Deep Convolutional Neural Networks Based on Knowledge Distillation for Offline Handwritten Chinese Character Recognition

The task of handwritten Chinese character recognition is one of the most challenging areas of human handwriting classification. The main reason for this is related to the writing system itself which encompasses thousands of characters, coupled with high levels of diversity in personal writing styles and attributes. Much of the existing work for both online and off-line handwritten Chinese character recognition has focused on methods which employ feature extraction and segmentation steps. The preprocessed data from these steps form the basis for the subsequent classification and recognition phases. This paper proposes an approach for handwritten Chinese character recognition and classification using only an image alignment technique and does not require the aforementioned steps. Rather than extracting features from the image, which often means building models from very large training data, the proposed method instead uses the mean image transformations as a basis for model building. The use of an image-only model means that no subjective tuning of the feature extraction is required. In addition by employing a fuzzy-entropy-based metric, the work also entails improved ability to model different types of uncertainty. The classifier is a simple distance-based nearest neighbour classification system based on template matching. The approach is applied to a publicly available real-world database of handwritten Chinese characters and demonstrates that it can achieve high classification accuracy and is robust in the presence of noise.

Handwritten Chinese character recognition (HCCR) is an important research field of pattern recognition, which has attracted extensive studies during the past decades. Recently convolutional neural network (CNN) based methods have achieved the state-of-the-art performance for handwritten Chinese character recognition. Nevertheless, handwritten Chinese character recognition is still limited to be effectively used in the actual environment due to the large-scale vocabulary and great diversity of handwriting style. In this paper, we constructed a handwritten Chinese character recognition service based on convolutional neural network, which tries to make effective use of handwritten based printed fonts and existing handwritten database. At the same time, the service can effectively collect more handwritten data to expand the training dataset, which makes it easy to adapt to the new handwriting styles. Meanwhile, We propose a multi-level recognition theory applied to online handwritten Chinese character recognition, which may improve the accuracy of handwritten Chinese character recognition and break the limitations of handwritten Chinese character recognition by identifying the structure of Chinese characters and possible stroke orders firstly. Furthermore, we try to apply the method of online character recognition to the offline character recognition based on the basic writing rules.

Offline handwritten chinese character recognition (HCCR) is one of means for quick text input and it has a great demand in the area of file recognition, form processing, machine translation and office automation. However it still is a difficult task for handwritten chinese character recognition to put into practical use because of its large stroke change, writing anomaly, and no stroke ranking information can get, etc. al. An efficient classifier occupies very important position for increasing offline HCCR ratio. Support vector machines offer a theoretically well-founded approach to automated learning of pattern classifiers for mining labeled data sets. But as we know, the performance of SVMs largely depend on the kernel function, different kernel function will produce different SVMs, and may result in different performance. However, there are no theories concerning how to choose good kernel functions based on practical using problem. In this paper we make use of the basic properties of Mercer kernel to construct a hybrid kernel from the existing common kernel, and to find the unknown parameters of the hybrid kernel in data-dependent way by minimizing the upper bound of the VC dimension of the set of functions. Our experiment results show that the proposed method is efficient compared with other classifier for handwritten Chinese character recognition.

Recognition of printed and handwritten text (characters and digits) has been a challenge for many researchers in the field of Document Image Analysis for almost thirty years. Many existing pattern recognition methods have been used and new ones have been proposed. Despite the satisfactory results obtained in recognizing printed text, recognition of handwritten text is still an open research. This paper presents a method for off-line recognition of handwritten Chinese characters. Each character is described by six structural features extracted using the dominant point method. The goodness of each feature is determined by a method called stroke probability. The classification was performed by the Fuzzy ARTMAP neural network within the context of the one-class problem approach. Evaluation of the proposed method was determined using database of 900 characters (an average of 40 samples/character). The average mean recognition rate was approximately 94%.

