A. F. M. Saifuddin Saif

Work place: Department of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh

E-mail: saif@aiub.edu


Research Interests: Medical Image Computing, Artificial Intelligence, Computer Vision, Image Processing


A.F.M. Saifuddin Saif received Ph.D. from Faculty of Information Science and Technology, University Kebangsaan Malaysia (UKM) in 2016. He received M.Sc. in Computer System Engineering (Software System) from University of East London, UK, and B.Sc. (Eng.) degree in Computer Science and Engineering from Shahjalal University of Science and Technology, Bangladesh in 2012 and 2008, respectively. Most of his contributions in Computer Vision and Artificial Intelligence Research field were published in ISI Q1 journals. He has published many papers in ISI indexed Journals; Scopus indexed Journals, Book Chapters, Conferences, and Proceedings. He served as Technical Committee Members, Reviewers, Guest Speakers, Session Chairs in many Conferences and Workshops. Currently, he is an Assistant Professor at the Faculty of Information Science and Technology, American International University Bangladesh (AIUB). Before joining the university, he did Post Doctorate at Faculty of Information Science and Technology, University Kebangsaan Malaysia. He spent more than 6 years in the IT industry such as Advanced Software Development, Web eMaze, etc as IT researcher. His research interests include Image Processing, Computer Vision, Artificial Intelligence, Augmented Reality, 3D Reconstruction, and Medical Image Processing.

Author Articles
Robust Underwater Fish Detection Using an Enhanced Convolutional Neural Network

By Dipta Gomes A. F. M. Saifuddin Saif

DOI: https://doi.org/10.5815/ijigsp.2021.03.04, Pub. Date: 8 Jun. 2021

Underwater Object Detection is one of the most challenging and unexplored domains in this area of Computer Vision. The proposed research refines the image enhancement of under-water imagery by proposing an improvement of already existing tools for underwater Object detection. The comparative study clearly depicts the enhancement of the proposed method with respect to the existing methods for underwater object detection. Moreover, a framework for detection of underwater organisms such as fishes are proposed, which will act as the steppingstone for re- serving the ecosystem of the whole fish community. Mostly the object detection using deep learning has been the prime goal to this research and the comparison between other preexisting methods are compared at the end. As a result, techniques that are already well established will be used for overall enhancement of those images. Through this enhancement and through finding a healthy environment for their breeding ground, the extinction of selected species of fishes is can be diminished and decreased. All this is carried out by overcoming difficulties underwater through a novel technique that can be integrated into an Underwater Autonomous Vehicle and can be classified as robust in nature. Robustness will depend on three important factors in this research, first is accuracy, then fast and lastly being upgradeable. The proposed method is a modified VGGNet-16, which is trained using the ImageCLEF FISH_TS dataset. The overall result provides an accuracy of 96.4% which surpasses all its predecessors.

[...] Read more.
Data Analysis and Visualization of Continental Cancer Situation by Twitter Scraping

By Md. Hosne Al Walid D. M. Anisuzzaman A. F. M. Saifuddin Saif

DOI: https://doi.org/10.5815/ijmecs.2019.07.03, Pub. Date: 8 Jul. 2019

With the advent of user-generated content, usability, and interoperability of web platforms, people are today more eager to express and share their opinions on the web regarding both daily activities and global issues. Cancer is often undetected, leading to serious issues which continue to affect a person's life and his surroundings. Recently Twitter has been very popular to be used to predict and monitor real-world outcomes as well as health-related concerns. Nowadays people are using social media in any situation. Even cancer patients, their friends, and family are increasingly sharing their experience in social media, which has increased the ability of patients to find others similar to their conditions to discuss treatment options, suggest lifestyle changes, and to offer support. Our work targets to link patients with a particular illness (cancer) together and to provide researchers with enriched patient data that might be very useful for future analysis of this disease. We wanted to create a meeting point for the healthcare sector and social media through our work. Our target was to collect Twitter data from different continents of the world and analyze them. We scraped tweets from over the last two years from all around the world. Then clean the data using a regular expression and then process it to prepare our own dataset. We used sentiment analysis and natural language processing to classify them into positive, negative and neutral tweets to determine which of the tweet means to have cancer and which don't. We then analyzed the prepared dataset and visualized and compared them with veritable cancer-related information to ascertain if people's tweets are allied with actual cancer situation.

