A Compact CNN-DBLSTM Based Character Model for Offline Handwriting Recognition with Tucker Decomposition

Ding, Haisong; Chen, Kai; Yuan, Ye; Cai, Meng; Sun, Lei; Huo, Qiang

doi:10.1109/icdar.2017.89

Cited by 30 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new very deep architecture [13] called VGG network was introduced for offline handwriting recognition [45], [77]. Although it is deeper as shown in Figure 13, yet it is simpler than the previous architecture [70].…”

Section: ) Vgg-16mentioning

confidence: 99%

Comparative Study on Deep Convolution Neural Networks DCNN-Based Offline Arabic Handwriting Recognition

2020

View full text Add to dashboard Cite

Recently, deep learning techniques demonstrated efficiency in building better performing machine learning models which are required in the field of offline Arabic handwriting recognition. Our ancient civilizations presented valuable handwritten manuscripts that need to be documented digitally. If we compared between Latin and the isolated Arabic character recognition, the latter is much more challenging due to the similarity between characters, and the variability of the writing styles. This paper proposes a multistage cascading system to serve the field of offline Arabic handwriting recognition. The approach starts with applying the Hierarchical Agglomerative Clustering (HAC) technique to split the database into partially interrelated clusters. The interrelations between the constructed clusters support representing the database as a big search tree model and help to attain a reduced complexity in matching each test image with a cluster. Cluster members are then ranked based on our new proposed ranking algorithm. This ranking algorithm starts with computing Pyramid Histogram of Oriented Gradients (PHoG), and is followed by measuring divergence by Kullback-Leibler method. Eventually, the classification process is applied only to the highly ranked matching classes. A comparative study is made to assess the effect of six different deep Convolution Neural Networks (DCNNs) on the final recognition rates of the proposed system. Experiments are done using the IFN/ENIT Arabic database. The proposed clustering and ranking stages lead to using only 11% of the whole database in classifying test images. Accordingly, more reduced computation complexity and more enhanced classification results are achieved compared to recent existing systems. INDEX TERMS Agglomerative hierarchical clustering, deep convolutional neural network, Kullback-Leibler divergence, offline arabic handwritting recognition, pyramid histogram of gradients.

show abstract

Section: ) Vgg-16mentioning

confidence: 99%

Comparative Study on Deep Convolution Neural Networks DCNN-Based Offline Arabic Handwriting Recognition

2020

View full text Add to dashboard Cite

show abstract

“…Significant advances in handwritten text recognition were realised by the description of the multidimensional recurrent neural networks (MD-RNN) in Graves et al [7] and the Connectionist Temporal Classification (CTC) loss. A number of advances based on the MD-RNN were reported including using attribute embeddings [8], dropout [9], Tucker decomposition [10] etc. Recent works conducted by Puigcerver [11] suggest that the multidimensional aspects of the MD-RNN can be replaced with feeding image-features (from a CNN) into a one-dimensional LSTM to significantly reduce the memory requirements of the systems.…”

Section: B Text Recognitionmentioning

confidence: 99%

A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognition

Chung¹,

Delteil²

2019

2019 International Conference on Document Analysis and Recognition Workshops (ICDARW)

View full text Add to dashboard Cite

Offline handwriting recognition with deep neural networks is usually limited to words or lines due to large computational costs. In this paper, a less computationally expensive full page offline handwritten text recognition framework is introduced. This framework includes a pipeline that locates handwritten text with an object detection neural network and recognises the text within the detected regions using features extracted with a multi-scale convolutional neural network (CNN) fed into a bidirectional long short term memory (LSTM) network. This framework achieves comparable error rates to state of the art frameworks while using less memory and time. The results in this paper demonstrate the potential of this framework and future work can investigate production ready and deployable handwritten text recognisers.

show abstract

“…Except for distillation based approaches, many other acceleration and compression algorithms have also been widely investigated such as low-rank decomposition [38], [39], [40], [41], [42],…”

Section: B Acceleration and Compressionmentioning

confidence: 99%

“…A representative work comes from [40], where the authors take the nonlinear units into account in their decomposition algorithm based on the assumption that the filter response lies on a low-rank subspace. The authors in [41], [42] use Tucker decomposition to achieve compression. Such algorithms need to be conducted layer by layer.…”

Section: B Acceleration and Compressionmentioning

confidence: 99%

Joint Architecture and Knowledge Distillation in CNN for Chinese Text Recognition

Wang

2019

Preprint

View full text Add to dashboard Cite

The technique of distillation helps transform cumbersome neural network into compact network so that the model can be deployed on alternative hardware devices. The main advantages of distillation based approaches include simple training process, supported by most off-the-shelf deep learning softwares and no special requirement of hardwares. In this paper, we propose a guideline to distill the architecture and knowledge of pre-trained standard CNNs simultaneously. We first make a quantitative analysis of the baseline network, including computational cost and storage overhead in different components.And then, according to the analysis results, optional strategies can be adopted to the compression of fully-connected layers. For vanilla convolution layers, the proposed parsimonious convolution (ParConv) block only consisting of depthwise separable convolution and pointwise convolution is used as a direct replacement without other adjustments such as the widths and depths in the network. Finally, the knowledge distillation with multiple losses is adopted to improve performance of the compact CNN.The proposed algorithm is first verified on offline handwritten Chinese text recognition (HCTR) where the CNNs are characterized by tens of thousands of output nodes and trained by hundreds of millions of training samples. Compared with the CNN in the state-of-the-art system, our proposed joint architecture and knowledge distillation can reduce the computational cost by >10× and model size by >8× with negligible accuracy loss. And then, by conducting experiments on one of the most popular data sets: MNIST, we demonstrate the proposed approach can also be successfully applied on mainstream backbone networks.

show abstract

A Compact CNN-DBLSTM Based Character Model for Offline Handwriting Recognition with Tucker Decomposition

Cited by 30 publications

References 17 publications

Comparative Study on Deep Convolution Neural Networks DCNN-Based Offline Arabic Handwriting Recognition

Comparative Study on Deep Convolution Neural Networks DCNN-Based Offline Arabic Handwriting Recognition

A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognition

Joint Architecture and Knowledge Distillation in CNN for Chinese Text Recognition

Contact Info

Product

Resources

About