scispace - formally typeset
Search or ask a question
Posted Content

Neural Computing for Online Arabic Handwriting Character Recognition using Hard Stroke Features Mining.

TL;DR: An enhanced method of detecting the desired critical points from vertical and horizontal direction-length of handwriting stroke features of online Arabic script recognition is proposed and achieves an average accuracy of 98.6% comparable in state of art character recognition techniques.
Abstract: Online Arabic cursive character recognition is still a big challenge due to the existing complexities including Arabic cursive script styles, writing speed, writer mood and so forth. Due to these unavoidable constraints, the accuracy of online Arabic character's recognition is still low and retain space for improvement. In this research, an enhanced method of detecting the desired critical points from vertical and horizontal direction-length of handwriting stroke features of online Arabic script recognition is proposed. Each extracted stroke feature divides every isolated character into some meaningful pattern known as tokens. A minimum feature set is extracted from these tokens for classification of characters using a multilayer perceptron with a back-propagation learning algorithm and modified sigmoid function-based activation function. In this work, two milestones are achieved; firstly, attain a fixed number of tokens, secondly, minimize the number of the most repetitive tokens. For experiments, handwritten Arabic characters are selected from the OHASD benchmark dataset to test and evaluate the proposed method. The proposed method achieves an average accuracy of 98.6% comparable in state of art character recognition techniques.
References
More filters
Journal ArticleDOI
TL;DR: The Grab cut method is applied for accurate segmentation of actual lesion symptoms while Transfer learning model visual geometry group (VGG-19) is fine-tuned to acquire the features which are then concatenated with hand crafted features through serial based method.

218 citations


"Neural Computing for Online Arabic ..." refers methods in this paper

  • ...ntinued until an appropriate output is matched with the actual output nodes on the same input dataset. To preserve the generation of initial weights out of the given range must be selected very small [67, 68, 69, 70], so here it is 0.1. As a final point, internal threshold and momentum coefficient values are selected 0.0 and 0.05 respectively; The BP/MLP classifier is utilized 70% of samples for training the netw...

    [...]

Journal ArticleDOI
TL;DR: Analysis of results indicate that classification and prediction of neurodegenerative brain disorders such as AD using functional magnetic resonance imaging and advanced deep learning methods is promising for clinical decision making and have the potential to assist in early diagnosis of AD and its associated stages.
Abstract: Alzheimer’s disease (AD) is an incurable neurodegenerative disorder accounting for 70%–80% dementia cases worldwide. Although, research on AD has increased in recent years, however, the complexity associated with brain structure and functions makes the early diagnosis of this disease a challenging task. Resting-state functional magnetic resonance imaging (rs-fMRI) is a neuroimaging technology that has been widely used to study the pathogenesis of neurodegenerative diseases. In literature, the computer-aided diagnosis of AD is limited to binary classification or diagnosis of AD and MCI stages. However, its applicability to diagnose multiple progressive stages of AD is relatively under-studied. This study explores the effectiveness of rs-fMRI for multi-class classification of AD and its associated stages including CN, SMC, EMCI, MCI, LMCI, and AD. A longitudinal cohort of resting-state fMRI of 138 subjects (25 CN, 25 SMC, 25 EMCI, 25 LMCI, 13 MCI, and 25 AD) from Alzheimer’s Disease Neuroimaging Initiative (ADNI) is studied. To provide a better insight into deep learning approaches and their applications to AD classification, we investigate ResNet-18 architecture in detail. We consider the training of the network from scratch by using single-channel input as well as performed transfer learning with and without fine-tuning using an extended network architecture. We experimented with residual neural networks to perform AD classification task and compared it with former research in this domain. The performance of the models is evaluated using precision, recall, f1-measure, AUC and ROC curves. We found that our networks were able to significantly classify the subjects. We achieved improved results with our fine-tuned model for all the AD stages with an accuracy of 100%, 96.85%, 97.38%, 97.43%, 97.40% and 98.01% for CN, SMC, EMCI, LMCI, MCI, and AD respectively. However, in terms of overall performance, we achieved state-of-the-art results with an average accuracy of 97.92% and 97.88% for off-the-shelf and fine-tuned models respectively. The Analysis of results indicate that classification and prediction of neurodegenerative brain disorders such as AD using functional magnetic resonance imaging and advanced deep learning methods is promising for clinical decision making and have the potential to assist in early diagnosis of AD and its associated stages.

