Automatic Monocular System for Human Fall Detection Based on Variations in Silhouette Area
- Behzad Mirmahboub, S. Samavi, N. Karimi, S. Shirani
- Computer ScienceIEEE Transactions on Biomedical Engineering
- 1 February 2013
This paper proposes to use variations in silhouette area that are obtained from only one camera to find the silhouette, and shows that the proposed feature is view invariant.
Polyp Segmentation in Colonoscopy Images Using Fully Convolutional Network
- Mojtaba Akbari, Majid Mohrekesh, K. Najarian
- Computer Science, MedicineAnnual International Conference of the IEEE…
- 1 February 2018
Evaluation of the proposed polyp segmentation method using the CVC-ColonDB database shows that the proposed method achieves more accurate results in comparison with previous colonoscopy video-segmentation methods.
Skin lesion segmentation in clinical images using deep learning
- M. Jafari, N. Karimi, K. Najarian
- Computer ScienceInternational Conference on Pattern Recognition
- 1 December 2016
The experimental results show that the proposed method for accurate extraction of lesion region can outperform the existing state-of-the-art algorithms in terms of segmentation accuracy.
ReDMark: Framework for residual diffusion watermarking based on deep networks
- Mahdi Ahmadi, Alireza Norouzi, N. Karimi, S. Samavi, Ali Emami
- Computer ScienceExpert systems with applications
- 15 May 2020
Fast exposure fusion using exposedness function
- M. Nejati, Maryam Karimi, S. Soroushmehr, N. Karimi, S. Samavi, K. Najarian
- Computer ScienceInternational Conference on Information Photonics
- 1 September 2017
Experimental results demonstrate that the proposed exposure fusion method is much faster than competing methods and can achieve state-of-the-art performance objectively and perceptually.
ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks
- Mahdi Ahmadi, Alireza Norouzi, Ali Emami
- Computer ScienceArXiv
- 16 October 2018
A deep end-to-end diffusion watermarking framework (ReDMark) which can be adapted for any desired transform space and has its capability to diffuse watermark information among a relatively wide area of the image.
Numerical investigation of heat transfer enhancement in a pipe partially filled with a porous material under local thermal non-equilibrium condition
- Y. Mahmoudi, N. Karimi
- Physics
- 2014
Linear and non-linear forced response of a conical, ducted, laminar premixed flame
- N. Karimi, M. Brear, Seong-Ho Jin, J. Monty
- Physics
- 1 November 2009
Boosted Dictionary Learning for Image Compression
- M. Nejati, S. Samavi, N. Karimi, S. Soroushmehr, K. Najarian
- Computer ScienceIEEE Transactions on Image Processing
- 1 October 2016
A boosted dictionary learning framework is presented to construct an ensemble of complementary specialized dictionaries for sparse image representation and a new image compression algorithm is developed using boosted multi-scale dictionaries learned in the wavelet domain.
Vessel extraction in X-ray angiograms using deep learning
- E. Nasr-Esfahani, S. Samavi, K. Najarian
- Computer ScienceAnnual International Conference of the IEEE…
- 1 August 2016
Experimental results on angiography images of a dataset show that the proposed deep learning approach using convolutional neural networks has a superior performance in extraction of vessel regions.
...
...