[...] Read more.
Category Specific Prediction Modules for Visual Relation Recognition

By Sohan Chowdhury Tanbirul Hashan Afif Abdur Rahman A. F. M. Saifuddin Saif

DOI: https://doi.org/10.5815/ijmsc.2019.02.02, Pub. Date: 8 Apr. 2019

Object classification in an image does not provide a complete understanding of the information contained in it. Visual relation information such as “person playing with dog” provides substantially more understanding than just “person, dog”. The visual inter-relations of the objects can provide substantial insight for truly understanding the complete picture. Due to the complex nature of such combinations, conventional computer vision techniques have not been able to show significant promise. Monolithic approaches are lacking in precision and accuracy due to the vastness of possible relation combinations. Solving this problem is crucial to development of advanced computer vision applications that impact every sector of the modern world. We propose a model using recent advances in novel applications of Convolution Neural Networks (Deep Learning) combined with a divide and conquer approach to relation detection. The possible relations are broken down to categories such as spatial (left, right), vehicle-related (riding, driving), etc. Then the task is divided to segmenting the objects, estimating possible relationship category and performing recognition on modules specially built for that relation category. The training process can be done for each module on significantly smaller datasets with less computation required. Additionally this approach provides recall rates that are comparable to state of the art research, while still being precise and accurate for the specific relation categories.

[...] Read more.
A Review based on Brain Computer Interaction using EEG Headset for Physically Handicapped People

By A. F. M. Saifuddin Saif MD. Ryhan Hossain Redwan Ahmed Tamanna Chowdhury

DOI: https://doi.org/10.5815/ijeme.2019.02.04, Pub. Date: 8 Mar. 2019

The universes’ most complex structure is the human brain. To analyze its characteristics, many studies and experiments have been carried out in a proper and systematic manner. From these researches and experiments, scientists have learnt to communicate with computer using brain and hence, BCI has been developed. A Brain-Computer Interface (BCI) provides a communication path between the human brain and the computer system. With the advancement of information technology and neuroscience, there has been a flow of interest in turning fiction into reality. This research investigated existing works of BCI with the purpose developing a system that allows physically challenged people to communicate with other persons and helps to interact with the external environments with the help of computers. Components like, comparison of invasive and non-invasive technologies to measure brain activity, evaluation of control signals (i.e. patterns of brain activity or brain waves that can be used for communication), development or improvement of algorithms for translation of brain signals into computer commands, specific frequency components like electroencephalography (EEG), artificial neural network (ANN) etc. are used to accomplish such a feat. With such, the developments of new BCI applications are emerging every day.

[...] Read more.
Online Trial Room based on Human Body Shape Detection

By D. M. Anisuzzaman Md. Hosne Al Walid A. F. M. Saifuddin Saif

DOI: https://doi.org/10.5815/ijigsp.2019.02.03, Pub. Date: 8 Feb. 2019

High returning rate of garments products have become a notable problem for online fashion shopping. This problem is partially caused by using different standards for measuring cloth sizes on different websites. In this research, we have designed a set of equipment to capture images of t-shirts of any color and propose an automatic cloth measurement approach using image processing techniques. A method has been introduced to recognize feature points, which has been used to calculate the cloth sizes. The method has provided a useful and efficient tool for cloth measurement. The photographs have been taken in a controlled environment, and then clothes have been categorized with the proportions of the neck, shoulder, chest width, upper waist, lower waist, and length. In this method, we have measured the t-shirt size for men by calculating the chest width and length of men. For this, a dataset has been created in a specific environment. This method has integrated with a web-based application. We have validated our work by calculating RMSE values.