176 citations

Journal ArticleDOI
TL;DR: A robust segmentation and deep learning techniques with the convolutional neural network are used to train the model on the bone marrow images to achieve accurate classification results, and experimental results reveal that the proposed method achieved 97.78% accuracy.
Abstract: Acute Leukemia is a life-threatening disease common both in children and adults that can lead to death if left untreated. Acute Lymphoblastic Leukemia (ALL) spreads out in children's bodies rapidly and takes the life within a few weeks. To diagnose ALL, the hematologists perform blood and bone marrow examination. Manual blood testing techniques that have been used since long time are often slow and come out with the less accurate diagnosis. This work improves the diagnosis of ALL with a computer-aided system, which yields accurate result by using image processing and deep learning techniques. This research proposed a method for the classification of ALL into its subtypes and reactive bone marrow (normal) in stained bone marrow images. A robust segmentation and deep learning techniques with the convolutional neural network are used to train the model on the bone marrow images to achieve accurate classification results. Experimental results thus obtained and compared with the results of other classifiers Naive Bayesian, KNN, and SVM. Experimental results reveal that the proposed method achieved 97.78% accuracy. The obtained results exhibit that the proposed approach could be used as a tool to diagnose Acute Lymphoblastic Leukemia and its sub-types that will definitely assist pathologists.

169 citations

Journal ArticleDOI
TL;DR: Experimental results on BRATS 2015 benchmark data show the usability of the proposed approach and its superiority over the other approaches in this area of research.
Abstract: A tumor could be found in any area of the brain and could be of any size, shape, and contrast. There may exist multiple tumors of different types in a human brain at the same time. Accurate tumor area segmentation is considered primary step for treatment of brain tumors. Deep Learning is a set of promising techniques that could provide better results as compared to nondeep learning techniques for segmenting timorous part inside a brain. This article presents a deep convolutional neural network (CNN) to segment brain tumors in MRIs. The proposed network uses BRATS segmentation challenge dataset which is composed of images obtained through four different modalities. Accordingly, we present an extended version of existing network to solve segmentation problem. The network architecture consists of multiple neural network layers connected in sequential order with the feeding of Convolutional feature maps at the peer level. Experimental results on BRATS 2015 benchmark data thus show the usability of the proposed approach and its superiority over the other approaches in this area of research.

162 citations


"Neural Computing for Online Arabic ..." refers background in this paper

  • ...Based on the complexities of Arabic cursive handwriting styles, speed, touching, overlapping and inherent properties, a pre-processing strategy is needed to collaborate with intelligent techniques to enhance the accuracy such as neural networks [33-37], GA [38-40], SVM [41-43]....

    [...]

Journal ArticleDOI
TL;DR: This work proposes a new automated approach for skin lesion detection and recognition using a deep convolutional neural network (DCNN) and concludes that the proposed method outperforms several existing methods and attained accuracy 98.4% on PH2 dataset, 95.1% on ISBI dataset and 94.8% onISBI 2017 dataset.
Abstract: Cancer is one of the leading causes of deaths in the last two decades. It is either diagnosed malignant or benign - depending upon the severity of the infection and the current stage. The conventional methods require a detailed physical inspection by an expert dermatologist, which is time-consuming and imprecise. Therefore, several computer vision methods are introduced lately, which are cost-effective and somewhat accurate. In this work, we propose a new automated approach for skin lesion detection and recognition using a deep convolutional neural network (DCNN). The proposed cascaded design incorporates three fundamental steps including; a) contrast enhancement through fast local Laplacian filtering (FlLpF) along HSV color transformation; b) lesion boundary extraction using color CNN approach by following XOR operation; c) in-depth features extraction by applying transfer learning using Inception V3 model prior to feature fusion using hamming distance (HD) approach. An entropy controlled feature selection method is also introduced for the selection of the most discriminant features. The proposed method is tested on PH2 and ISIC 2017 datasets, whereas the recognition phase is validated on PH2, ISBI 2016, and ISBI 2017 datasets. From the results, it is concluded that the proposed method outperforms several existing methods and attained accuracy 98.4% on PH2 dataset, 95.1% on ISBI dataset and 94.8% on ISBI 2017 dataset.

141 citations