Afsana Ahsan Jeny

Afsana Ahsan Jeny

Auto-generated profile, based on publicly available information

Afsana Ahsan Jeny

Computer Science and Engineering, University of Connecticut, Storrs, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
23 December 2021 in IEEE Access
Verified
Journal Article
Open access
MJMasum Shah Junayed
Masum Shah Junayed
Md Baharul IslamMd Baharul Islam
Md Baharul Islam
AJAfsana Ahsan Jeny
Afsana Ahsan Jeny
ASArezoo Sadeghzadeh
Arezoo Sadeghzadeh
TBTopu Biswas
Topu Biswas
A. F. M. Shahen ShahA. F. M. Shahen Shah
A. F. M. Shahen Shah
Acne scarring occurs in 95% of people with acne vulgaris due to collagen loss or gains when the body is healing the damages of the skin caused by acne inflammation. Accurate classification of acne scars is a vital factor in providing a timely, effective treatment protocol. Dermatologists mainly recognize the type of acne scars manually based on visual inspections, which are time- and energy-consuming and subject to intra- and inter-reader variability. In this paper, a novel automated acne scar classification system is proposed based on a deep Convolutional Neural Network (CNN) model. First, a dataset of 250 images from five different classes is collected and labeled by four well-experienced dermatologists. The pre-processed input images are fed into our proposed model, namely ScarNet , for deep feature map extraction. The optimizer, loss function, activation functions, filter and kernel sizes, regularization methods, and the batch size of the proposed architecture are tuned so that the classification performance is maximized while minimizing the computational cost. Experimental results demonstrate the feasibility of the proposed method with accuracy, specificity, and kappa score of 92.53%, 95.38%, and 76.7%, respectively.

1 August 2022 in IEEE Access
Verified
Journal Article
Open access
AJAfsana Ahsan Jeny
Afsana Ahsan Jeny
Md Baharul IslamMd Baharul Islam
Md Baharul Islam
MJMasum Shah Junayed
Masum Shah Junayed
DDDebashish Das
Debashish Das
Recently, learned image compression algorithms have shown incredible performance compared to classic hand-crafted image codecs. Despite its considerable achievements, the fundamental disadvantage is not optimized for retaining local redundancies, particularly non-repetitive patterns, which have a detrimental influence on the reconstruction quality. This paper introduces the autoencoder-style network-based efficient image compression method, which contains three novel blocks, i.e., adjacent attention block, Gaussian merge block, and decoded image refinement block, to improve the overall image compression performance. The adjacent attention block allocates the additional bits required to capture spatial correlations (both vertical and horizontal) and effectively remove worthless information. The Gaussian merge block assists the rate-distortion optimization performance, while the decoded image refinement block improves the defects in low-resolution reconstructed images. A comprehensive ablation study analyzes and evaluates the qualitative and quantitative capabilities of the proposed model. Experimental results on two publicly available datasets reveal that our method outperforms the state-of-the-art methods on the KODAK dataset (by around 4dB and 5dB) and CLIC dataset (by about 4dB and 3dB) in terms of PSNR and MS-SSIM.

1 December 2018
Verified
Conference Paper
Closed access
AJAfsana Ahsan Jeny
Afsana Ahsan Jeny
MJMasum Shah Junayed
Masum Shah Junayed
SASyeda Tanjila Atik
Syeda Tanjila Atik
Globalization has enhanced the transportation system resulting in the increased mobility of the people all around the world. More people are now travelling outside their own border for self-refreshment or business purpose. The task of the immigration officers in the airport thus has become more challenging now-a-days. Moreover, there are many countries whose people are restricted from travelling to other certain countries. Hence, the country identification by analyzing only the passport cover can reduce both time and hassle greatly by detecting those unauthorized travelers. In our paper, we present a model for country recognition by analyzing any passport cover using a deep Convolutional Neural Network (CNN) model based on the Residual Network architecture with 50 layers termed as ResNet50. We have experimented our model with images of seven passport covers of seven different countries from different angles and found an average accuracy rate of 98.56%. Our model can also be enhanced to detect fake and forged passports.


16 March 2022
Verified
Book Chapter
Closed access
PDF file
MJMasum Shah Junayed
Masum Shah Junayed
AJAfsana Ahsan Jeny
Afsana Ahsan Jeny
Lavdie RadaLavdie Rada
Lavdie Rada
Md Baharul IslamMd Baharul Islam
Md Baharul Islam

12 October 2025
Verified
Conference Paper
Open access
AJAfsana Ahsan Jeny
Afsana Ahsan Jeny
SHSahand Hamzehei
Sahand Hamzehei
MKMostafa Karami
Mostafa Karami
SBStephen Andrew Baker
Stephen Andrew Baker
TRTucker Van Rathe
Tucker Van Rathe
SNSheida Nabavi
Sheida Nabavi