Mehwish leghari | QUEST Engineering University Nawabshah, Sindh, Pakistan (original) (raw)
Uploads
Papers by Mehwish leghari
IEEE Access
Text recognition in natural scene images is a challenging problem in computer vision. Different t... more Text recognition in natural scene images is a challenging problem in computer vision. Different than the optical character recognition (OCR), text recognition in natural scene images is more complex due to variations in text size, colors, fonts, orientations, complex backgrounds, occlusion, illuminations and uneven lighting conditions. In this paper, we propose a segmentation-free method based on a deep convolutional recurrent neural network to solve the problem of cursive text recognition, particularly focusing on Urdu text in natural scenes. Compared to the non-cursive scripts, Urdu text recognition is more complex due to variations in the writing styles, several shapes of the same character, connected text, ligature overlapping, stretched, diagonal and condensed text. The proposed model gets a whole word image as an input without pre-segmenting into individual characters, and then transforms into the sequence of the relevant features. Our model is based on three components: a deep convolutional neural network (CNN) with shortcut connections to extract and encode the features, a recurrent neural network (RNN) to decode the convolutional features, and a connectionist temporal classification (CTC) to map the predicted sequences into the target labels. To increase the text recognition accuracy further, we explore deeper CNN architectures like VGG-16, VGG-19, ResNet-18 and ResNet-34 to extract more appropriate Urdu text features, and compare the recognition results. To conduct the experiments, a new large-scale benchmark dataset of cropped Urdu word images in natural scenes is developed. The experimental results show that the proposed deep CRNN network with shortcut connections outperform than other network architectures. The dataset is publicly available and can be downloaded from https://data.mendeley.com/datasets/k5fz57zd9z/1. INDEX TERMS Cursive text recognition in natural images, Urdu scene text recognition, natural scene text recognition, convolutional recurrent neural network, segmentation-free scene text recognition
Pakistan Journal of Engineering and Applied Sciences, 2019
In this paper, a problem of multi-font, multi-color and multi-size printed character recognition ... more In this paper, a problem of multi-font, multi-color and multi-size printed character recognition of Sindhi language are addressed. Although previous studies for offline handwritten isolated Sindhi character recognition with unique font and size have achieved satisfactory results, the problem of multi-fonts, multi-size and multi-color character recognition is still a major challenge. This is due to the various varieties in the shape, style, and layout of the character. A synthetic dataset with background color image consisting of Sindhi characters with multi-fonts, multi-size, and multi-colors is created. Three types of experiments with Convolutional Neural Networks (CNN) are performed separately. The first CNN network uses max-pooling layer after every two convolutional layers, the second network applies multi max-pooling layers after the last convolutional layer and the third network is created without applying any max-pooling layer. The experimental results demonstrate that convol...
2018 International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)
Multimodal biometrie systems have received greater attention from the research community since fe... more Multimodal biometrie systems have received greater attention from the research community since few decades due to various reasons such as: to increase accuracy and efficiency as compared to a single biometric system, decrease error rate or false acceptance and improve the security of the biometric data. In this research, a preliminary idea has been discussed for the fusion of fingerprint and online signature to make the biometric data safe from theft and misuse. The proposed multimodal biometric system will combine the features from both the fingerprint and the signature, which are the most widely used physiological and behavioral biometric traits.
2018 5th International Multi-Topic ICT Conference (IMTIC)
Computers
The extensive research in the field of multimodal biometrics by the research community and the ad... more The extensive research in the field of multimodal biometrics by the research community and the advent of modern technology has compelled the use of multimodal biometrics in real life applications. Biometric systems that are based on a single modality have many constraints like noise, less universality, intra class variations and spoof attacks. On the other hand, multimodal biometric systems are gaining greater attention because of their high accuracy, increased reliability and enhanced security. This research paper proposes and develops a Convolutional Neural Network (CNN) based model for the feature level fusion of fingerprint and online signature. Two types of feature level fusion schemes for the fingerprint and online signature have been implemented in this paper. The first scheme named early fusion combines the features of fingerprints and online signatures before the fully connected layers, while the second fusion scheme named late fusion combines the features after fully conne...
