Publications

DIANA: A deep learning-based paprika plant disease and pest phenotyping system with disease severity analysis

Published in Frontiers in Plant Science, 2022

By taking a single image as input, our algorithm is able to generate detailed descriptive phrases (user-defined) that display the location, severity stage, and visual attributes of all the abnormalities that are present in the image.

Ilyas, T., Jin, H. et al. A pixel-level coarse-to-fine image segmentation labelling algorithm. Sci Rep 12, 8672 (2022). https://doi.org/10.1038/s41598-022-12532-7

A Pixel-Level Coarse-to-Fine Image Segmentation Labelling Algorithm

Published in Nature Scientific Reports, 2022

A novel method for efficiently creating pixel-level fine segmentation labelling that significantly reduces the amount of necessary human labor.

Lee, J., Ilyas, T., Jin, H. et al. A pixel-level coarse-to-fine image segmentation labelling algorithm. Sci Rep 12, 8672 (2022). https://doi.org/10.1038/s41598-022-12532-7

TSFD-Net: Tissue specific feature distillation network for nuclei segmentation and classification.

Published in Elsevier Neural Networks, 2022

Tissue specific feature distillation network for cancer detection.

Ilyas, T., Mannan, Z.I., Khan, A., Azam, S., Kim, H. and De Boer, F., 2022. TSFD-Net: Tissue specific feature distillation network for nuclei segmentation and classification. Neural Networks.

Multi-Scale Context Aggregation for Strawberry Fruit Recognition and Disease Phenotyping

Published in IEEE Access, 2021

A deep learning based Strawberry fruit and disease phenotyping.

Ilyas, Talha, Abbas Khan, Muhammad Umraiz, Yongchae Jeong, and Hyongsuk Kim. "Multi-Scale Context Aggregation for Strawberry Fruit Recognition and Disease Phenotyping." IEEE Access 9 (2021): 124491-124504.

DAM: Hierarchical Adaptive Feature Selection Using Convolution Encoder Decoder Network for Strawberry Segmentation

Published in Frontiers in Plant Science, 2021

A dynamic feature selection mechanism for Strawberry fruit phenotyping via deep learning.

Ilyas, T., Umraiz, M., Khan, A., & Kim, H. (2021). DAM: Hierarchical Adaptive Feature Selection Using Convolution Encoder Decoder Network for Strawberry Segmentation. Frontiers in plant science, 12, 189.

CED-Net: Crops and Weeds Segmentation for Smart Farming Using a Small Cascaded Encoder-Decoder Architecture

Published in MDPI Electronics, 2020

A semantic segmentation method based on a cascaded encoder-decoder network to differentiate between weeds and crops for precision agriculture.

Khan, A., Ilyas, T., Umraiz, M., & Kim, H. (2021). CED-Net: Crops and Weeds Segmentation for Smart Farming Using a Small Cascaded Encoder-Decoder Architecture. MDPI, Electronics, 2020, 9(10), 1602.

LIP Net: Real-Time Semantic Segmentation of Person Body Parts

Published in ICROS 35th symposium, 2020

This paper we proposes an architecture for real-time pixel-wise semantic segmentation for human body parts.

Ilyas, T., & Kim, H. (2021). LIP Net: Real-Time Semantic Segmentation of Person Body Parts. Proceedings of the domestic conference of the Control Robot System Society(ICROS), 2020, 110-112.

Low-Cost 3D Sensor System: Using Image-based Laser Triangulation

Published in ICROS 35th symposium, 2020

An Image-based laser Triangulation system for measuing the diseance form images for 3D deep learning and robotics.

Khan, A., Ilyas, T., Umraiz, M., & Kim, H. (2021). CED-Net: Crops and Weeds Segmentation for Smart Farming Using a Small Cascaded Encoder-Decoder Architecture. Proceedings of the domestic conference of the Control Robot System Society(ICROS), 2020, 105-107.

Tumor Detection in Breast Histopathology Images via modified Faster-RCNN

Published in ICROS 35th symposium, 2020

An algorithm for converting classical histopathology annotations to bounding box annotations is introduced in this paper. As a result, current state-of-the-art models could be used for tumor detection without having to relabel the data.

Ilyas, T., Kim, S. & Kim, H. (2021). Tumor Detection in Breast Histopathology Images via modified Faster-RCNN. Proceedings of the domestic conference of the Control Robot System Society(ICROS), 2021.

SEEK: A Framework of Superpixel Learning with CNN Features for Unsupervised Segmentatio

Published in MDPI Electronics, 2020

An Unsupervised algorithm fo semantic secene parsing by using deep CNNs to learn superpixel represenetations.

Ilyas, T., Khan, A., Umraiz, M., & Kim, H. (2021). SEEK: A Framework of Superpixel Learning with CNN Features for Unsupervised Segmentation. MDPI, Electronics, 2020, 9(3), 383.

Talha Ilyas

Publications