Papers by Md. Asifuzzaman Jishan
Science in Information Technology Letters, 2023
Object detection system in light of deep learning have been monstrously effective in complex item... more Object detection system in light of deep learning have been monstrously effective in complex item identification task images and have shown likely in an extensive variety of genuine applications counting the Coronavirus pandemic. Ensuring and enforcing the proper use of face masks is one of the main obstacles in containing and reducing the spread of the infection among the population. This paper aims to find out how the urban population of a megacity uses facial masks correctly. Using YOLOv3 and YOLOv5, we trained and validated a brand-new dataset to identify images as "with mask", "without mask", and "mask not in position". In the YOLOv3 we carried out three pre-trained models which are: YOLOv3, YOLOv3-tiny, and SPP-YOLOv3. In addition, we utilized five pre-trained models in the YOLOv5: YOLOv5n, YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x. The dataset is included 6550 pictures with three classes. On mAP, the dataset achieved a commendable 95% performance accuracy. This research can be used to monitor the proper use of face masks in various public spaces through automated scanning.
International Journal of Computing, 2023
Object detection systems based on deep learning have been immensely successful in complex object ... more Object detection systems based on deep learning have been immensely successful in complex object detection tasks images and have shown potential in a wide range of real-life applications including the COVID-19 pandemic. One of the key challenges in containing and mitigating the infection among the population is to ensure and enforce the proper use of face masks. The objective of this paper is to detect the proper use of facial masks among the urban population in a megacity. In this study, we trained and validated a new dataset to detect images such as 'with mask', 'without mask', and 'mask not in position' using YOLOv5. The dataset is comprised of 6550 images with the three classes. The dataset attained a commendable performance accuracy of 95% on mAP. This study can be implemented for automated scanning for monitoring the proper use of face masks in different settings of public spaces.
Indonesian Journal of Electrical Engineering and Computer Science, 2021
Automatic image captioning task in different language is a challenging task which has not been we... more Automatic image captioning task in different language is a challenging task which has not been well investigated yet due to the lack of dataset and effective models. It also requires good understanding of scene and contextual embedding for robust semantic interpretation of images for natural language image descriptor. To generate image descriptor in Bangla, we created a new Bangla dataset of images paired with target language label, named as Bangla Natural Language Image to Text (BNLIT) dataset. To deal with the image understanding, we propose a hybrid encoder-decoder model based on encoder-decoder architecture and the model is evaluated on our newly created dataset. This proposed approach achieves significance performance improvement on task of semantic retrieval of images. Our hybrid model uses the Convolutional NeuralNetwork as an encoder whereas the Bidirectional Long Short Term Memory is used for the sentence representation that decreases the computational complexities without ...
Neural Networks and Deep Learning have seen an upsurge of research in the past decade due to the ... more Neural Networks and Deep Learning have seen an upsurge of research in the past decade due to the improved results. Generates text from the given image is a crucial task that requires the combination of both sectors which are computer vision and natural language processing in order to understand an image and represent it using a natural language. However existing works have all been done on a particular lingual domain and on the same set of data. This leads to the systems being developed to perform poorly on images that belong to specific locales' geographical context. TextMage is a system that is capable of understanding visual scenes that belong to the Bangladeshi geographical context and use its knowledge to represent what it understands in Bengali. Hence, we have trained a model on our previously developed and published dataset named BanglaLekhaImageCaptions. This dataset contains 9,154 images along with two annotations for each image. In order to access performance, the proposed model has been implemented and evaluated.
Indonesian Journal of Electrical Engineering and Computer Science, 2021
Automatic image captioning task in different language is a challenging task which has not been we... more Automatic image captioning task in different language is a challenging task which has not been well investigated yet due to the lack of dataset and effective models. It also requires good understanding of scene and contextual embedding for robust semantic interpretation of images for natural language image descriptor. To generate image descriptor in Bangla, we created a new Bangla dataset of images paired with target language label, named as Bangla natural language image to text (BNLIT) dataset. To deal with the image understanding, we propose a hybrid encoder-decoder model based on encoder-decoder architecture and the model is evaluated on our newly created dataset. This proposed approach achieves significance performance improvement on task of semantic retrieval of images. Our hybrid model uses the convolutional neural network as an encoder whereas the bidirectional long short term memory is used for the sentence representation that decreases the computational complexities without trading off the exactness of the descriptor. The model yielded benchmark accuracy in recovering Bangla natural language and we also conducted a thorough numerical analysis of the model performance on the BNLIT dataset.
International Journal of Advances in Intelligent Informatics, Jul 12, 2020
Automated image to text generation is a computationally challenging computer vision task which re... more Automated image to text generation is a computationally challenging computer vision task which requires sufficient comprehension of both syntactic and semantic meaning of an image to generate a meaningful description. Until recent times, it has been studied to a limited scope due to the lack of visual-descriptor dataset and functional models to capture intrinsic complexities involving features of an image. In this study, a novel dataset was constructed by generating Bangla textual descriptor from visual input, called Bangla Natural Language Image to Text (BNLIT), incorporating 100 classes with annotation. A deep neural network-based image captioning model was proposed to generate image description. The model employs Convolutional Neural Network (CNN) to classify the whole dataset, while Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) capture the sequential semantic representation of text-based sentences and generate pertinent description based on the modular complexities of an image. When tested on the new dataset, the model accomplishes significant enhancement of centrality execution for image semantic recovery assignment. For the experiment of that task, we implemented a hybrid image captioning model, which achieved a remarkable result for a new self-made dataset, and that task was new for the Bangladesh perspective. In brief, the model provided benchmark precision in the characteristic Bangla syntax reconstruction and comprehensive numerical analysis of the model execution results on the dataset.
