Handwriting Recognition in Free Space Using WIMU-Based Hand Motion Analysis

Patil, Shashidhar; Kim, Dubeom; Park, Seong Sill; Chai, Young Ho

doi:10.1155/2016/3692876

Cited by 19 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worthwhile to notice that our results were obtained using a proprietary database focused on the handwriting recognition task. Furthermore, the results reported in [4,14,19,25,40] used 26, 26, 10, 12, and 12 different classes, respectively, in contrast to Patil et al [13] and the results of this study, where 36 different classes were used. In this context, it was noticed that 36 classes were used by Patil et al [13].…”

Section: Comparison With the State-of-the-artcontrasting

confidence: 76%

“…Furthermore, the results reported in [4,14,19,25,40] used 26, 26, 10, 12, and 12 different classes, respectively, in contrast to Patil et al [13] and the results of this study, where 36 different classes were used. In this context, it was noticed that 36 classes were used by Patil et al [13]. However, they reported only the results for two sets processed separately, obtaining an accuracy of 98.69% and 99.5% for letters (a-z) and digits (0-9), respectively.…”

Section: Comparison With the State-of-the-artcontrasting

confidence: 76%

“…To successfully carry out handwriting recognition, it is necessary to synchronize two main steps, the data acquisition, and identification processes. In the former, some works perform data acquisition by using a specially designed device [12][13][14][15]. Nevertheless, nowadays, many wearable devices such as smartphones or smartwatches are equipped with accelerometers, gyroscopes, magnetometers, and other wearables such as the shimmer3 IMU or the MYO armband.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Handwriting Recognition Based on 3D Accelerometer Data by Deep Learning

et al. 2022

View full text Add to dashboard Cite

Online handwriting recognition has been the subject of research for many years. Despite that, a limited number of practical applications are currently available. The widespread use of devices such as smartphones, smartwatches, and tablets has not been enough to convince the user to use pen-based interfaces. This implies that more research on the pen interface and recognition methods is still necessary. This paper proposes a handwritten character recognition system based on 3D accelerometer signal processing using Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM). First, a user wearing an MYO armband on the forearm writes a multi-stroke freestyle character on a touchpad by using the finger or a pen. Next, the 3D accelerometer signals generated during the writing process are fed into a CNN, LSTM, or CNN-LSTM network for recognition. The convolutional backbone obtains spatial features in order to feed an LSTM that extracts short-term temporal information. The system was evaluated on a proprietary dataset of 3D accelerometer data collected from multiple users with an armband device, corresponding to handwritten English lowercase letters (a–z) and digits (0–9) in a freestyle. The results show that the proposed system overcomes other systems from the state of the art by 0.53%.

show abstract

Section: Comparison With the State-of-the-artcontrasting

confidence: 76%

Section: Comparison With the State-of-the-artcontrasting

confidence: 76%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Handwriting Recognition Based on 3D Accelerometer Data by Deep Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In this section, we present the DTW similarity measure. DTW is a type of dynamic programming technique, a nonlinear warping algorithm that compares several temporally successive data points (i.e., without skipping any data) to determine the similarity of the two types of data [49,50]. The DTW algorithm is superior to the Euclidean distance method in measuring the similarity of time series data because it matches similar shapes even if there is a temporal difference between the data [51,52].…”

Section: Conventional Dtw Algorithm and Its Application Tomentioning

confidence: 99%

New Approach for Snow Cover Detection through Spectral Pattern Recognition with MODIS Data

et al. 2017

View full text Add to dashboard Cite

Snow cover plays an important role in climate and hydrology, at both global and regional scales. Most previous studies have used static threshold techniques to detect snow cover, which can lead to errors such as misclassification of snow and clouds, because the reflectance of snow cover exhibits variability and is affected by several factors. Therefore, we present a simple new algorithm for mapping snow cover from Moderate Resolution Imaging Spectroradiometer (MODIS) data using dynamic wavelength warping (DWW), which is based on dynamic time warping (DTW). DTW is a pattern recognition technique that is widely used in various fields such as human action recognition, anomaly detection, and clustering. Before performing DWW, we constructed 49 snow reflectance spectral libraries as reference data for various solar zenith angle and digital elevation model conditions using approximately 1.6 million sampled data. To verify the algorithm, we compared our results with the MODIS swath snow cover product (MOD10 L2). Producer's accuracy, user's accuracy, and overall accuracy values were 92.92%, 78.41%, and 92.24%, respectively, indicating good overall classification accuracy. The proposed algorithm is more useful for discriminating between snow cover and clouds than threshold techniques in some areas, such as those with a high viewing zenith angle.

show abstract

“…Writing styles can thereby be characterized by an information-rich multivariate time series (MTS). These datasets lay the foundation for HWR from pens with integrated sensors [17,23,68,71,84,105,109], a so far unsolved challenge in machine learning.…”

Section: Introductionmentioning

confidence: 99%

Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens

Ott¹,

Rügamer²,

Heublein³

et al. 2022

Preprint

View full text Add to dashboard Cite

Handwriting is one of the most frequently occurring patterns in everyday life and with it come challenging applications such as handwriting recognition (HWR), writer identification, and signature verification. In contrast to offline HWR that only uses spatial information (i.e., images), online HWR (OnHWR) uses richer spatio-temporal information (i.e., trajectory data or inertial data). While there exist many offline HWR datasets, there is only little data available for the development of OnHWR methods as it requires hardwareintegrated pens. This paper presents data and benchmark models for real-time sequence-to-sequence (seq2seq) learning and single character-based recognition. Our data is recorded by a sensor-enhanced ballpoint pen, yielding sensor data streams from triaxial accelerometers, a gyroscope, a magnetometer and a force sensor at 100 Hz. We propose a variety of datasets including equations and words for both the writer-dependent and writer-independent tasks. We provide an evaluation benchmark for seq2seq and single character-based HWR using recurrent and temporal convolutional networks and Transformers combined with a connectionist temporal classification (CTC) loss and cross entropy losses. Our methods do not resort to language or lexicon models.

show abstract

Handwriting Recognition in Free Space Using WIMU-Based Hand Motion Analysis

Cited by 19 publications

References 26 publications

Handwriting Recognition Based on 3D Accelerometer Data by Deep Learning

Handwriting Recognition Based on 3D Accelerometer Data by Deep Learning

New Approach for Snow Cover Detection through Spectral Pattern Recognition with MODIS Data

Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens

Contact Info

Product

Resources

About