Segmentation and recognition of Chinese bank check amounts

Yu, Mali; Kwok, P.C.K.; Leung, C. H.; Tse, K. W.

doi:10.1007/pl00013562

Cited by 19 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…12(a) was a strong indicator of the similarity of the writing styles of different writers. For example, all the distances of ID pairs (31,33), (32,34), and (39,40) were small, while the corresponding writing styles for those pairs were quite similar, as observed from the handwritten text lines, which demonstrates that the learned writer code indeed carries the writer information. Table VIII shows CER comparison of different language models.…”

Section: ) Visualization Analysis For Writer Codementioning

confidence: 62%

Writer-aware CNN for parsimonious HMM-based offline handwritten Chinese text recognition

Wang

2020

Pattern Recognition

View full text Add to dashboard Cite

Recently, the hybrid convolutional neural network hidden Markov model (CNN-HMM) has been introduced for offline handwritten Chinese text recognition (HCTR) and has achieved state-of-the-art performance. However, modeling each of the large vocabulary of Chinese characters with a uniform and fixed number of hidden states requires high memory and computational costs and makes the tens of thousands of HMM state classes confusing. Another key issue of CNN-HMM for HCTR is the diversified writing style, which leads to model strain and a significant performance decline for specific writers. To address these issues, we propose a writer-aware CNN based on parsimonious HMM (WCNN-PHMM). First, PHMM is designed using a data-driven state-tying algorithm to greatly reduce the total number of HMM states, which not only yields a compact CNN by state sharing of the same or similar radicals among different Chinese characters but also improves the recognition accuracy due to the more accurate modeling of tied states and the lower confusion among them. Second, WCNN integrates each convolutional layer with one adaptive layer fed by a writer-dependent vector, namely, the writer code, to extract the irrelevant variability in writer information to improve recognition performance.The parameters of writer-adaptive layers are jointly optimized with other network parameters in the training stage, while a multiple-pass decoding strategy is adopted to learn the writer code and generate recognition results. Validated on the ICDAR 2013 competition of CASIA-HWDB database, the more compact WCNN-PHMM of a 7360-class vocabulary can achieve a relative character error rate (CER) reduction of 16.6% over the conventional CNN-HMM without considering language modeling. By adopting a powerful hybrid language model (N-gram language model and recurrent neural network language model), the CER of WCNN-PHMM is reduced to 3.17%. Moreover, the state-tying results of PHMM explicitly show the information sharing among similar characters and the confusion reduction of tied state classes. Finally, we visualize the learned writer codes and demonstrate the strong relationship with the writing styles of different writers. To the best of our knowledge, WCNN-PHMM yields the 2 best results on the ICDAR 2013 competition set, demonstrating its power when enlarging the size of the character vocabulary. Index TermsOffline handwritten Chinese text recognition, writer-aware CNN, parsimonious HMM, state tying, adaptation, hybrid language model.

show abstract

Section: ) Visualization Analysis For Writer Codementioning

confidence: 62%

Writer-aware CNN for parsimonious HMM-based offline handwritten Chinese text recognition

Wang

2020

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Recognition-based segmentation algorithms [Casey and Nagy 1982;Kimura et al 1993aKimura et al , 1993bNohl et al 1992;Yu et al 2001;Bulacu et al 2009] consist of two steps: generation of segmentation hypotheses and choice of the best hypothesis. In this method, recognition is done iteratively according to the hypothesis generating the most satisfactory recognition score.…”

Section: Recognition-based Segmentationmentioning

confidence: 99%

Bangla Handwritten Character Segmentation Using Structural Features

Bhowmik

Parui

Roy

et al. 2016

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

In this article, we propose a new framework for segmentation of Bangla handwritten word images into meaningful individual symbols or pseudo-characters. Existing segmentation algorithms are not usually treated as a classification problem. However, in the present study, the segmentation algorithm is looked upon as a two-class supervised classification problem. The method employs an SVM classifier to select the segmentation points on the word image on the basis of various structural features. For training of the SVM classifier, an unannotated training set is prepared first using candidate segmenting points. The training set is then clustered, and each cluster is labeled manually with minimal manual intervention. A semi-automatic bootstrapping technique is also employed to enlarge the training set from new samples. The overall architecture describes a basic step toward building an annotation system for the segmentation problem, which has not so far been investigated. The experimental results show that our segmentation method is quite efficient in segmenting not only word images but also handwritten texts. As a part of this work, a database of Bangla handwritten word images has also been developed. Considering our data collection method and a statistical analysis of our lexicon set, we claim that the relevant characteristics of an ideal lexicon set are present in our handwritten word image database.

show abstract

“…A check also has a signature field to be filled by the payee or on his or her behalf. Much progress has already been made in automatic check processing from checks written in different languages and countries, such as English (e.g., [3] ), French (e.g., [4,5]), Swiss (e.g., [6]), Chinese (e.g., [7][8][9]), Brazilian (e.g., [10,11]), and Indian (e.g., [12,13]), and there are many commercial products already available for automated check processing (e.g., A2iA, Mitek, Parascript, and Soft-Pro, cf. [14]); however, automatic processing of Arabic checks is still an ongoing research problem.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Rule-Based and Machine Learning System for Arabic Check Courtesy Amount Recognition

Ahmad

2023

Sensors

View full text Add to dashboard Cite

Courtesy amount recognition from bank checks is an important application of pattern recognition. Although much progress has been made on isolated digit recognition for Indian digits, there is no work reported in the literature on courtesy amount recognition for Arabic checks using Indian digits. Arabic check courtesy amount recognition comes with its own unique challenges that are not seen in isolated digit recognition tasks and, accordingly, need specific approaches to deal with them. This paper presents an end-to-end system for courtesy amount recognition starting from check images as input to recognizing amounts as a sequence of digits. The system is a hybrid system, combining rule-based modules as well as machine learning modules. For the amount recognition system, both segmentation-based and segmentation-free approaches were investigated and compared. We evaluated our system on the CENPARMI dataset of real bank checks in Arabic. We achieve 67.4% accuracy at the amount level and 87.15% accuracy at the digit level on the test set consisting of 626 check images. The results are presented with detailed analysis, and some possible future work is identified. This work can be used as a baseline to benchmark future research in Arabic check courtesy amount recognition.

show abstract

Segmentation and recognition of Chinese bank check amounts

Cited by 19 publications

References 23 publications

Writer-aware CNN for parsimonious HMM-based offline handwritten Chinese text recognition

Writer-aware CNN for parsimonious HMM-based offline handwritten Chinese text recognition

Bangla Handwritten Character Segmentation Using Structural Features

A Hybrid Rule-Based and Machine Learning System for Arabic Check Courtesy Amount Recognition

Contact Info

Product

Resources

About