International Journal of Electrical and Computer Engineering (IJECE), 2019
We presented a learning model that generated natural language description of images. The model ut... more We presented a learning model that generated natural language description of images. The model utilized the connections between natural language and visual data by produced text line based contents from a given image. Our Hybrid Recurrent Neural Network model is based on the intricacies of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bi-directional Recurrent Neural Network (BRNN) models. We conducted experiments on three benchmark datasets, e.g., Flickr8K, Flickr30K, and MS COCO. Our hybrid model utilized LSTM model to encode text line or sentences independent of the object location and BRNN for word representation, this reduced the computational complexities without compromising the accuracy of the descriptor. The model produced better accuracy in retrieving natural language based description on the dataset.
Bangla Dataset-Online Publications
Institute of Advanced Engineering and Science (IAES), Aug 1, 2019
We presented a learning model that generated natural language description of images. The model ut... more We presented a learning model that generated natural language description of images. The model utilized the connections between natural language and visual data by produced text line based contents from a given image. Our Hybrid Recurrent Neural Network model is based on the intricacies of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bi-directional Recurrent Neural Network (BRNN) models. We conducted experiments on three benchmark datasets, e.g., Flickr8K, Flickr30K, and MS COCO. Our hybrid model utilized LSTM model to encode text line or sentences independent of the object location and BRNN for word representation, this reduced the computational complexities without compromising the accuracy of the descriptor. The model produced better accuracy in retrieving natural language based description on the dataset.
Books by Md. Asifuzzaman Jishan
Final year thesis-Preprint
Generating a natural language description from images is an important problem at the section of c... more Generating a natural language description from images is an important problem at the section of computer vision, natural language processing, artificial intelligence and image processing. Observing many recent works in deep learning sector, we introduced a hybrid RNN model which is generating text from the given input images. We presented the learning model that generates natural language of images. The model utilized the connections between natural language and visual data by produced text line based contents from a given image. Our Hybrid Recurrent Neural Network model is based on the combination of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Bi-directional Recurrent Neural Network (BRNN) models. We used three benchmark datasets: Flickr8K, Flickr30K and MS COCO for training our model and observed the accuracy improvement comparing with the state of the art work. A new Bangla dataset is also created which we named as BNLIT (Bangla Natural Language Image to Text) is made to generate Bangla caption from given input image. This dataset contains 8,700 images and all the images are in Bangladesh perspective images. Our hybrid model learns from a new set of data and annotations that reflect the Bangladeshi geographical context.
Thesis Chapters by Md. Asifuzzaman Jishan
Springer, Singapore, May 23, 2020
In protein structure prediction problem, DNA-binding protein identification plays a significant r... more In protein structure prediction problem, DNA-binding protein identification plays a significant role in various processes like transcription, DNA replication, DNA recombination, repair and modification. It has been a very active area of research to find an effective way to solve DNA-binding protein problem. The experimental methods that are employed for protein structure prediction are quite expensive and time consuming. Most of the methods have yielded better results in extracting evolutionary features. Recently, hidden Markov model (HMM) has been employed to extract features with remarkable increase in the efficiency for identification of DNA-binding proteins. In this study, a novel system based on HMM profile has been proposed to capture distant homology and evolutionary information. The experiments using the HMM profile model have been carried out on independent dataset with prediction accuracy 72% prediction accuracy, which is 3% better compared to the previous attempts. In this study, a comprehensive analysis of HMM profile model is conducted and the results are compared with other traditional models based on performances indices.
Drafts by Md. Asifuzzaman Jishan
Automatic image and digit recognition is a compu-tationally challenging task for the image proces... more Automatic image and digit recognition is a compu-tationally challenging task for the image processing and pattern recognition, requiring an adequate appreciation of the syntactic and semantic importance of the image for the identification of the handwritten digits. Image and Pattern Recognition has been identified as one of the driving forces in the research areas because of its shifting of different types of applications, such as safety frameworks, clinical frameworks, diversion, and so on. In this study, for recognition, we implemented a hybrid neural network model that is capable of recognizing the digit of MNIST dataset and achieved a remarkable result. The proposed neural model network can extract features from the image and recognize the features in the layer by layer. To expand, it is so important for the neural network to recognize how the proposed model can work in each layer, how it can generate output, and so on. Besides, it also can recognize the auto-encoding system and the variational auto-encoding system of the MNIST dataset. This study will explore those issues that are discussed above, and the explanation for them, and how this phenomenon can be overcome.
Uploads
Papers by Md. Asifuzzaman Jishan
Online Link -
1. http://doi.org/10.5281/zenodo.3372752 (Zenodo);
2. https://doi.org/10.7910/DVN/DZZ1ZB (Harvard Dataverse);
3. http://dx.doi.org/10.17632/ws3r82gnm8.1 (Mendeley);
4. https://www.kaggle.com/jishan900/bangla-natural-language-image-to-text-bnlit (Kaggle)
Books by Md. Asifuzzaman Jishan
Thesis Chapters by Md. Asifuzzaman Jishan
Drafts by Md. Asifuzzaman Jishan
Online Link -
1. http://doi.org/10.5281/zenodo.3372752 (Zenodo);
2. https://doi.org/10.7910/DVN/DZZ1ZB (Harvard Dataverse);
3. http://dx.doi.org/10.17632/ws3r82gnm8.1 (Mendeley);
4. https://www.kaggle.com/jishan900/bangla-natural-language-image-to-text-bnlit (Kaggle)