Employing CNN to Identify Noisy Documents Thereafter Accomplishing Text Line Segmentation

Text line segmentation is a necessary preliminary step before most text transcription algorithms are applied. The leading deep learning networks used in this context (ARU-Net, dhSegment, and Doc-UFCN) are based on the U-Net architecture. They are efficient, but fall under the same concept, requiring a post-processing step to perform instance (e.g., text line) segmentation. In the present work, we test the advantages of Mask-RCNN, which is designed to perform instance segmentation directly. This work is the first to directly compare Mask-RCNN- and U-Net-based networks on text segmentation of historical documents, showing the superiority of the former over the latter. Three studies were conducted, one comparing these networks on different historical databases, another comparing Mask-RCNN with Doc-UFCN on a private historical database, and a third comparing the handwritten text recognition (HTR) performance of the tested networks. The results showed that Mask-RCNN outperformed ARU-Net, dhSegment, and Doc-UFCN using relevant line segmentation metrics, that performance evaluation should not focus on the raw masks generated by the networks, that a light mask processing is an efficient and simple solution to improve evaluation, and that Mask-RCNN leads to better HTR performance.

In this paper, we propose a new model for text line segmentation and classification, which consists of convolutional and two-layer bi-directional long short-term memory (BiLSTM) networks. Trained on the synthetic text dataset, it performs excellently when predicting the real data. Without labelling every line on the real data, a generalized standard for evaluating the accuracy is proposed. We also propose a simplified IoU loss to improve the execution speed greatly. In the experiments, it achieves 98.1% line segmentation accuracy and 99.5% classification accuracy on the English fiction Pride and Prejudice by Jane Austen, and achieves 98.5% line segmentation accuracy and 99.7% classification accuracy on the The Secret Of Plato's Atlantis by John Arundell, outperforming the traditional methods. Furthermore, for 1024 × 724 input samples, it gets 2.95 FPS speed when using a Tesla K80 GPU. Index Terms—Text line segmentation, Text classification, Synthetic text, BiLSTM, Convolutional network.

Recognition of human activity based on convolutional neural network has received the interest of researchers in recent years due to its significant improvement in accuracy. A large number of algorithms based on the deep learning approach have been proposed for activity recognition purpose. However, with the increasing advancements in technologies having limited computational resources, it needs to design an efficient deep learning-based approaches with improved utilization of computational resources. This paper presents a simple and efficient 2-Dimensional convolutional neural network (2-D CNN) architecture with very small size convolutional kernel for human activity recognition. The merit of the proposed CNN architecture over standard deep learning architectures is fewer trainable parameters and lesser memory requirement which enables it to train the proposed CNN architecture on low GPU memory-based devices and also works well with smaller as well as larger size datasets. The proposed approach consists of mainly four stages: namely (1) creation of dataset and data augmentation, (2) designing 2-D convolutional neural network (CNN) architecture, (3) the proposed 2-D CNN architecture trained from scratch up to optimum stage, and (4) evaluation of the trained 2-D CNN architecture. To illustrate the effectiveness of the proposed architecture several extensive experiments are conducted on three publicly available datasets, namely IXMAS, YouTube, and UCF101 dataset. The results of the proposed method and its comparison with other state-of-the-art methods [8-12,14,18-26,29-33] demonstrate the usefulness of the proposed method.

Ultrasound (US) is the preferred modality for fatty liver disease diagnosis due to its noninvasive, real-time, and cost-effective imaging capabilities. However, traditional B-mode US is qualitative, and therefore, the assessment is very subjective. Computer-aided diagnostic tools can improve the specificity and sensitivity of US and help clinicians to perform uniform diagnoses. In this work, we propose a novel deep learning model for nonalcoholic fatty liver disease classification from US data. We design a multi-feature guided multi-scale residual convolutional neural network (CNN) architecture to capture features of different receptive fields. B-mode US images are combined with their corresponding local phase filtered images and radial symmetry transformed images as multi-feature inputs for the network. Various fusion strategies are studied to improve prediction accuracy. We evaluate the designed network architectures on B-mode in vivo liver US images collected from 55 subjects. We also provide quantitative results by comparing our proposed multi-feature CNN architecture against traditional CNN designs and machine learning methods. Quantitative results show an average classification accuracy above 90% over tenfold cross-validation. Our proposed method achieves a 97.8% area under the ROC curve (AUC) for the patient-specific leave-one-out cross-validation (LOOCV) evaluation. Comprehensive validation results further demonstrate that our proposed approaches achieve significant improvements compared to training mono-feature CNN architectures ([Formula: see text]). Feature combination is valuable for the traditional classification methods, and the use of multi-scale CNN can improve liver classification accuracy. Based on the promising performance, the proposed method has the potential in practical applications to help radiologists diagnose nonalcoholic fatty liver disease.

