Search Results (55)

Stochastic Computing has attracted extensive attention in the deployment of neural networks at the edge due to its low hardware cost and high fault tolerance. However, traditional stochastic computing requires a long random bit stream to achieve sufficient numerical precision. The long bit stream, in turn, increases the network inference time, hardware cost, and power consumption, which limits its application in executing tasks such as handwritten recognition, speech recognition, image processing, and image classification at the near-sensor end. To realize high-energy-efficiency and low-cost hardware neural networks at the near-sensor end, a hardware optimization design of convolutional neural networks based on the hybrid encoding of deterministic encoding and binary encoding is proposed. By transforming the output signals from the sensor into deterministic encoding and co-optimizing the network training process, a low-cost and high-energy-efficiency convolution operation network is achieved with a shorter bit stream input. This network can achieve good recognition performance with an extremely short bit stream, significantly reducing the system’s latency and energy consumption. Compared with traditional stochastic computing networks, this network shortens the bit stream length by 64 times without affecting the recognition rate, achieving a recognition rate of 99% with a 2-bit input. Compared with the traditional 2-bit stochastic computing scheme, the area is reduced by 44.98%, the power consumption is reduced by 60.47%, and the energy efficiency is increased by 12 times. Compared with the traditional 256-bit stochastic computing scheme, the area is reduced by 82.87%, and the energy efficiency is increased by 1947 times. These comparative results demonstrate that this work has significant advantages in executing tasks such as image classification at the near-sensor end and edge devices. Full article

Many people admire the Japanese language and culture, but mastering the language’s writing system, particularly handwritten kanji, presents a significant challenge. Furthermore, translating historical manuscripts containing archaic or rare kanji requires specialized expertise. To address this, we designed a new model for handwritten kanji recognition based on the concept of cross-language transfer learning using a Preact ResNet-18 architecture. The model was pretrained in a Chinese dataset and subsequently fine-tuned in a Japanese dataset. We also adapted and evaluated two fine-tuning strategies: unfreezing only the last layer and unfreezing all the layers during fine-tuning. During the implementation of our training algorithms, we trained a model with the CASIA-HWDB dataset with handwritten Chinese characters and used its weights to initialize models that were fine-tuned with a Kuzushiji-Kanji dataset that consists of Japanese handwritten kanji. We investigated the effectiveness of the developed model when solving a multiclass classification task for three subsets with the one hundred fifty, two hundred, and three hundred most-sampled classes and showed an improvement in the recognition accuracy and an enhancement in a number of recognizable kanji with the proposed model compared to those of the existing methods. Our best model achieved 97.94% accuracy for 150 kanji, exceeding the previous SOTA result by 1.51%, while our best model for 300 kanji achieved 97.62% accuracy (exceeding the 150-kanji SOTA accuracy by 1.19% while doubling the class count). This confirms the effectiveness of our proposed model and establishes new benchmarks in handwritten kanji recognition, both in terms of accuracy and the number of recognizable kanji. Full article

WO₃-based electrochemical transistors (ECTs) are recognized as candidates for three-terminal memristors due to their high on–off ratio, long retention time, and rapid switching speed. However, their patterned fabrication often relies on complex vacuum systems or extreme processing conditions, hindering cost-effective scalability. Here, we developed a novel wet etching technique integrated with sol–gel-derived WO₃ channels, enabling ambient-air fabrication of Nafion-WO₃ ECTs. The wet-etched devices achieve an on–off ratio of ~10⁵, surpassing unetched and dry-etched counterparts by orders of magnitude. Furthermore, they exhibit exceptional paired-pulse facilitation and long-term stability, maintaining 12 distinct conductance states for 10³ s, and an on–off ratio of ~10² over 25 read–write cycles. XPS result shows higher W⁵⁺ content and M-O-H bond proportion for wet-etched devices, revealing an optimized interface, with enhanced H⁺ injection efficiency. The simulated artificial neural network using this wet-etched ECT shows ~97% recognition accuracy for handwritten numerals. This approach offers a novel patterning strategy for developing cost-effective, high-performance neuromorphic devices. Full article

