Tanjina Helaly

Mrs. Tanjina Helaly


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 October 2020
Verified
Conference Paper
Closed access
MSMesbah Sarif
Mesbah Sarif
Tanmoy Sarkar PiasTanmoy Sarkar Pias
Tanmoy Sarkar Pias
THTanjina Helaly
Tanjina Helaly
STSohel Rana Tutul
Sohel Rana Tutul
NRNymur Rahman
Nymur Rahman
A License Plate Recognition (LPR) is a technique to automatically identify and recognize the license plate of a vehicle. In today’s world where we want to do everything in no time, automated LPR has opened a new door in Intelligent Traffic System. With the help of ALPR, we can implement many smart systems starting from a parking facility to crime investigation. For effective License Plate Recognition, accurate License Plate Detection and License Plate Segmentation are crucial. Many existing algorithms are using different image processing and machine learning techniques for detection, segmentation, and recognition. These algorithms are highly computational extensive and somewhat unreliable. In our paper, we have proposed an end- to-end license plate recognition system for Bangladeshi vehicles. We have divided our system into three different phases. The first phase is license plate detection and localization. For that, we have used YOLOv3. In the second phase, we have implemented a custom segmentation algorithm specifically for Bangladeshi license plates which is robust and computationally fast. In the final phase, we have implemented a character recognition model with convolutional neural network (CNN). This recognition system has achieved 97.5% accuracy. Moreover, we have built a diversified dataset with 2000 images where we have tried to capture the environmental factors.

23 May 2020
Verified
Book Chapter
Closed access
PDF file
SHSafayet Hossain
Safayet Hossain
SSShowrav Saha
Showrav Saha
JAJannatul Ferdous Akhi
Jannatul Ferdous Akhi
THTanjina Helaly
Tanjina Helaly

22 April 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Nasima BegumNasima Begum
Nasima Begum
Rashik RahmanRashik Rahman
Rashik Rahman
NJNusrat Jahan
Nusrat Jahan
SKSaqib Sizan Khan
Saqib Sizan Khan
THTanjina Helaly
Tanjina Helaly
NKNipa Khatun
Nipa Khatun
Sign language is the most commonly used form of communication for persons with disabilities who have hearing or speech difficulties. However, persons without hearing impairment cannot understand these signs in many cases. As a consequence, persons with disabilities experience difficulties while expressing their emotions or needs. Thus, a sign character detection and text generation system is necessary to mitigate this issue. In this paper, we propose an end-to-end system that can detect Bengali sign characters from input images or video frames and generate meaningful sentences. The proposed system consists of two phases. In the first phase, a quantization technique for the YoloV4-Tiny detection model is proposed for detecting 49 different sign characters, including 36 Bengali alphabet characters, 10 numeric characters, and 3 special characters. Here, the detection model localizes hand signs and predicts the corresponding character. The second phase generates text from the predicted characters by a detection model. The Long Short-Term Memory (LSTM) model is utilized to generate meaningful text from the character signs detected in the previous phase. To train the proposed system, the BdSL 49 dataset is used, which has approximately 14,745 images of 49 different classes. The proposed quantized YoloV4-Tiny model achieves a mAP of 99.7%, and the proposed language model achieves an overall accuracy of 99.12%. In addition, performance analysis among YoloV4, YoloV4 Tiny, and YoloV7 models is provided in this research.

28 September 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
WHWaliul Hasan
Waliul Hasan
SSShahria Shanto
Shahria Shanto
JNJannatun Nayeema
Jannatun Nayeema
Rashik RahmanRashik Rahman
Rashik Rahman
THTanjina Helaly
Tanjina Helaly
Sk Tanzir MehediSk Tanzir Mehedi
Sk Tanzir Mehedi
Early fire detection is the key to saving lives and limiting property damage. Advanced technology can detect fires in high-risk zones with minimal human presence before they escalate beyond control. This study focuses on providing a more advanced model structure based on the YOLOv8 architecture to enhance early recognition of fire. Although YOLOv8 is excellent at real-time object detection, it can still be better adjusted to the nuances of fire detection. We achieved this advancement by incorporating an additional context-to-flow layer, enabling the YOLOv8 model to more effectively capture both local and global contextual information. The context-to-flow layer enhances the model’s ability to recognize complex patterns like smoke and flames, leading to more effective feature extraction. This extra layer helps the model better detect fires and smoke by improving its ability to focus on fine-grained details and minor variation, which is crucial in challenging environments with low visibility, dynamic fire behavior, and complex backgrounds. Our proposed model achieved a 2.9% greater precision rate, 4.7% more recall rate, and 4% more F1-score in comparison to the YOLOv8 default model. This study discovered that the architecture modification increases information flow and improves fire detection at all fire sizes, from tiny sparks to massive flames. We also included explainable AI strategies to explain the model’s decision-making, thus adding more transparency and improving trust in its predictions. Ultimately, this enhanced system demonstrates remarkable efficacy and accuracy, which allows additional improvements in autonomous fire detection systems.

