Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Comprehensive Comparison of End-to-End Approaches for Handwritten Digit String Recognition
254
0
0.0
(
0
)
Added by
Andre G Hochuli
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Over the last decades, most approaches proposed for handwritten digit string recognition (HDSR) have resorted to digit segmentation, which is dominated by heuristics, thereby imposing substantial constraints on the final performance. Few of them have been based on segmentation-free strategies where each pixel column has a potential cut location. Recently, segmentation-free strategies has added another perspective to the problem, leading to promising results. However, these strategies still show some limitations when dealing with a large number of touching digits. To bridge the resulting gap, in this paper, we hypothesize that a string of digits can be approached as a sequence of objects. We thus evaluate different end-to-end approaches to solve the HDSR problem, particularly in two verticals: those based on object-detection (e.g., Yolo and RetinaNet) and those based on sequence-to-sequence representation (CRNN). The main contribution of this work lies in its provision of a comprehensive comparison with a critical analysis of the above mentioned strategies on five benchmarks commonly used to assess HDSR, including the challenging Touching Pair dataset, NIST SD19, and two real-world datasets (CAR and CVL) proposed for the ICFHR 2014 competition on HDSR. Our results show that the Yolo model compares favorably against segmentation-free models with the advantage of having a shorter pipeline that minimizes the presence of heuristics-based models. It achieved a 97%, 96%, and 84% recognition rate on the NIST-SD19, CAR, and CVL datasets, respectively.
rate research
Read More
End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies have focused primarily on short utterances that typically last for just a few seconds or, at most, a few tens of seconds. Whether such architectures are practical on long utterances that last from minutes to hours remains an open question. In this paper, we both investigate and improve the performance of end-to-end models on long-form transcription. We first present an empirical comparison of different end-to-end models on a real world long-form task and demonstrate that the RNN-T model is much more robust than attention-based systems in this regime. We next explore two improvements to attention-based systems that significantly improve its performance: restricting the attention to be monotonic, and applying a novel decoding algorithm that breaks long utterances into shorter overlapping segments. Combining these two improvements, we show that attention-based end-to-end models can be very competitive to RNN-T on long-form speech recognition.
CNN model is a popular method for imagery analysis, so it could be utilized to recognize handwritten digits based on MNIST datasets. For higher recognition accuracy, various CNN models with different fully connected layer sizes are exploited to figure out the relationship between the CNN fully connected layer size and the recognition accuracy. Inspired by previous pruning work, we performed pruning methods of distinctiveness on CNN models and compared the pruning performance with NN models. For better pruning performances on CNN, the effect of angle threshold on the pruning performance was explored. The evaluation results show that: for the fully connected layer size, there is a threshold, so that when the layer size increases, the recognition accuracy grows if the layer size smaller than the threshold, and falls if the layer size larger than the threshold; the performance of pruning performed on CNN is worse than on NN; as pruning angle threshold increases, the fully connected layer size and the recognition accuracy decreases. This paper also shows that for CNN models trained by the MNIST dataset, they are capable of handwritten digit recognition and achieve the highest recognition accuracy with fully connected layer size 400. In addition, for same dataset MNIST, CNN models work better than big, deep, simple NN models in a published paper.
Plenty of effective methods have been proposed for face recognition during the past decade. Although these methods differ essentially in many aspects, a common practice of them is to specifically align the facial area based on the prior knowledge of human face structure before feature extraction. In most systems, the face alignment module is implemented independently. This has actually caused difficulties in the designing and training of end-to-end face recognition models. In this paper we study the possibility of alignment learning in end-to-end face recognition, in which neither prior knowledge on facial landmarks nor artificially defined geometric transformations are required. Specifically, spatial transformer layers are inserted in front of the feature extraction layers in a Convolutional Neural Network (CNN) for face recognition. Only human identity clues are used for driving the neural network to automatically learn the most suitable geometric transformation and the most appropriate facial area for the recognition task. To ensure reproducibility, our model is trained purely on the publicly available CASIA-WebFace dataset, and is tested on the Labeled Face in the Wild (LFW) dataset. We have achieved a verification accuracy of 99.08% which is comparable to state-of-the-art single model based methods.
In this paper, we present an end-to-end training framework for building state-of-the-art end-to-end speech recognition systems. Our training system utilizes a cluster of Central Processing Units(CPUs) and Graphics Processing Units (GPUs). The entire data reading, large scale data augmentation, neural network parameter updates are all performed on-the-fly. We use vocal tract length perturbation [1] and an acoustic simulator [2] for data augmentation. The processed features and labels are sent to the GPU cluster. The Horovod allreduce approach is employed to train neural network parameters. We evaluated the effectiveness of our system on the standard Librispeech corpus [3] and the 10,000-hr anonymized Bixby English dataset. Our end-to-end speech recognition system built using this training infrastructure showed a 2.44 % WER on test-clean of the LibriSpeech test set after applying shallow fusion with a Transformer language model (LM). For the proprietary English Bixby open domain test set, we obtained a WER of 7.92 % using a Bidirectional Full Attention (BFA) end-to-end model after applying shallow fusion with an RNN-LM. When the monotonic chunckwise attention (MoCha) based approach is employed for streaming speech recognition, we obtained a WER of 9.95 % on the same Bixby open domain test set.
The HGR is a quite challenging task as its performance is influenced by various aspects such as illumination variations, cluttered backgrounds, spontaneous capture, etc. The conventional CNN networks for HGR are following two stage pipeline to deal with the various challenges: complex signs, illumination variations, complex and cluttered backgrounds. The existing approaches needs expert expertise as well as auxiliary computation at stage 1 to remove the complexities from the input images. Therefore, in this paper, we proposes an novel end-to-end compact CNN framework: fine grained feature attentive network for hand gesture recognition (Fit-Hand) to solve the challenges as discussed above. The pipeline of the proposed architecture consists of two main units: FineFeat module and dilated convolutional (Conv) layer. The FineFeat module extracts fine grained feature maps by employing attention mechanism over multiscale receptive fields. The attention mechanism is introduced to capture effective features by enlarging the average behaviour of multi-scale responses. Moreover, dilated convolution provides global features of hand gestures through a larger receptive field. In addition, integrated layer is also utilized to combine the features of FineFeat module and dilated layer which enhances the discriminability of the network by capturing complementary context information of hand postures. The effectiveness of Fit- Hand is evaluated by using subject dependent (SD) and subject independent (SI) validation setup over seven benchmark datasets: MUGD-I, MUGD-II, MUGD-III, MUGD-IV, MUGD-V, Finger Spelling and OUHANDS, respectively. Furthermore, to investigate the deep insights of the proposed Fit-Hand framework, we performed ten ablation study.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