A series of studies and research have shown the existence of a link between handwriting and a person’s personality traits. There are numerous fields that require a psychological assessment of individuals, where there is a need to determine personality traits in a faster and more efficient manner than that based on classic questionnaires or graphological analysis. The development of image processing and recognition algorithms based on machine learning and deep neural networks has led to a series of applications in the field of graphology. In the present study, a system for automatically extracting handwriting characteristics from written documents and correlating them with Myers–Briggs type indicator is implemented. The system has an architecture composed of three levels, the main level being formed by four convolutional neural networks. To train the networks, a database with different types of handwriting was created. The experimental results show an accuracy ranging between 89% and 96% for handwritten features’ recognition and results ranging between 83% and 91% in determining Myers–Briggs indicators. Full article

Video location prediction for handwritten digits presents unique challenges in computer vision due to the complex spatiotemporal dependencies and the need to maintain digit legibility across predicted frames, while existing deep learning-based video prediction models have shown promise, they often struggle with preserving local details and typically achieve clear predictions for only a limited number of frames. In this paper, we present a novel video location prediction model based on Convolutional Gated Recurrent Units (ConvGRU) that specifically addresses these challenges in the context of handwritten digit sequences. Our approach introduces three key innovations. Firstly, we introduce a specialized decoupling model using modified Generative Adversarial Networks (GANs) that effectively separates background and foreground information, significantly improving prediction accuracy. Secondly, we introduce an enhanced ConvGRU architecture that replaces traditional linear operations with convolutional operations in the gating mechanism, substantially reducing spatiotemporal information loss. Finally, we introduce an optimized parameter-tuning strategy that ensures continuous feature transmission while maintaining computational efficiency. Extensive experiments on both the MNIST dataset and custom mobile datasets demonstrate the effectiveness of our approach. Our model achieves a structural similarity index of 0.913 between predicted and actual sequences, surpassing current state-of-the-art methods by 1.2%. Furthermore, we demonstrate superior performance in long-term prediction stability, with consistent accuracy maintained across extended sequences. Notably, our model reduces training time by 9.5% compared to existing approaches while maintaining higher prediction accuracy. These results establish new benchmarks for handwritten digit video prediction and provide practical solutions for real-world applications in digital education, document processing, and real-time handwriting recognition systems. Full article

Using biometric data for user authentication is a frequently addressed subject within the context of computer security. Despite significant advancements in technology, handwriting analysis continues to be the most common method of identifying individuals. There are two distinct types of handwriting recognition: offline and online. The first type involves the identification and interpretation of handwritten content obtained from an image, such as digitized human handwriting. The latter pertains to the identification of handwriting derived from digital writing performed on a touchpad or touchscreen. This research paper provides a comprehensive overview of the proposed apparatus specifically developed for collecting handwritten data. The acquisition of biometric information is conducted using a touchscreen device equipped with a variety of integrated and external sensors. In addition to acquiring signatures, the sensor-fusion-based configuration accumulates handwritten phrases, words, and individual letters to facilitate online user authentication. The proposed system can collect an extensive array of data. Specifically, it is possible to capture data related to stylus pressure, magnetometer readings, images, videos, and audio signals associated with handwriting executed on a tablet device. The study incorporates instances of gathered records, providing a graphical representation of the variation in handwriting among distinct users. The data obtained were additionally analyzed with regard to inter-person variability, intra-person variability, and classification potential. Initial findings from a limited sample of users demonstrate favorable results, intending to gather data from a more extensive user base. Full article

Conductive hydrogels are promising active materials for wearable flexible electronics, yet it is still challenging to fabricate conductive hydrogels with good environmental stability and electrical properties. In this work, a conductive MXene/LiCl/poly(sulfobetaine methacrylate) hydrogel system was successfully prepared with an impressive conductivity of 12.2 S/m. Interestingly, the synergistic effect of MXene and a lithium bond can significantly accelerate the polymerization process, forming the conductive hydrogel within 1 min. In addition, adding LiCl to the hydrogel not only significantly increases its water retention ability, but also enhances its conductivity, both of which are important for practical applications. The flexible strain sensors based on the as-prepared hydrogel have demonstrated excellent monitoring ability for human joint motion, pulse, and electromyographic signals. More importantly, based on machine learning image recognition technology, the handwritten letter recognition system displayed a high accuracy rate of 93.5%. This work demonstrates the excellent comprehensive performance of MXene-based hydrogels in health monitoring and image recognition and shows potential applications in human–machine interfaces and artificial intelligence. Full article

