-point error update for hierarchical mode synthesis.
result MSM achieves lower error values than RBM on independent and mixed 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 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.
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.
New handwritten digits dataset for Kannada script.
problem Lack of datasets for Kannada numeral digits.
method Developed Kannada-MNIST and Dig-MNIST datasets.
result Initial CNN accuracy is lower than MNIST, indicating a challenge in generalization.
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.
RNN model predicts handwritten characters from accelerometer and gyroscope data.
problem Online handwritten character recognition using sensor data.
method RNN-based neural network trained on gyroscope and accelerometer data.
result High accuracy on test data, achieving character prediction.
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.
Novel SNN achieves 99.80% accuracy on MNIST handwritten digits.
problem Real-time handwritten digit classification.
method Fixed synaptic weight maps for feature extraction and NormAD algorithm for weight adjustment.
result 7x fewer parameters than state-of-the-art networks, real-time predictions within 100ms.
We propose a simple kernel based nearest neighbor approach for handwritten digit classification. The "distance" here is actually a kernel defining the similarity between two images. We carefully study the effects of different number of neighbors and weight schemes and report the results. With only a few nearest neighbo…
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.
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.
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.
EdgeNet improves Arabic numeral classification accuracy to 99.59%.
problem Improving accuracy in Arabic numeral classification.
method Unified dataset and a novel deep model with residual connections.
result Proposed model achieves 99.59% accuracy on validation set.
Extracts transformations from images without supervision.
problem Learning meaningful image transformations from unlabeled data.
method Unsupervised learning via convex relaxation of linear combinations of nearest neighbors.
result Generated high-quality modified images with linear transformations.
Bidirectional whitening improves neural network performance.
problem Improving the efficiency and effectiveness of neural networks.
method Extending whitening process to both forward and backward propagation phases.
result Bidirectional whitening enhances natural gradient descent for better performance.
Deep learning improves gender classification from handwriting.
problem Classifying gender from handwritten text.
method Convolutional Neural Network (CNN) for feature extraction and gender classification.
result Deep learning approach outperforms human examiners in gender classification accuracy.
It is proposed a new code for contours of plane images. This code was applied for optical character recognition of printed and handwritten characters. One can apply it to recognition of any visual images.
This text aims to explain general relativity to geometers who have no knowledge about physics. Using handwritten notes by Michel Vaugon, we construct the bases of the theory.
Symmetry improves machine learning models by reducing overfitting and complexity.
problem Ignoring symmetry in machine learning models can lead to overfitting and increased complexity.
method Incorporating symmetry into machine learning models, specifically neural networks for classifying handwritten digits.
result Incorporating symmetry into machine learning models reduces overfitting and complexity, requiring less training data and less time to train.
Generative models learn useful representations for complex sequential data.
problem Sequence prediction for high-dimensional input sequences.
method Three models based on Generative Stochastic Networks (GSN) for unsupervised sequence learning.
result GSNs provide evidence as a viable framework for complex sequential data.
The paper revisits expected signatures in semimartingale models, providing new formulae and simplifying complexity.
problem Computing expected signatures in semimartingale models.
method Revisits and provides new formulae for computing expected signatures in a general semimartingale setting.
result Log-transform of expected signatures simplifies complexity, leading to signature cumulants.
Defines knot signature invariant using G-signature theorem.
problem No specific problem stated; focuses on knot theory.
method Uses G-signature theorem to define knot invariant.
result Defines an invariant for strongly invertible knots.
Deep signature/log-signature FBSDE algorithm improves accuracy and training time.
problem Solving FBSDEs with state and path dependent features.
method Incorporates deep signature/log-signature transformation into RNN model.
result Improves accuracy and training time compared to existing methods.
A well-known property of the signature of closed oriented 4n-dimensional manifolds is Novikov additivity, which states that if a manifold is split into two manifolds with boundary along an oriented smooth hypersurface, then the signature of the original manifold equals the sum of the signatures of the resulting manifol…
Maximum Levine-Tristram signature of torus knots follows a reduction formula.
problem Determining the maximum Levine-Tristram signature for torus knots.
method Proved a reduction formula analogous to Gordon-Litherland-Murasugi's classical signature result.
result Maximum Levine-Tristram signature of torus knots satisfies a reduction formula.
New findings on mesh group-planes validate Signature-inverse Theorem under specific conditions.
problem Invalidity of existing inverse theorems for mesh group-planes.
method Classification of three and five point meshes, analysis of joint invariant signatures.
result Valid conditions for the Signature-inverse Theorem in mesh group-planes.
Introduces flat discrete signatures for financial data analysis.
problem Representing financial data for machine learning without continuous transformation.
method Introduced flat discrete signatures and discrete signatures, generalizing flat discrete signatures.
result Flat discrete signatures can represent quadratic variation relevant in finance.
Method extracts cancer signatures from genome data, reducing noise and variability.
problem Identifying stable cancer signatures from noisy genomic data.
method Applied statistical risk models from finance to cancer genome data, using NMF.
result Extracted signatures have lower variability and improved stability.
This is a sequel to the paper "The signature package on Witt spaces, I. Index classes" by the same authors. In the first part we investigated, via a parametrix construction, the regularity properties of the signature operator on a stratified Witt pseudomanifold, proving, in particular, that one can define a K-homology …
We define the Analytical signature, the Hodge signature and the de Rham signature for a foliated manifold with boundary with foliation transverse to the boundary. We show that all these signatures coincide and a Hirzebruch formula is valid.
The paper examines the consistency of Lasso regression applied to signature analysis of time series data.
problem Consistency of Lasso regression in signature analysis of time series data.
method The paper studies the consistency of Lasso regression applied to signature analysis of time series data, both theoretically and numerically.
result The Lasso regression is consistent both asymptotically and in finite sample for certain types of time series and processes.
Study signatures of torus links and their cores using Neumann's equivariant signatures and Hirzebruch's formula.
problem Computing signatures of torus links and their cores.
method Use Neumann's equivariant signatures and rewrite Hirzebruch's formula for torus links (without cores) in terms of integral points in a parallelogram.
result Rewritten Hirzebruch's formula for torus links with cores using integral points in a parallelogram.