Deep learning models for handwriting recognition have been developed in recent years. To improve the model’s generalization ability for sequence modeling task, this paper proposes to use domain adaptation with statistical distribution alignment and entropy regularization. For statistical distribution alignment, a domain adaptation loss function is proposed by using both the first and second order statistical information of deep feature representations, which is equivalent to maximizing the mutual information in feature spaces of the source domain and target domain. For entropy regularization, the entropy of the predicted text symbols of unlabeled samples in the target domain is also utilized as an additional loss function, which maximizes the mutual information between the feature space and pattern space in the target domain. Experimental results on the IAM handwriting dataset have demonstrated the effectiveness of the proposed domain adaptation method for sequence modeling task.

Scene text recognition is a challenging task due to di-verse variations of text instances in natural scene images. Conventional methods based on CNN-RNN-CTC or encoder-decoder with attention mechanism may not fully investigate stable and efficient feature representations for multi-oriented scene texts. In this paper, we propose a primitive representation learning method that aims to exploit intrinsic representations of scene text images. We model elements in feature maps as the nodes of an undirected graph. A pooling aggregator and a weighted aggregator are proposed to learn primitive representations, which are transformed into high-level visual text representations by graph convolutional networks. A Primitive REpresentation learning Network (PREN) is constructed to use the visual text representations for parallel decoding. Furthermore, by integrating visual text representations into an encoder-decoder model with the 2D attention mechanism, we pro-pose a framework called PREN2D to alleviate the misalignment problem in attention-based methods. Experimental results on both English and Chinese scene text recognition tasks demonstrate that PREN keeps a balance between ac-curacy and efficiency, while PREN2D achieves state-of-the-art performance.

Long short-term memory (LSTM) networks have been widely used in automatic speech recognition (ASR). This paper proposes a novel dynamic temporal residual learning mechanism for LSTM networks to better explore temporal dependencies in sequential data. The temporal residual learning mechanism is implemented by applying shortcut connections with dynamic weights to temporally adjacent LSTM outputs. Two types of dynamic weight generation methods are proposed: using a secondary network and using a random weight generator. Experimental results on Wall Street Journal (WSJ) speech recognition dataset reveal that our proposed methods have surpassed the baseline LSTM network.

Scene text recognition is a challenging problem due to the wide variances in contents, styles, orientations, and image quality of text instances in natural scene images. To learn the intrinsic representation of scene texts, a novel multi-element attention (MEA) mechanism is proposed to exploit geometric structures from local to global levels in feature maps extracted from a scene text image. The MEA mechanism is a generalized form of self-attention technique. The elements in feature maps are taken as the nodes of an undirected graph, and three kinds of adjacency matrices are designed to aggregate information at local, neighborhood and global levels before calculating the attention weights. A multi-element attention network (MEAN) is implemented, which includes a CNN for feature extraction, an encoder with MEA mechanism and a decoder for predicting text codes. Orientational positional encoding is added to feature maps output by the CNN, and a feature vector sequence transformed from the feature maps is used as the input of the encoder. Experimental results show that MEAN has achieved state-of-the-art or competitive performance on seven public English scene text datasets (IIITSk, SVT, IC03, IC13, IC15, SVTP, and CUTE). Further experiments have been conducted on a selected subset of the RCTW Chinese scene text dataset, demonstrating that MEAN can handle horizontal, vertical, and irregular scene text samples.

Offline handwriting recognition is a well-known challenging task in the optical character recognition (OCR) field due to the difficulty caused by various unconstraint handwriting styles. In order to learn invariant feature representations for handwriting, we propose a novel method to incorporate pixel-level rectification into a CNN and RNN based model. We also propose an adjacent output mixup method for RNN layer's training to improve the generalization ability of the model, i.e., the previous output of an RNN layer is added to the current output with random weights. We additionally adopt a series of techniques including pre-training, data augmentation and language model, and further analyze their contributions to the improvement of the model performance. The proposed method performs well on three public benchmarks, including the IAM, Rimes and IFN/ENIT datasets.

Deep Recurrent Neural Networks (RNN) have been suffering from the overfitting problem due to the model redundancy of the network structures. We propose a novel temporal and spatial residual learning method for RNN, followed with sparse training by weight pruning to gain sparsity in network parameters. For a Long Short-Term Memory (LSTM) network, we explore the combination schemes and parameter settings for temporal and spatial residual learning with sparse training. Experiments are carried out on the IFN/ENIT database. For the character error rate on the testing set e while training with sets a, b, c, d, the previously reported best result is 13.42%, and the proposed configuration of temporal residual learning followed with sparse training achieves the state-of-the-art result 12.06%.

According to the characteristics and difficulties of the aircraft tooling collaborative design as well as the state-of-the-art of some aircraft manufacturing enterprises, the necessity of realizing semantic collaboration of the aircraft tooling design is analyzed. By studying semantic collaboration and semantic information transferring in aircraft tooling design, a semantic collaboration implementation framework of aircraft tooling design is constructed. Based on this framework, the multi-agent-based semantic collaboration technology of aircraft tooling design is put forward. By mean of combining multi-agent technology with CAD, PDM and knowledge management technologies, this technology solves the issues in distributed semantic collaboration and semantic information transmission of aircraft tooling design. And the implementation process is introduced through a pilot system. This system has been partially tested in an aviation enterprise. By comparison, this system has the advantages of opening, real-time, intelligence and etc. Finally, further work is prospected.

Considering the characteristic and difficulty of airplane tooling design that the correlation is complicated and cooperation is difficult, the collaborative design framework for airplane tooling is constructed, and the key technologies, including the technology of collaboration between tooling design and airplane product design, the collaborative design technology of airplane tooling application model, the correlative design technology of airplane tooling structure, and the correlative design technology of airplane tooling semantic information are brought forward in this paper and the collaborative design for airplane tooling in different levels is realized. The software system based on those technologies is applied to an aviation manufacture enterprise and has many advantages such as little dependence on the network, controllable and correlative update.