This paper presents a methodology for off-line handwritten Chinese character recognition based on mergence of consecutive segments of adaptive duration. The handwritten Chinese character string is partitioned into a sequence of consecutive segments, which are combined to implement dissimilarity evaluation within a sliding window whose durations are determined adaptively by the integration of shapes and context of evaluations. The average stroke width is estimated for the handwritten Chinese character string, and a set of candidate character segmentation boundaries is found by using the integration of pixel and stroke features. The final decisions on segmentation and recognition are made under minimal arithmetical mean dissimilarities. Experiments proved that the proposed approach of adaptive duration outperforms the method of fixed duration, and is very effective for the recognition of overlapped, broken, touched, loosely configured Chinese characters.

Based on the rough set theory and variable granular theorem, a kind of decision information system of off-line handwritten Chinese character recognition is constructed. The performance index entropy in this decision information system is defined in this paper. According to the definition of attribute relative significance, the feature attributes are classified, that the representation of feature attributes in single layer and single granularity become multiple layers and multiple granularities, and a hierarchical reduction approach is designed. The weak points of the single granularity that fixed and reduction is not fine are made up. Based on the D-S evidence theory, the decision rules after reduction are fused, so that the recognition rate can be improved. The experiment results show that the method is feasible and effective.

Recognition of handwritten Chinese characters by elastic matching

In recent years, the transformer model has been widely used in computer-vision tasks and has achieved impressive results. Unfortunately, these transformer-based models have the common drawback of having many parameters and a large memory footprint, causing them to be difficult to deploy on mobiles as lightweight convolutional neural networks. To address these issues, a Vision Transformer (ViT) model, named the lightweight Vision Transformer (LW-ViT) model, is proposed to reduce the complexity of the transformer-based model. The model is applied to offline handwritten Chinese character recognition. The design of the LW-ViT model is inspired by MobileViT. The lightweight ViT model reduces the number of parameters and FLOPs by reducing the number of transformer blocks and the MV2 layer based on the overall framework of the MobileViT model. The number of parameters and FLOPs for the LW-ViT model was 0.48 million and 0.22 G, respectively, and it ultimately achieved a high recognition accuracy of 95.8% on the dataset. Furthermore, compared to the MobileViT model, the number of parameters was reduced by 53.8%, and the FLOPs were reduced by 18.5%. The experimental results show that the LW-ViT model has a low number of parameters, proving the correctness and feasibility of the proposed model.

This paper proposes an approach combining the set of Krawtchouk moments and HMMs (Hidden Markov Models) for unconstrained offline handwritten Chinese character recognition. The Krawtchouk moments can be effectively used as pattern features in analysis of two-dimensional images. Since the basis set is orthogonal in the discrete domain of the image coordinate space, the implementation of Krawtchouk moments doesn't involve any numerical approximation or coordinate transformation. This property makes Krawtchouk moments superior to conventional, more continuous moments such as Legendre moments and Zernike moments. In the field of character recognition, HMMs architecture has been used widely because of its strong adaptability to written distortion and variability. In this paper, Krawtchouk moments and HMMs are combined to recognize unconstrained offline handwritten Chinese amount in words. Experiments show that the average recognition of Krawtchouk is higher than Zernike and Legendre moments within the HMM framework.

Offline handwritten Chinese character recognition is a very hard pattern-recognition problem of considerable practical importance. Two popular approaches are to extract features holistically from the character image or to decompose characters structurally into component parts---usually strokes. Here we take a novel approach, that of decomposing into radicals on the basis of image information (i.e., without first decomposing into strokes). During training, 60 examples of each radical were represented by "landmark" points, labeled semiautomatically, with radicals in different characteristic positions treated as distinctly different radicals. Kernel principal-component analysis then captured the main (nonlinear) variations around the mean radical. During the recognition, the dynamic tunneling algorithm was used to search for optimal shape parameters in terms of chamfer distance minimization. Considering character composition as a Markov process in which up to four radicals are combined in some assumed sequential order, we can recognize complete, hierarchically-composed characters by using the Viterbi algorithm. This gave a character recognition rate of 93.5% characters correct (writer-independent) on a test set of 430,800 characters from 2,154 character classes composed of 200 radical categories, which is comparable to the best reported results in the literature. Although the initial semiautomatic landmark labeling is time consuming, the decomposition approach is theoretically well-motivated and allows the different sources of variability in Chinese handwriting to be handled separately and by the most appropriate means--either learned from example data or incorporated as prior knowledge. Hence, high generalizability is obtained from small amounts of training data, and only simple prior knowledge needs to be incorporated, thus promising robust recognition performance. As such, there is very considerable potential for further development and improvement in the direction of larger character sets and less constrained writing conditions.

