23 January 2019 in IEEE Transactions on Neural Networks and Learning Systems
Deep neural networks have proved promising results in many applications and fields, but they are still assimilated to a black box. Thus, it is very useful to introduce interpretability aspects to prevent the blind application of deep networks. This paper proposed an interpretable morphological convolutional neural network called Morph-CNN for pattern recognition, where morphological operations were incorporated using counter-harmonic mean into the convolutional layer in order to generate enhanced feature maps. Morph-CNN was extensively evaluated on MNIST and SVHN benchmarks for digit recognition. The different tested configurations showed that Morph-CNN outperforms the existing methods.
20 March 2024 in IEEE Access
In recent years, Optical character recognition (OCR) has experienced a resurgence of interest especially for contemporary Arabic data. In fact, OCR development for printed and handwritten Arabic script is still a challenging task. These challenges are due to the specific characteristics of the Arabic script. In this work, we attempt to address these challenges by creating a deep learning OCR for Arabic document recognition called ADOCRNet. It is a novel deep learning framework whose architecture is built of layers of Convolutional Neural Networks (CNNs) and Bidirectional Long Short-Term Memory (BLSTM) trained by the so-called Connectionist Temporal Classification (CTC) algorithm. In order to assess the performance of our OCR, the proposed system is performed on two printed text datasets which are P-KHATT (text line images) and APTI (word images). It’s also evaluated on a handwritten Arabic text dataset IFN/ENIT (word images). According to the practical tests, the conceived model achieves strength recognition rates on the three datasets. ADOCRNet reaches a Character Error Rate (CER) of 0.01% on the P-KHATT dataset, 0.03% on the APTI dataset and a Word Error Rate (WER) of 1.09% on the IFN/ENIT dataset, which considerably outperforms the outcomes of the current systems.
1 March 2011 in Applied Soft Computing
10 April 2024 in IEEE Access
The increasing age of our society is connected to a rising number of people suffering from disorders. One such disorder is Parkinson’s disease (PD). Predictions indicate that the number of individuals affected by PD will more, than double in the future. Neurologists and data scientists consider handwriting as one of the motor symptoms of PD and recognize it as a valuable resource for detecting this disorder. Within this framework, we introduce an innovative system for Parkinson’s disease detection, which encompasses several key stages. The process commences with data augmentation and preprocessing, subsequently leading to the segmentation of online handwriting into Beta strokes. Following that, feature extraction is carried out utilizing the Beta-elliptical approach and the fuzzy perceptual detector. Finally, we employ bidirectional long short-term memory (BLSTM) for the classification task. To assess the performance of our system, we created a new online Arabic handwriting dataset designed for detecting Parkinson’s disease. The results we obtained affirm the efficacy of our proposed system. Through comprehensive evaluations conducted on the PaHaW dataset, we achieved good accuracy, thereby highlighting that our system surpasses the performance of existing systems.