The rapid development in technology has facilitated human beings in many ways such as automated h... more The rapid development in technology has facilitated human beings in many ways such as automated home appliances, smart vehicles, smart mobile phones, and tablet computers. The uses of these tools and techniques are increasing in our daily lives to facilitate day to day work. The new trends in technology have focused on finding approaches towards improved learning techniques. Various tools are being used to integrate Information and Communication Technology in education. Tablet Personal Computers (PCs) are one of the new and innovative tools used in education for enhancing learning skills. This research has been conducted in five primary schools, where students of class nursery to class three were taught basic lessons using Tablet PC. In this research an application has been developed on android platform with easy to use interface, where the students were able to perform simple arithmetic calculations and learned alphabet of Sindhi and English languages in visual form. During the experiment, it was observed that with visual aids students understood lessons more clearly and easily.
cle.org.pk
In this research a model for transliteration is presented for two scripts of Sindhi language that... more In this research a model for transliteration is presented for two scripts of Sindhi language that is Perso-Arabic script and Devanagari script, based on an intermediate Roman script. After analyzing both Perso-Arabic and Devanagari scripts, a set of Roman ...
Mehran University Research Journal of Engineering and Technology
Now-a-days, in the field of machine learning the data augmentation techniques are common in use, ... more Now-a-days, in the field of machine learning the data augmentation techniques are common in use, especially with deep neural networks, where a large amount of data is required to train the network. The effectiveness of the data augmentation technique has been analyzed for many applications; however, it has not been analyzed separately for the multimodal biometrics. This research analyzes the effects of data augmentation on single biometric data and multimodal biometric data. In this research, the features from two biometric modalities: fingerprint and signature, have been fused together at the feature level. The primary motivation for fusing biometric data at feature level is to secure the privacy of the user’s biometric data. The results that have been achieved by using data augmentation are presented in this research. The experimental results for the fingerprint recognition, signature recognition and the feature-level fusion of fingerprint with signature have been presented separa...
January 2020
Conventional solar cells are not economical and are recently too expensive to the manufacturers f... more Conventional solar cells are not economical and are recently too expensive to the manufacturers for extensive-scale electricity generation. Cost and efficiency is most vital factor in the accomplishment of any solar technology. In order to improve the conversion efficiency, the major research in third generation photovoltaic (PV) cells is directed toward retaining more sunlight using nanotechnology. Advancement in nanotechnology solar cell via quantum dots (QDs) could reduce the cost of PV cell and additionally enhance cell conversion efficiency. Silicon quantum dots (Si-QDs) are semiconductor nano crystals of nanometers dimension whose electron-holes are confined in all three spatial dimensions. Quantum dots have discrete electronic states. Quantum dots have capacity to change band gap with the adjustment in size of quantum dot. As the quantum dots size fluctuates over a wide range that demonstrates the variety of band gap so it will assimilate or discharge light. In this paper, th...
January 2020
Conventional solar cells are not economical and are recently too expensive to the manufacturers f... more Conventional solar cells are not economical and are recently too expensive to the manufacturers for extensive-scale electricity generation. Cost and efficiency is most vital factor in the accomplishment of any solar technology. In order to improve the conversion efficiency, the major research in third generation photovoltaic (PV) cells is directed toward retaining more sunlight using nanotechnology. Advancement in nanotechnology solar cell via quantum dots (QDs) could reduce the cost of PV cell and additionally enhance cell conversion efficiency. Silicon quantum dots (Si-QDs) are semiconductor nano crystals of nanometers dimension whose electron-holes are confined in all three spatial dimensions. Quantum dots have discrete electronic states. Quantum dots have capacity to change band gap with the adjustment in size of quantum dot. As the quantum dots size fluctuates over a wide range that demonstrates the variety of band gap so it will assimilate or discharge light. In this paper, th...
In this research a model for transliteration is presented for two scripts of Sindhi language that... more In this research a model for transliteration is presented for two scripts of Sindhi language that is Perso-Arabic script and Devanagari script, based on an intermediate Roman script. After analyzing both Perso-Arabic and Devanagari scripts, a set of Roman script for Sindhi language is also suggested. Different issues, complexities and problems of Sindhi transliteration are discussed in detail. An algorithm to transliterate between two scripts of Sindhi language is also proposed.