In this paper, we study the performance of variants of well-known Convolutional Neural Network (CNN) architectures on different audio tasks. We show that tuning the Receptive Field (RF) of CNNs is crucial to their generalization. An insufficient RF limits the CNN's ability to fit the training data. In contrast, CNNs with an excessive RF tend to over-fit the training data and fail to generalize to unseen testing data. As state-of-the-art CNN architectures - in computer vision and other domains - tend to go deeper in terms of number of layers, their RF size increases and therefore they degrade in performance in several audio classification and tagging tasks. We study well-known CNN architectures and how their building blocks affect their receptive field. We propose several systematic approaches to control the RF of CNNs and systematically test the resulting architectures on different audio classification and tagging tasks and datasets. The experiments show that regularizing the RF of CNNs using our proposed approaches can drastically improve the generalization of models, out-performing complex architectures and pre-trained models on larger datasets. The proposed CNNs achieve state-of-the-art results in multiple tasks, from acoustic scene classification to emotion and theme detection in music to instrument recognition, as demonstrated by top ranks in several pertinent challenges (DCASE, MediaEval).

Every year, new Convolutional Neural Network (CNN) architectures appear to deal with different problems in the activity of image and video recognition. These architectures usually work along the ImageNet dataset for looking for the best performance of the CNNs without taking into account the video task where they are used. This can represent a problem if the task is Human Action Recognition (HAR) in video, since the CNN architectures are pre-trained with an image dataset that can practically contain any object, while HAR problem requires consecutive frames of people doing actions. To prove the idea that using CNNs pre-trained on an image dataset does not always achieve the best performance on a video dataset and that, therefore, it is worth comparing the performance of different CNNs under similar circumstances for the HAR problem, this work proposes an analysis between eight different CNN architectures. Each one of the CNN was exclusively trained with RGB images, which were extracted from the frames of the different classes of videos of HMDB51 dataset. To make the classification of an activity in video, we average the predictions taking into account the successes. We also made some ensembles with the best performance CNNs to measure the improvement in accuracy. Our results suggest that Xception is a strong baseline model that could be used by the community to make their comparisons of their proposals more robust.

Segmentation of text lines is one of the important steps in the Optical Character Recognition system. Text Line Segmentation is pre-processing step of word and character segmentation. Text Line Segmentation can be viewed simple for printing documents which contains distinct spaces between the lines. And it is more complex for the documents where text lines are overlap, touch, curvilinear and variation of space between text lines like in Telugu scripts and skewed documents. The main objective of this project is to investigate different text line segmentation algorithms like Projection Profiles, Run length smearing and Adaptive Run length smearing on low quality documents. These methods are experimented and compare their accuracy and results.

In this paper, the Convolutional Neural Network (CNN) architecture, which is one of the deep learning architectures, is used to classify the basic circuit components drawn by hand. During the training and testing stages of the model, a new dataset containing images of 863 circuit components manually drawn by different people is created. The data set contains images of four different classes of circuit components such as resistor, inductor, capacitor and voltage source. All images have been fixed to the same size and converted to grayscale to increase recognition performance and reduce process complexity. In the study, training for four classes is performed with CNN architecture. Based on the CNN architecture, four new CNN models are employed with different the number of layers. The training and validation results of these models are compared separately, the model with the highest training and validation performance is observed with four layer CNN model (CNN-4). This model obtained 84.41% accuracy rate at classification task.

Although font recognition is a fundamental issue in the field of document analysis and recognition, it was usually ignored in the past. With the development of optical character recognition (OCR), font recognition becomes more and more important. This paper proposed a well-designed convolutional neural network (CNN) architecture for traditional Mongolian font recognition by means of a single word. To be specific, the whole word image is regarded as input of CNN. Hence, the word images should be normalized into the same size before being inputted into CNN. By comparison, an appropriate aspect ratio for the traditional Mongolian word images has been determined. Experimental results demonstrate that the proposed CNN architecture outperforms three classic CNN architectures, including LeNet-5, AlexNet and GoogLeNet. Therefore, the proposed CNN is much more suitable for the task of the traditional Mongolian font recognition in the way of a single word.

Despite recent advances in the field of supervised deep learning for text line segmentation, unsupervised deep learning solutions are beginning to gain popularity. In this paper, we present an unsupervised deep learning method that embeds document image patches to a compact Euclidean space where distances correspond to a coarse text line pattern similarity. Once this space has been produced, text line segmentation can be easily implemented using standard techniques with the embedded feature vectors. To train the model, we extract random pairs of document image patches with the assumption that neighbour patches contain a similar coarse trend of text lines, whereas if one of them is rotated, they contain different coarse trends of text lines. Doing well on this task requires the model to learn to recognize the text lines and their salient parts. The benefit of our approach is zero manual labelling effort. We evaluate the method qualitatively and quantitatively on several variants of text line segmentation datasets to demonstrate its effectivity.

