In recent years, it has become a focus to make use of the address recognition technology to improve the performance of mail sorting machines. The research in the postal address recognition, which extends the context r...
详细信息
A novel method is proposed for text extraction from mail images with complex background. Firstly, wavelet transform and Laplacian operator are applied to generate the features of regions which are obtained by dividing...
详细信息
Mail sorting machines play an important role in postal automation. In this paper, we give a brief overview of mail sorting machines in China Post from a pattern recognition point of view. OCR techniques such as postco...
详细信息
This paper proposes a cost-sensitive transformation for improving handwritten address recognition performance by converting a general-purpose handwritten Chinese character recognition engine to a special-purpose one. ...
详细信息
ISBN:
(纸本)9781479952106
This paper proposes a cost-sensitive transformation for improving handwritten address recognition performance by converting a general-purpose handwritten Chinese character recognition engine to a special-purpose one. The class probabilities produced by character recognition engine for predicting a sample to candidate classes are transformed to the expected costs based on Naive Bayes optimal theoretical predictions firstly. And then candidate probabilities are reestimated based on the expected costs. Two general-purpose offline handwritten Chinese character recognition engines, PAIS and HAW, are tested in our experiments by applying them in handwritten Chinese address recognition system. 1822 live handwritten Chinese address images are tested with multiple cost matrices. Experimental results show that cost-sensitive transformation improves the recognition performance of general purpose recognition engines on handwritten Chinese address recognition.
Different recognizers may result in different mistakes when they are used to recognize a Chinese address. In this paper, we present a method of combining multiple Chinese address recognition outputs to improve Chinese...
详细信息
ISBN:
(纸本)9781479918065
Different recognizers may result in different mistakes when they are used to recognize a Chinese address. In this paper, we present a method of combining multiple Chinese address recognition outputs to improve Chinese address recognition accuracy. The method first employs multiple sequence alignment to generate a lattice of candidate hypotheses from multiple different recognizer outputs and then applies statistical language model to choose the maximum likelihood candidate sequence. Taking the maximum as the final decision, the performance of our method is superior, compared to the single recognizers and Miyao's method. The experiments on the address images of real envelopes demonstrate that the proposed method increases the character recognition accuracy rate from 95.80% to 98.38%, with 61.30% error reduction. Furthermore, the corrected sorting rate of an automatic mail sorting system increases from 84.11% to 93.72%.
To overcome the class imbalance problem in Chinese address recognition, we propose a cost-sensitive learning method for MQDF classifier. In the learning process, a cost vector is introduced to the discriminative learn...
详细信息
ISBN:
(纸本)9781479918065
To overcome the class imbalance problem in Chinese address recognition, we propose a cost-sensitive learning method for MQDF classifier. In the learning process, a cost vector is introduced to the discriminative learning process of MQDF, and minimization of misclassification cost is used as the convergence criteria. A cost-sensitive MQDF classifier (CMQDF) is then obtained, and it is integrated into a handwritten Chinese address recognition (HCAR) system to validate its effectiveness. The experimental results show that CMQDF is an effective cost-sensitive classifier for the class imbalance problem in HCAR system. Moreover, it enhances the reliability of the HCAR system.
We propose an efficient method for automatically extracting express waybills from parcel images, which is challenging due to varied resolution of parcel images, arbitrary direction of waybills and different informatio...
详细信息
ISBN:
(纸本)9781467399623
We propose an efficient method for automatically extracting express waybills from parcel images, which is challenging due to varied resolution of parcel images, arbitrary direction of waybills and different information filled by senders. To address these challenges, logo matching is employed to extract the waybills. We begin by extracting scale-invariant feature-transformation (SIFT) keypoints from both the reference logo image and a parcel image, and matching them subject to a consistent projective transformation (homography) by using random sample consensus (RANSAC). Once the homography matrix is computed, we extract the waybill of parcel image by mapping all pixels from a standard waybill image to the parcel image. Experimental results on test datasets demonstrate the effectiveness of the proposed method.
This paper presents a binarization approach to degraded document images, which is based on Gaussian Markov Random Field (GMRF) model. The energy function with the single-site and pair-site clique potential functions i...
详细信息
ISBN:
(纸本)9781479939046
This paper presents a binarization approach to degraded document images, which is based on Gaussian Markov Random Field (GMRF) model. The energy function with the single-site and pair-site clique potential functions is formulated for the GMRF. The parameters of the potential functions are estimated by expectation-maximization (EM) algorithm, without necessity of training process. Experiments on different types of degraded document images with various noise, contrast variation or uneven illumination, have demonstrated the validity of the proposed method.
A mail retrieval method based on image feature is an innovative approach by which the postal department can realize the query of mail information. The paper chooses envelope images with handwritten address characters ...
详细信息
暂无评论