Due to the various individual handwriting styles and diverse structures of Chinese characters, it is rather intricate to recognize handwritten Chinese characters precisely. In this paper, a muti-stage system that combines a Differentiable Binarization Network (DBNet) for text detection and Scene Text Recognition with a Single Visual Model (SVTR) for effective character recognition is developed, aiming to offer a potential solution for correct identification of handwritten Chinese characters in real-world scenarios. More specifically, the proposed system utilized the CASIA-HWDB2.x dataset from the Institute of Automation of the Chinese Academy of Sciences to train text detection and recognition models. For the detection, the Differentiable Binarization method in the Head Network applies a dynamic threshold map for text-background differentiation. On top of the SVTR employed as a recognition module, this research proposed a performance-optimized PP-LCNet architecture and the Guided Training of Continuous Time-Series Classifiers (GTC) with TextConAug, which is a data augmentation strategy to accommodate real-world scenarios. Briefly, DBNet and SVTR are integrated to form an end-to-end system. The output of DBNet after undergoing cropping and direction classifier, guides SVTR for a comprehensive system, ensuring seamless detection and recognition of handwritten Chinese characters. Experimental results indicate that this system achieves a promising performance and can provide accurate information on handwritten Chinese characters.

This paper proposes a hidden Markov mesh random field (HMMRF)-based stochastic model for off-line handwritten Chinese characters recognition using statistical observation sequences embedded in the strokes of a character. Due to the great amount of Chinese characters and many different writing styles or variations, the recognition of handwritten Chinese characters becomes more difficult and challenging than any other character recognition. In our approach, a new framework based on HMMRF model is put forward at first. The estimation of model parameters and state sequence decoding algorithms are also discussed later. Besides the mathematical model and corresponding issues, nonlinear shape normalization scheme that modifies the distortion and adjusts the correlation of strokes is applied. Two types of stroke-based features are extracted for the rough classification and observation sequence respectively. Experimental results on isolated handwritten Chinese characters demonstrate the effectiveness of our approach.

Chinese characters are constructed by basic strokes based on structural rules. In handwritten characters, the shapes of the strokes may vary to some extent, but the spatial relations and geometric configurations of the strokes are usually maintained. Therefore these spatial relations and configurations could be regarded as invariant features and could be used in the recognition of handwritten Chinese characters. In this paper, we investigate the structural knowledge in Chinese characters and propose the stroke spatial relationship representation (SSRR) to describe Chinese characters. An On-Line Chinese Character Recognition (OLCCR) method using the SSRR is also presented. With SSRR, each character is processed and is represented by an attribute graph. The process of character recognition is thereby transformed into a graph matching problem. After careful analysis, the basic spatial relationship between strokes can be characterized into five classes. A bitwise representation is adopted in the design of the data structure to reduce storage requirements and to speed up character matching. The strategy of hierarchical search in the preclassification improves the recognition speed. Basically, the attribute graph model is a generalized character representation that provides a useful and convenient representation for newly added characters in an OLCCR system with automatic learning capability. The significance of the structural approach of character recognition using spatial relationships is analyzed and is proved by experiments. Realistic testing is provided to show the effectiveness of the proposed method.

Self-generation Voting Based Method for Handwritten Chinese Character Recognition

Hierarchical attributed graph representation and recognition of handwritten chinese characters