This paper introduces a Convolutional Neural Network (CNN) architecture for radio event and source detection. The upper triangle of the auto-correlation matrix is extracted as the feature input to an uni-dimensional (1D) CNN and trained to detect the presence of a source in the sampled signal and estimate the number of signals. Since, the number of source signals present in the sampled waveform can vary between 0 and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$L-1$</tex> , where <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$L$</tex> is the number of sensors in the array, the network is modeled as a multi-class, multi-label classification problem. The proposed method is robust to a varying number of incoming signals to resolve and Signal to Interference Plus Noise Ratio (SINR). The CNN architecture is trained and tested with the number of sources varying between 0 and 4. The source detection architecture is introduced and its efficacy is validated using simulations closely replication real-time RF events.

In recent years, many researchers have focused on using convolutional neural networks to perform human activity recognition as evidenced by the emergence of a number of convolutional neural network architectures such as LeNet-5, AlexNet and VGG16 and modern architectures such as ResNet, Inception V3, Inception-ResNet, MobileNet V2, NASNet and PNASNet. The main characteristic of a convolutional neural network (CNN) is its ability to extract features automatically from input images, which facilitates the processes of activity recognition and classification. Convolutional networks indeed derive more relevant and complex features with every additional layer. In addition, CNNs have achieved perfect classification on highly similar activities that were previously extremely difficult to classify. In this paper, we evaluate modern convolutional neural networks in terms of their human activity recognition accuracy, and we compare the results with the state of the art methods. In our research, we used two public data sets, HMDB (Shooting gun, kicking, falling to the floor, punching) and the Weizman dataset (walking, running, jumping, bending, one hand waving, two-hand waving, jumping in place, jumping jack, skipping). Our experimental results indicated that the CNN with NASNet architecture achieves the best performance of the six CNN architectures on both human activity data sets (HMDB and Weizman).

Text line segmentation in unconstrained handwritten documents remains a challenge because handwritten text lines are multi-skewed and not obviously separated. This paper presents a new approach based on the variational Bayes (VB) framework for text line segmentation. Viewing the document image as a mixture density model, with each text line approximated by a Gaussian component, the VB method can automatically determine the number of components. We extend the VB method such that it can both eliminate and split components and control the orientation of text line lines. Experiments on Chinese handwritten documents demonstrated the effectiveness of the approach.

Bangla handwritten character recognition is a popular research topic as its difficulty is higher than the recognition of other languages because of multiple formats of compound characters. State of the art Convolutional neural network (CNN) architectures are very much useful in computer vision applications. Some works have been carried out in Bangla handwritten character recognition but most of them either not very efficient or they can not classify a lot of characters. In this work, state of art pre-trained CNN architectures is used to classify 231 different Bangla handwritten characters using CMATERdb dataset. The images were first converted to B&W form with white as the foreground color. The size of the images is reduced to 28 × 28 form. These images are used as input to the CNN architectures. The weights of the state-of-the-art CNN models are kept as it was. The training learning rate was set to 0.001 and categorical cross-entropy as the error function. After 50 epochs, InceptionResNetV2 achieved the best accuracy (96.99%). DenseNet121 and InceptionNetV3 also provided remarkable recognition accuracy (96.55 and 96.20%, respectively). We also considered combination of trained InceptionResNetV2, InceptionNetV3 and DenseNet121 architectures which provided better recognition accuracy (97.69%) than other single CNN architectures but it is not feasible for using as it requires a lot of computation power and memory. The models were tested in the cases where characters look confusing to humans, but all the architectures showed equal capability in recognizing these images. Considering computational complexity, memory and capability of recognizing confused characters, InceptionResNetV2 can be said as the best performing model.

Classification performance based on ImageNet is the de-facto standard metric for CNN development. In this work we challenge the notion that CNN architecture design solely based on ImageNet leads to generally effective convolutional neural network (CNN) architectures that perform well on a diverse set of datasets and application domains. To this end, we investigate and ultimately improve ImageNet as a basis for deriving such architectures. We conduct an extensive empirical study for which we train 500 CNN architectures, sampled from the broad AnyNetX design space, on ImageNet as well as 8 additional well-known image classification benchmark datasets from a diverse array of application domains. We observe that the performances of the architectures are highlydataset dependent. Some datasets even exhibit a negative error correlation with ImageNet across all architectures. We show how to significantly increase these correlations byutilizing ImageNet subsets restricted to fewer classes. These contributions can have a profound impact on the way we design future CNN architectures and help alleviate the tilt we see currently in our community with respect to over-reliance on one dataset.