30 December 2023 in Human Behavior and Emerging Technologies
Verified
Journal Article
Open access
PDF file
BFB. J. Ferdosi
B. J. Ferdosi
MRM. Rahman
M. Rahman
ASA. M. Sakib
A. M. Sakib
THTanjina Helaly
Tanjina Helaly
Online education has become an essential part of the modern education system, but keeping the integrity of the online examination remains a challenge. A significant increase in cheating in online examinations (from 29.9% before COVID-19 to 54.7% during COVID-19, as per a recent survey) points out the necessity of online exam proctoring systems. Traditionally, educational institutes utilize different questions in onsite exams: multiple-choice questions (MCQs), analytical questions, descriptive questions, etc. For online exams, form-based exams using MCQs are popular though in disciplines like math, engineering, architecture, art, or other courses, paper and pen tests are typical for proper assessment. In form-based exams, students’ attention is toward display devices, and cheating behavior is identified as the deviation of head and eye gaze direction from the display device. In paper- and pen-based exams, students’ main attention is on the answer script not on the device. Identifying cheating behavior in such exams is not a trivial task since complex body movements need to be observed to identify cheating. Previous research works focused on the deviation of the head and eyes from the screen which is more suited for form-based exams. Most of them are very resource-intensive; along with a webcam, they require additional hardware such as sensors, microphones, and security cameras. In this work, we propose an automated proctoring solution for paper- and pen-based online exams considering specific requirements of pen-and-paper exams. Our approach tracks head and eye orientations and lip movements in each frame and defines the movement as the change of orientation. We relate cheating with frequent coordinated movements of the head, eyes, and lips. We calculate a cheating score indicative of the frequency of movements. A case is marked as a cheating case if the cheating score is higher than the proctor-defined threshold (which may vary depending on the specific requirement of the discipline). The proposed system has five major parts: (1) identification and coordinate extraction of selected facial landmarks using MediaPipe; (2) orientation classification of the head, eye, and lips with K-NN classifier, based on the landmarks; (3) identification of abnormal movements; (4) calculation of a cheating score based on abnormal movement patterns; and (5) a visual representation of students’ behavior to support the proctor for early intervention. Our system is robust since it observes the pattern of movement over a sequence of frames and considers the coordinated movement pattern of the head, eye, and lips rather than considering a single deviation as a cheating behavior which will minimize the false positive cases. Visualization of the student behavior is another strength of our system that enables the human proctor to take preventive measures rather than punishing the student for the final cheating score. We collected video data with the help of 16 student volunteers from the authors’ university who participated in the two well-instructed mock exams: one with cheating and another without cheating. We achieved 100% accuracy in detecting noncheating cases and 87.5% accuracy for cheating cases when the threshold was set to 40.

25 August 2024 in Data in Brief
Verified
Journal Article
Open access
AMAbu Bakar Siddique Mahi
Abu Bakar Siddique Mahi
FEFarhana Sultana Eshita
Farhana Sultana Eshita
TCTabassum Chowdhury
Tabassum Chowdhury
Rashik RahmanRashik Rahman
Rashik Rahman
THTanjina Helaly
Tanjina Helaly
Security professionals and law enforcement, who presently have to manually go through hours of film to find minor incidents, are becoming more interested in automated crime and violence detection. Developments in computer vision and machine learning are enabling automated systems to quickly scan and mark relevant incidents, reducing the workload of human investigators. Most existing datasets tend to focus on too specific situations (e.g., vehicle violence). Typically, these datasets consist of a limited number of video clips gathered from various sources, such as YouTube. Furthermore, the lack of distinct action-based groups or precise diversity in these datasets may limit their broader usefulness. To overcome the constraints of existing datasets, we have developed a balanced dataset that includes 3020 video clips. This dataset is evenly divided between 1510 non-violent clips and 1510 violent clips, capturing a diverse range of real-world situations. The duration of the clips ranged from 3 to 12 seconds, and they were recorded by non-professional actors. The aim of this comprehensive and balanced approach is to offer an extended resource for the training and evaluation of automated video analysis systems.