[...] Read more.
Aggressive Action Estimation: A Comprehensive Review on Neural Network Based Human Segmentation and Action Recognition

By A. F. M. Saifuddin Saif Md. Akib Shahriar Khan Abir Mohammad Hadi Rahul Prashad Karmoker Julian Gomes

DOI: https://doi.org/10.5815/ijeme.2019.01.02, Pub. Date: 8 Jan. 2019

Human action recognition has been a talked topic since machine vision was coined. With the advent of neural networks and deep learning methods, various architectures were suggested to address the problems within a context. Convolutional neural network has been the primary go-to architecture for image segmentation, flow estimation and action recognition in recent days. As the problem itself is an extended version of various sub-problems, such as frame segmentation, spatial and temporal feature extraction, motion modeling and action classification as a whole, some methods reviewed in this paper addressed sub-problems and some tried to address a single architecture to the action recognition problem. While being a success, convolution neural networks have drawbacks in its pooling methods. CapsNet, on the other hand, uses squashing function to determine the activation. Also it addresses spatiotemporal information with the normalized vector maps while CNN-based methods extracts feature map for spatial and temporal information and later augment them in a fusion layer for combining two separate feature maps. Critical review of papers provided in this work can contribute significantly in addressing human action recognition problem as a whole.

[...] Read more.
Anomaly Detection in Crowded Scene by Pedestrians Behaviour Extraction using Long Short Term Method: A Comprehensive Study

By Anupam Dey Fahad Mira Saleque Ahmed Raiyan Sharif A. F. M. Saifuddin Saif

DOI: https://doi.org/10.5815/ijeme.2019.01.05, Pub. Date: 8 Jan. 2019

With the expansion of worldwide security concerns and a consistently expanding requirement for successful checking of open places, i.e. air terminals, railroad stations, shopping centres, crowded sports fields, army bases or smart healthcare facilities such as daily activity monitoring and fall detection in old people’s homes is increasing very rapidly. The visual occlusions and ambiguities in crowded scenes, usage of suitable method and in addition the perplexing practices and scene semantics make the investigation a challenging task. This research demonstrates comprehensive and critical analysis of crowd scene involves in object detection, tracking, feature extraction and learning from visual surveillance which helps to recognize behavioural pattern. This research refers scene understanding as scene layout, i.e. finding streets, structures, side-walks, vehicles turning, person on foot intersection and scene status such as crowd congestion, split, merge etc. The  significance of the proposed comprehensive review to create crowd administration procedures and help the development of the group or people, to maintain a strategic distance from the group calamities and guarantee general society security. Based on the observation of previous research in three aspects, i.e. review based on methods, frameworks and critical existing results analysis, this research propose a framework for anomaly detection in crowded scene using LSTM (long Short-Term Method).  Proposed comprehensive review is expected to contribute significantly for the investigation of behavior pattern analysis in computer vision research domains.

[...] Read more.
Real Time Bangla Vehicle Plate Recognition towards the Need of Efficient Model - A Comprehensive Study

By A. F. M. Saifuddin Saif Mohammad Jaber Hossain Md. Hasan Uzzaman Mobinur Rahman MD.Tawhid Islam

DOI: https://doi.org/10.5815/ijigsp.2018.12.04, Pub. Date: 8 Dec. 2018

Bangla vehicle number plate recognition is still an unsolved research issue for efficient investigation of unregistered vehicles, traffic observation, management and most importantly for Intelligent Transportation System (ITS). Previous research on vehicle plate recognition have been suffering various challenges, i.e. capturing high level image from moving vehicles, number plate with complicated background, detection from different tilt and angle, detection in different lightening conditions and weather conditions, recognition of doubtful and ambiguous signs in road time road scenario. The main aim of this research is to provide critical analysis on various perspectives of vehicle plate recognition, i.e. Extraction of vehicle plates from vehicle, Segmentation of characters and finally, Recognition of segmented characters. At first, this research illustrates comprehensive reviews on existing methods. After that, existing frameworks are analyzed based on overall advantages and disadvantages for each steps in the previous research. Finally, extensive experimental validation is depicted in five aspects, i.e. method, accuracy, processing time, datasets and relevancy with real time scenario. Proposed comprehensive reviews are expected to contribute significantly to perform efficient vehicle plate recognition in Intelligent Transportation System (ITS) research.