This paper introduces a novel capacitive sensor array designed for tactile perception applications. Utilizing an all-in-one inkjet deposition printing process, the sensor array exhibited exceptional flexibility and accuracy. With a resolution of up to 32.7 dpi, the sensor array was capable of capturing the fine details of touch inputs, making it suitable for applications requiring high spatial resolution. The design incorporates two multiplexers to achieve a scanning rate of 100 Hz, ensuring the rapid and responsive data acquisition that is essential for real-time feedback in interactive applications, such as gesture recognition and haptic interfaces. To evaluate the performance of the capacitive sensor array, an experiment that involved handwritten number recognition was conducted. The results demonstrated that the sensor accurately captured fingertip inputs with a high precision. When combined with an Auxiliary Classifier Generative Adversarial Network (ACGAN) algorithm, the sensor system achieved a recognition accuracy of 98% for various handwritten numbers from “0” to “9”. These results show the potential of the capacitive sensor array for advanced human–computer interaction applications. Full article

Text recognition is an important area of the pattern recognition field. Natural language processing (NLP) and pattern recognition have been utilized efficiently in script recognition. Much research has been conducted on handwritten script recognition. However, the research on the Arabic language for handwritten text recognition received little attention compared with other languages. Therefore, it is crucial to develop a new model that can recognize Arabic handwritten text. Most of the existing models used to acknowledge Arabic text are based on traditional machine learning techniques. Therefore, we implemented a new model using deep machine learning techniques by integrating two deep neural networks. In the new model, the architecture of the Residual Network (ResNet) model is used to extract features from raw images. Then, the Bidirectional Long Short-Term Memory (BiLSTM) and connectionist temporal classification (CTC) are used for sequence modeling. Our system improved the recognition rate of Arabic handwritten text compared to other models of a similar type with a character error rate of 13.2% and word error rate of 27.31%. In conclusion, the domain of Arabic handwritten recognition is advancing swiftly with the use of sophisticated deep learning methods. Full article

Named entity recognition is a critical task in the electronic medical record management system for rehabilitation robots. Handwritten documents often contain spelling errors and illegible handwriting, and healthcare professionals frequently use different terminologies. These issues adversely affect the robot’s judgment and precise operations. Additionally, the same entity can have different meanings in various contexts, leading to category inconsistencies, which further increase the system’s complexity. To address these challenges, a novel medical entity recognition algorithm for Chinese electronic medical records is developed to enhance the processing and understanding capabilities of rehabilitation robots for patient data. This algorithm is based on a fusion classification strategy. Specifically, a preprocessing strategy is proposed according to clinical medical knowledge, which includes redefining entities, removing outliers, and eliminating invalid characters. Subsequently, a medical entity recognition model is developed to identify Chinese electronic medical records, thereby enhancing the data analysis capabilities of rehabilitation robots. To extract semantic information, the ALBERT network is utilized, and BILSTM and MHA networks are combined to capture the dependency relationships between words, overcoming the problem of different meanings for the same entity in different contexts. The CRF network is employed to determine the boundaries of different entities. The research results indicate that the proposed model significantly enhances the recognition accuracy of electronic medical texts by rehabilitation robots, particularly in accurately identifying entities and handling terminology diversity and contextual differences. This model effectively addresses the key challenges faced by rehabilitation robots in processing Chinese electronic medical texts, and holds important theoretical and practical value. Full article

Arabic handwriting recognition and conversion are crucial for financial operations, particularly for processing handwritten amounts on cheques and financial documents. Compared to other languages, research in this area is relatively limited, especially concerning Arabic. This study introduces an innovative AI-driven method for simultaneously recognizing and converting Arabic handwritten legal amounts into numerical courtesy forms. The framework consists of four key stages. First, a new dataset of Arabic legal amounts in handwritten form (“.png” image format) is collected and labeled by natives. Second, a YOLO-based AI detector extracts individual legal amount words from the entire input sentence images. Third, a robust hybrid classification model is developed, sequentially combining ensemble Convolutional Neural Networks (CNNs) with a Vision Transformer (ViT) to improve the prediction accuracy of single Arabic words. Finally, a novel conversion algorithm transforms the predicted Arabic legal amounts into digital courtesy forms. The framework’s performance is fine-tuned and assessed using 5-fold cross-validation tests on the proposed novel dataset, achieving a word level detection accuracy of 98.6% and a recognition accuracy of 99.02% at the classification stage. The conversion process yields an overall accuracy of 90%, with an inference time of 4.5 s per sentence image. These results demonstrate promising potential for practical implementation in diverse Arabic financial systems. Full article

