Saif Zahir
Research Subjects
Saif Zahir has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Rejaul Chowdhury
University of Northern British Columbia, Prince George, BC, V2N 4Z9, Canada
2 shared publications - Deborah C. Poff
University of Northern British Columbia
1 shared publication - Geoffrey W. Payne
Northern Medical Program, University of Northern British Columbia;
1 shared publication - Han Donker
College of Business and Public Policy/Accounting and Finance Dept, University of Alaska Anchorage, Anchorage, Alaska, United States
1 shared publication - Lele Zhou
Computer Science Department, The University of Northern British Columbia, 3333 University Way, Prince George, BC, Canada, V2N 4Z9
1 shared publication - Radwa Hammad
Computer Science Department, UNBC, Prince George, Canada
1 shared publication
Latest Publications
- Open Access
- 1 January 2015
- Published by Springer Nature
- p. 473-488
mHealth Portable Systems and Platforms
- 1 January 2015
- Published by Springer Nature
- p. 473-488
Open AccessmHealth Portable Systems and Platforms
- 5 October 2007
- Published by Springer Nature in Journal of Business Ethics
- Vol. 82 (3) , 527-537
Corporate Values, Codes of Ethics, and Firm Performance: A Look at the Canadian Context
- 5 October 2007
- Published by Springer Nature in Journal of Business Ethics
- Vol. 82 (3) , 527-537
Corporate Values, Codes of Ethics, and Firm Performance: A Look at the Canadian Context
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 781-786
A Hybrid 2-3-3 Bits-Based Image Encoding Scheme
In this paper, we present a hybrid 2-3-3 bits based encoding scheme for gray scale images. In this scheme, the gray scale image is converted to its equivalent 8-binary maps. We employ our lossless block coding technique along with a two-dimensional information preserving skip-line routine on the two most significant binary maps. Then, we apply our lossy block coding technique along with a lossy skip-line routine to the next three binary maps. Finally, the three least significant binary maps are set to zero. We tested this scheme on a large set of images of different sizes and applications. The simulation results show that the proposed scheme outperformed the standard JPEG compression in most of the cases while maintained high SNR values
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 781-786
A Hybrid 2-3-3 Bits-Based Image Encoding Scheme
In this paper, we present a hybrid 2-3-3 bits based encoding scheme for gray scale images. In this scheme, the gray scale image is converted to its equivalent 8-binary maps. We employ our lossless block coding technique along with a two-dimensional information preserving skip-line routine on the two most significant binary maps. Then, we apply our lossy block coding technique along with a lossy skip-line routine to the next three binary maps. Finally, the three least significant binary maps are set to zero. We tested this scheme on a large set of images of different sizes and applications. The simulation results show that the proposed scheme outperformed the standard JPEG compression in most of the cases while maintained high SNR values
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21627843,p. 776-780
Automated Assessment of Erythrocyte Disorders Using Artificial Neural Network
In this paper, we employ artificial neural network (ANN) together with image analysis techniques to automate the assessment of erythrocyte disorders using blood parameters such as red blood cell (RBC) count, hemoglobin (Hgb) level, and mean corpuscular hemoglobin (MCH). The neural network is trained using 800 blood sample images collected from the Prince George-EC, Hospital. The images are captured using a high-resolution digital camera mounted on a microscope. The red, green, and blue values of each image are fed as the input of the neural network. The Hospital RBC, Hgb values of the samples measured using hydrodynamic focused analyzer (CELL-DYN 3200 System) are provided as the target values during training. Several variations of the back propagation-learning algorithm were applied for training. The trained network is tested against 200 blood samples. The output results are compared with those of Hospital laboratory and found to be near identical, most of which are within 5% margin of error, and are much significantly better than those published. The proposed method is simple, fast, accurate, and can be a crucial step in automating laboratory reporting
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21627843,p. 776-780
Automated Assessment of Erythrocyte Disorders Using Artificial Neural Network