IEEE Access
Text recognition in natural scene images is a challenging problem in computer vision. Different t... more Text recognition in natural scene images is a challenging problem in computer vision. Different than the optical character recognition (OCR), text recognition in natural scene images is more complex due to variations in text size, colors, fonts, orientations, complex backgrounds, occlusion, illuminations and uneven lighting conditions. In this paper, we propose a segmentation-free method based on a deep convolutional recurrent neural network to solve the problem of cursive text recognition, particularly focusing on Urdu text in natural scenes. Compared to the non-cursive scripts, Urdu text recognition is more complex due to variations in the writing styles, several shapes of the same character, connected text, ligature overlapping, stretched, diagonal and condensed text. The proposed model gets a whole word image as an input without pre-segmenting into individual characters, and then transforms into the sequence of the relevant features. Our model is based on three components: a deep convolutional neural network (CNN) with shortcut connections to extract and encode the features, a recurrent neural network (RNN) to decode the convolutional features, and a connectionist temporal classification (CTC) to map the predicted sequences into the target labels. To increase the text recognition accuracy further, we explore deeper CNN architectures like VGG-16, VGG-19, ResNet-18 and ResNet-34 to extract more appropriate Urdu text features, and compare the recognition results. To conduct the experiments, a new large-scale benchmark dataset of cropped Urdu word images in natural scenes is developed. The experimental results show that the proposed deep CRNN network with shortcut connections outperform than other network architectures. The dataset is publicly available and can be downloaded from https://data.mendeley.com/datasets/k5fz57zd9z/1. INDEX TERMS Cursive text recognition in natural images, Urdu scene text recognition, natural scene text recognition, convolutional recurrent neural network, segmentation-free scene text recognition
Pakistan Journal of Engineering and Applied Sciences, 2019
In this paper, a problem of multi-font, multi-color and multi-size printed character recognition ... more In this paper, a problem of multi-font, multi-color and multi-size printed character recognition of Sindhi language are addressed. Although previous studies for offline handwritten isolated Sindhi character recognition with unique font and size have achieved satisfactory results, the problem of multi-fonts, multi-size and multi-color character recognition is still a major challenge. This is due to the various varieties in the shape, style, and layout of the character. A synthetic dataset with background color image consisting of Sindhi characters with multi-fonts, multi-size, and multi-colors is created. Three types of experiments with Convolutional Neural Networks (CNN) are performed separately. The first CNN network uses max-pooling layer after every two convolutional layers, the second network applies multi max-pooling layers after the last convolutional layer and the third network is created without applying any max-pooling layer. The experimental results demonstrate that convol...
2018 International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)
Multimodal biometrie systems have received greater attention from the research community since fe... more Multimodal biometrie systems have received greater attention from the research community since few decades due to various reasons such as: to increase accuracy and efficiency as compared to a single biometric system, decrease error rate or false acceptance and improve the security of the biometric data. In this research, a preliminary idea has been discussed for the fusion of fingerprint and online signature to make the biometric data safe from theft and misuse. The proposed multimodal biometric system will combine the features from both the fingerprint and the signature, which are the most widely used physiological and behavioral biometric traits.
2018 5th International Multi-Topic ICT Conference (IMTIC)
Computers
The extensive research in the field of multimodal biometrics by the research community and the ad... more The extensive research in the field of multimodal biometrics by the research community and the advent of modern technology has compelled the use of multimodal biometrics in real life applications. Biometric systems that are based on a single modality have many constraints like noise, less universality, intra class variations and spoof attacks. On the other hand, multimodal biometric systems are gaining greater attention because of their high accuracy, increased reliability and enhanced security. This research paper proposes and develops a Convolutional Neural Network (CNN) based model for the feature level fusion of fingerprint and online signature. Two types of feature level fusion schemes for the fingerprint and online signature have been implemented in this paper. The first scheme named early fusion combines the features of fingerprints and online signatures before the fully connected layers, while the second fusion scheme named late fusion combines the features after fully conne...
