Skip to main content

Research Repository

Advanced Search

All Outputs (22)

Kernelized dynamic convolution routing in spatial and channel interaction for attentive concrete defect recognition (2022)
Journal Article
Mandal, B. (2022). Kernelized dynamic convolution routing in spatial and channel interaction for attentive concrete defect recognition. Signal Processing: Image Communication, 116818 - 116818. https://doi.org/10.1016/j.image.2022.116818

Image/video based defect recognition is a crucial task in automating visual inspection of concrete structures. Although some progress has been made to automatically recognize defects in concrete structural images, significant challenges still exist.... Read More about Kernelized dynamic convolution routing in spatial and channel interaction for attentive concrete defect recognition.

MacularNet: Towards Fully Automated Attention-Based Deep CNN for Macular Disease Classification (2022)
Journal Article
Mandal, B. (2022). MacularNet: Towards Fully Automated Attention-Based Deep CNN for Macular Disease Classification. https://doi.org/10.1007/s42979-022-01024-0

AbstractIn this work, we propose an attention-based deep convolutional neural network (CNN) model as an assistive computer-aided tool to classify common types of macular diseases: age-related macular degeneration, diabetic macular edema, diabetic ret... Read More about MacularNet: Towards Fully Automated Attention-Based Deep CNN for Macular Disease Classification.

Perturbed Composite Attention Model for Macular Optical Coherence Tomography Image Classification (2021)
Journal Article
Mishra, S. S., Mandal, B., & Puhan, N. B. (2022). Perturbed Composite Attention Model for Macular Optical Coherence Tomography Image Classification. IEEE Transactions on Artificial Intelligence, 3(4), 625-635. https://doi.org/10.1109/tai.2021.3135797

In this article, we propose a deep architecture stemming from a perturbed composite attention mechanism with the following two novel attention modules: Multilevel perturbed spatial attention (MPSA) and multidimension attention (MDA) for macular optic... Read More about Perturbed Composite Attention Model for Macular Optical Coherence Tomography Image Classification.

Interleaved Deep Artifacts-Aware Attention Mechanism for Concrete Structural Defect Classification. (2021)
Journal Article
Mandal, B. (2021). Interleaved Deep Artifacts-Aware Attention Mechanism for Concrete Structural Defect Classification. IEEE Transactions on Image Processing, 6957 - 6969. https://doi.org/10.1109/TIP.2021.3100556

Automatic machine classification of concrete structural defects in images poses significant challenges because of multitude of problems arising from the surface texture, such as presence of stains, holes, colors, poster remains, graffiti, marking and... Read More about Interleaved Deep Artifacts-Aware Attention Mechanism for Concrete Structural Defect Classification..

GlaucoNet: Patch-Based Residual Deep Learning Network for Optic Disc and Cup Segmentation Towards Glaucoma Assessment (2021)
Journal Article
Mandal, B. (2021). GlaucoNet: Patch-Based Residual Deep Learning Network for Optic Disc and Cup Segmentation Towards Glaucoma Assessment. https://doi.org/10.1007/s42979-021-00491-1

Glaucoma is a chronic eye condition causing irreversible vision damage and presently stands as the second leading cause of blindness worldwide. Damaged optic disc and optic cup assessment in color fundus image has been shown to be a promising method... Read More about GlaucoNet: Patch-Based Residual Deep Learning Network for Optic Disc and Cup Segmentation Towards Glaucoma Assessment.

Multi-Deformation Aware Attention Learning for Concrete Structural Defect Classification (2020)
Journal Article
Bhattacharya, G., Mandal, B., & Puhan, N. B. (2020). Multi-Deformation Aware Attention Learning for Concrete Structural Defect Classification. IEEE Transactions on Circuits and Systems for Video Technology, 31(9), 3707-3713. https://doi.org/10.1109/TCSVT.2020.3028008

In this work, we propose a deep multi-deformation aware attention learning (MDAL) architecture comprising of multi-scale committee of attention (MSCA) and fine-grained feature induced attention (FGIA) modules to classify multi-target multi-class defe... Read More about Multi-Deformation Aware Attention Learning for Concrete Structural Defect Classification.

Multi-level Dual-attention Based CNN for Macular Optical Coherence Tomography Classification (2019)
Journal Article
Mandal, B. (2019). Multi-level Dual-attention Based CNN for Macular Optical Coherence Tomography Classification. IEEE Signal Processing Letters, 1793-1797. https://doi.org/10.1109/LSP.2019.2949388

In this letter, we propose a multi-level dual-attention model to classify two common macular diseases, age-related macular degeneration (AMD) and diabetic macular edema (DME) from normal macular eye conditions using optical coherence tomography (OCT)... Read More about Multi-level Dual-attention Based CNN for Macular Optical Coherence Tomography Classification.

Deep Convolutional Generative Adversarial Network-Based Food Recognition Using Partially Labeled Data (2019)
Journal Article
Mandal, B., Puhan, N. B., & Verma, A. (2019). Deep Convolutional Generative Adversarial Network-Based Food Recognition Using Partially Labeled Data. IEEE Sensors Letters, 3(2), Article ARTN 7000104. https://doi.org/10.1109/LSENS.2018.2886427

Traditional machine learning algorithms using hand-crafted feature extraction techniques (such as local binary pattern) have limited accuracy because of high variation in images of the same class (or intraclass variation) for food recognition tasks.... Read More about Deep Convolutional Generative Adversarial Network-Based Food Recognition Using Partially Labeled Data.

Deep Residual Network with Regularized Fisher Framework for Detection of Melanoma (2018)
Journal Article
Mandal, B. (2018). Deep Residual Network with Regularized Fisher Framework for Detection of Melanoma. IET Computer Vision, 1096-1104. https://doi.org/10.1049/iet-cvi.2018.5238

Of all the skin cancer that is prevalent, melanoma has the highest mortality rates. Melanoma becomes life threatening when it penetrates deep into the dermis layer unless detected at an early stage, it becomes fatal since it has a tendency to migrate... Read More about Deep Residual Network with Regularized Fisher Framework for Detection of Melanoma.

SocioGlass: Social interaction assistance with face recognition on google glass (2016)
Journal Article
Mandal, B. (2016). SocioGlass: Social interaction assistance with face recognition on google glass. https://doi.org/10.1186/s41070-016-0011-8

We present SocioGlass - a system built on Google Glass paired with a mobile phone that provides a user with in-situ information about an acquaintance in face-to-face communication. The system can recognize faces from the live feed of visual input. Ac... Read More about SocioGlass: Social interaction assistance with face recognition on google glass.