In this paper, we employ artificial neural network (ANN) together with image analysis techniques to automate the assessment of erythrocyte disorders using blood parameters such as red blood cell (RBC) count, hemoglobin (Hgb) level, and mean corpuscular hemoglobin (MCH). The neural network is trained using 800 blood sample images collected from the Prince George-EC, Hospital. The images are captured using a high-resolution digital camera mounted on a microscope. The red, green, and blue values of each image are fed as the input of the neural network. The Hospital RBC, Hgb values of the samples measured using hydrodynamic focused analyzer (CELL-DYN 3200 System) are provided as the target values during training. Several variations of the back propagation-learning algorithm were applied for training. The trained network is tested against 200 blood samples. The output results are compared with those of Hospital laboratory and found to be near identical, most of which are within 5% margin of error, and are much significantly better than those published. The proposed method is simple, fast, accurate, and can be a crucial step in automating laboratory reporting
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21627843,p. 787-790
A New Efficient Context-Based Relative-Directional Chain Coding
Chain coding is widely used in a variety of image processing applications. In this paper, we present a new chain coding scheme: context-based relative-directional chain coding (CRCC). It applies a novel context modeling with adaptive arithmetic coding to encode contour images. The proposed context modeling is based on the relative-directional chain representation. It provides a favorable conditional probability for the next encoding pixel so that the arithmetic coding is efficiently performed. The experimental results shows that the CRCC coding scheme overall outperforms the chain coding (CC), differential chain coding (DCC) and Differential chain coding mode-8 (DCC-8). More importantly, the proposed CRCC coding scheme completely avoids the cost in computation of eight-directional chain codes and its associated sequence of differences
- 1 August 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21627843,p. 787-790
A New Efficient Context-Based Relative-Directional Chain Coding
Chain coding is widely used in a variety of image processing applications. In this paper, we present a new chain coding scheme: context-based relative-directional chain coding (CRCC). It applies a novel context modeling with adaptive arithmetic coding to encode contour images. The proposed context modeling is based on the relative-directional chain representation. It provides a favorable conditional probability for the next encoding pixel so that the arithmetic coding is efficiently performed. The experimental results shows that the CRCC coding scheme overall outperforms the chain coding (CC), differential chain coding (DCC) and Differential chain coding mode-8 (DCC-8). More importantly, the proposed CRCC coding scheme completely avoids the cost in computation of eight-directional chain codes and its associated sequence of differences
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 08407789,p. 2107-2111
A Low Complexity Wavelet-Packets Based Image Signature for Indexing and Retrieval
Image signature is a signal that is significantly shorter and simpler than the image signal and can be used to efficiently identify the original image. Generating an image signature that accurately represents an image can only be done by means of extracting specific features of the image and express it in an efficient way. In this paper, a new wavelet-packets-based (WP) image signature that can be used for image indexing and fast retrieval is proposed. This signature is generated via encoding the position of specific points of the signal that represents some statistics of the wavelet packets coefficients in the various frequency bands. Computer simulation results using nearly 7500 image signatures show that the targeted image signature was identified with a very high accuracy in a very short period of time. Also, it showed that the proposed signature is robust against geometric transformation
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 08407789,p. 2107-2111
A Low Complexity Wavelet-Packets Based Image Signature for Indexing and Retrieval
Image signature is a signal that is significantly shorter and simpler than the image signal and can be used to efficiently identify the original image. Generating an image signature that accurately represents an image can only be done by means of extracting specific features of the image and express it in an efficient way. In this paper, a new wavelet-packets-based (WP) image signature that can be used for image indexing and fast retrieval is proposed. This signature is generated via encoding the position of specific points of the signal that represents some statistics of the wavelet packets coefficients in the various frequency bands. Computer simulation results using nearly 7500 image signatures show that the targeted image signature was identified with a very high accuracy in a very short period of time. Also, it showed that the proposed signature is robust against geometric transformation