Handwritten Text Recognition (HTR) is essential for digitizing historical documents in different kinds of archives. In this study, we introduce a hybrid form archive written in French: the Belfort civil registers of births. The digitization of these historical documents is challenging due to their unique characteristics such as writing style variations, overlapped characters and words, and marginal annotations. The objective of this survey paper is to summarize research on handwritten text documents and provide research directions toward effectively transcribing this French dataset. To achieve this goal, we presented a brief survey of several modern and historical HTR offline systems of different international languages, and the top state-of-the-art contributions reported of the French language specifically. The survey classifies the HTR systems based on techniques employed, datasets used, publication years, and the level of recognition. Furthermore, an analysis of the systems’ accuracies is presented, highlighting the best-performing approach. We have also showcased the performance of some HTR commercial systems. In addition, this paper presents a summarization of the HTR datasets that publicly available, especially those identified as benchmark datasets in the International Conference on Document Analysis and Recognition (ICDAR) and the International Conference on Frontiers in Handwriting Recognition (ICFHR) competitions. This paper, therefore, presents updated state-of-the-art research in HTR and highlights new directions in the research field. Full article

Offline handwritten text recognition (HTR) is a long-standing research project for a wide range of applications, including assisting visually impaired users, humans and robot interactions, and the automatic entry of business documents. However, due to variations in writing styles, visual similarities between different characters, overlap between characters, and source document noise, designing an accurate and flexible HTR system is challenging. The problem becomes serious when the algorithm has a low learning capacity and when the text used is complex and has a lot of characters in the writing system, such as Ethiopic script. In this paper, we propose a new model that recognizes offline handwritten Ethiopic text using a gated convolution and stacked self-attention encoder–decoder network. The proposed model has a feature extraction layer, an encoder layer, and a decoder layer. The feature extraction layer extracts high-dimensional invariant feature maps from the input handwritten image. Using the extracted feature maps, the encoder and decoder layers transcribe the corresponding text. For the training and testing of the proposed model, we prepare an offline handwritten Ethiopic text-line dataset (HETD) with 2800 samples and a handwritten Ethiopic word dataset (HEWD) with 10,540 samples obtained from 250 volunteers. The experiment results of the proposed model on HETD show a 9.17 and 13.11 Character Error Rate (CER) and Word Error Rate (WER), respectively. However, the model on HEWD shows an 8.22 and 9.17 CER and WER, respectively. These results and the prepared datasets will be used as a baseline for future research. Full article

Handwritten digit recognition has been used in many consumer electronic devices for a long time. However, we found that the recognition system used in current consumer electronics is sensitive to image or character rotations. To address this problem, this study builds a low-cost and light computation consumption handwritten digit recognition system. A Principal Component Analysis (PCA)-based logistic regression classifier is presented, which is able to provide a certain degree of robustness in the digit subject to rotations. To validate the effectiveness of the developed image recognition algorithm, the popular MNIST dataset is used to conduct performance evaluations. Compared to other popular classifiers installed in MATLAB, the proposed method is able to achieve better prediction results with a smaller model size, which is 18.5% better than the traditional logistic regression. Finally, real-time experiments are conducted to verify the efficiency of the presented method, showing that the proposed system is successfully able to classify the rotated handwritten digit. Full article

Optical character recognition systems for Malayalam handwritten documents have become an open research area. A major hindrance in this research is the unavailability of a benchmark database. Therefore, a new database of 402 Malayalam handwritten document images and ground truth images of 7535 text lines is developed for the implementation of the proposed technique. This paper proposes a technique for the extraction of text lines from handwritten documents in the Malayalam language, specifically based on the handwriting of the writer. Text lines are extracted based on horizontal and vertical projection values, the size of the handwritten characters, the height of the text lines and the curved nature of the Malayalam alphabet. The proposed technique is able to overcome incorrect segmentation due to the presence of characters written with spaces above or below other characters and the overlapping of lines because of ascenders and descenders. The performance of the proposed method for text line extraction is quantitatively evaluated using the MatchScore value metric and is found to be 85.507%. The recognition accuracy, detection rate and F-measure of the proposed method are found to be 99.39%, 85.5% and 91.92%, respectively. It is experimentally verified that the proposed method outperforms some of the existing language-independent text line extraction algorithms. Full article