[...] Read more.
Efficient Framework Using Morphological Modeling for Frequent Iris Movement Investigation towards Questionable Observer Detection

By D. M. Anisuzzaman A. F. M. Saifuddin Saif

DOI: https://doi.org/10.5815/ijigsp.2018.11.04, Pub. Date: 8 Nov. 2018

This research presents a framework to detect a questionable observer depending on a specific activity named “frequent iris movement”. We have focused on some activities and behaviors upon which we can classify one as questionable. So this research area is not only an important part of computer vision and artificial intelligence, but also a major part of human activity recognition (HAR). We have used Haar Cascade Classifier to detect irises of both left and right eyes. Then running some morphological operation we have detected the midpoint between left and right irises; and based on some characteristics of midpoint movement we have detected a specific activity – frequent iris movement. Depending on this activity we are declaring someone as questionable observer. To validate this research we have created our own dataset with 86 videos, where 15 individuals have volunteered. We have achieved an accuracy of 90% for the first 100 frames or 3.33 seconds of each of our videos and an accuracy of 93% for the first 150 frames or 5.00 seconds of each of our videos. No work has been done yet on basis of this specific activity to detect someone as questionable and furthermore our work outperforms most of the existing work on questionable observe detection and suspicious activity recognition. 

[...] Read more.
Efficient Mathematical Procedural Model for Brain Signal Improvement from Human Brain Sensor Activities

By Rajib Chowdhury A. F. M. Saifuddin Saif

DOI: https://doi.org/10.5815/ijigsp.2018.10.05, Pub. Date: 8 Oct. 2018

Human brain signals obtained by the human brain sensor electrodes measure the cerebral activities on the human brain. The main aim of our research is to improve the human brain activities based on the human brain signal. The entire procedure contains three steps. The first step is to acquire the brain signal, then develop this brain signal with the proposed method and finally improve the human brain activities with this modified brain signal. The entire procedure will proceed in a proposed Neuroheadset device embedded with necessary sensors using the non-invasive technique. This device will help to acquire the brain signal, modify this signal and improve the brain activities with this modified brain signal. In this research, we illustrated the first two steps like signal acquisition and signal modification. In the experiment, we used Electroencephalogram as an efficient non-invasive signal acquisition technique for acquiring the brain signal and also introduced a proposed method to modify this signal. This method helped to improve the human brain signal using the required times of the iteration process. In the experiment level, several iteration processes have been done to get above 90% improvement rate of the brainwaves. In this research, the improved signal has been considered based on the generated brain signal in various aspects like human intelligence, memory and also the capability of better feelings.

[...] Read more.
Traffic Sign Detection based on Color Segmentation of Obscure Image Candidates: A Comprehensive Study

By Dip Nandi A. F. M. Saifuddin Saif Prottoy Paul Kazi Md. Zubair Seemanta Ahmed Shubho

DOI: https://doi.org/10.5815/ijmecs.2018.06.05, Pub. Date: 8 Jun. 2018

Automated Vehicular System has become a necessity in the current technological revolution. Real Traffic sign detection and recognition is a vital part of that system that will find roadside traffic signs to warn the automated system or driver beforehand of the physical conditions of roads. Mostly, researchers based on Traffic sign detection face problems such as locating the sign, classifying it and distinguishing one sign from another. The most common approach for locating and detecting traffic signs is the color information extraction method. The accuracy of color information extraction is dependent upon the selection of a proper color space and its capability to be robust enough to provide color analysis data. Techniques ranging from template matching to critical Machine Learning algorithms are used in the recognition process. The main purpose of this research is to give a review based on methods and framework of Traffic Sign Detection and Recognition solution and discuss also the current challenges of the whole solution.

[...] Read more.
Other Articles