The rapid development in technology has facilitated human beings in many ways such as automated h... more The rapid development in technology has facilitated human beings in many ways such as automated home appliances, smart vehicles, smart mobile phones, and tablet computers. The uses of these tools and techniques are increasing in our daily lives to facilitate day to day work. The new trends in technology have focused on finding approaches towards improved learning techniques. Various tools are being used to integrate Information and Communication Technology in education. Tablet Personal Computers (PCs) are one of the new and innovative tools used in education for enhancing learning skills. This research has been conducted in five primary schools, where students of class nursery to class three were taught basic lessons using Tablet PC. In this research an application has been developed on android platform with easy to use interface, where the students were able to perform simple arithmetic calculations and learned alphabet of Sindhi and English languages in visual form. During the experiment, it was observed that with visual aids students understood lessons more clearly and easily.
cle.org.pk
In this research a model for transliteration is presented for two scripts of Sindhi language that... more In this research a model for transliteration is presented for two scripts of Sindhi language that is Perso-Arabic script and Devanagari script, based on an intermediate Roman script. After analyzing both Perso-Arabic and Devanagari scripts, a set of Roman ...
Mehran University Research Journal of Engineering and Technology
Now-a-days, in the field of machine learning the data augmentation techniques are common in use, ... more Now-a-days, in the field of machine learning the data augmentation techniques are common in use, especially with deep neural networks, where a large amount of data is required to train the network. The effectiveness of the data augmentation technique has been analyzed for many applications; however, it has not been analyzed separately for the multimodal biometrics. This research analyzes the effects of data augmentation on single biometric data and multimodal biometric data. In this research, the features from two biometric modalities: fingerprint and signature, have been fused together at the feature level. The primary motivation for fusing biometric data at feature level is to secure the privacy of the user’s biometric data. The results that have been achieved by using data augmentation are presented in this research. The experimental results for the fingerprint recognition, signature recognition and the feature-level fusion of fingerprint with signature have been presented separa...
January 2020
Conventional solar cells are not economical and are recently too expensive to the manufacturers f... more Conventional solar cells are not economical and are recently too expensive to the manufacturers for extensive-scale electricity generation. Cost and efficiency is most vital factor in the accomplishment of any solar technology. In order to improve the conversion efficiency, the major research in third generation photovoltaic (PV) cells is directed toward retaining more sunlight using nanotechnology. Advancement in nanotechnology solar cell via quantum dots (QDs) could reduce the cost of PV cell and additionally enhance cell conversion efficiency. Silicon quantum dots (Si-QDs) are semiconductor nano crystals of nanometers dimension whose electron-holes are confined in all three spatial dimensions. Quantum dots have discrete electronic states. Quantum dots have capacity to change band gap with the adjustment in size of quantum dot. As the quantum dots size fluctuates over a wide range that demonstrates the variety of band gap so it will assimilate or discharge light. In this paper, th...
January 2020
Conventional solar cells are not economical and are recently too expensive to the manufacturers f... more Conventional solar cells are not economical and are recently too expensive to the manufacturers for extensive-scale electricity generation. Cost and efficiency is most vital factor in the accomplishment of any solar technology. In order to improve the conversion efficiency, the major research in third generation photovoltaic (PV) cells is directed toward retaining more sunlight using nanotechnology. Advancement in nanotechnology solar cell via quantum dots (QDs) could reduce the cost of PV cell and additionally enhance cell conversion efficiency. Silicon quantum dots (Si-QDs) are semiconductor nano crystals of nanometers dimension whose electron-holes are confined in all three spatial dimensions. Quantum dots have discrete electronic states. Quantum dots have capacity to change band gap with the adjustment in size of quantum dot. As the quantum dots size fluctuates over a wide range that demonstrates the variety of band gap so it will assimilate or discharge light. In this paper, th...
In this research a model for transliteration is presented for two scripts of Sindhi language that... more In this research a model for transliteration is presented for two scripts of Sindhi language that is Perso-Arabic script and Devanagari script, based on an intermediate Roman script. After analyzing both Perso-Arabic and Devanagari scripts, a set of Roman script for Sindhi language is also suggested. Different issues, complexities and problems of Sindhi transliteration are discussed in detail. An algorithm to transliterate between two scripts of Sindhi language is also proposed.