Farukuzzaman Khan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Farukuzzaman Khan has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Md. Atiqur Rahman
Institute of Genetics and Developmental Biology, University of Chinese Academy of Sciences (UCAS), Beijing, China
1 shared publication - Md. Ibrahim Abdullah
Department of Computer Science and Engineering, Islamic University, Kushtia, Bangladesh
1 shared publication - Mijanur Rahman
Jatiya Kabi kazi Nazrul Islam University
1 shared publication - Mohammad Alamgir Hossain
Islamic University
1 shared publication - Nazrul Islam
Islamic University
1 shared publication - Tushar Kanti Saha1 shared publication
Latest Publications
- Open Access
- 9 May 2025
- Published by Springer Nature in Research Square
Dynamic Focal Length Adjustment for Drift-Free Cylindrical Panorama Stitching Using Feature-Based Image Alignment
Panoramic image stitching is a fundamental technique in computer vision and graphics , widely utilized in virtual tours, immersive experiences, and robotic vision. However , traditional cylindrical panorama stitching techniques often face challenges with accumulated drift, resulting in visual misalignments in the final output. This paper presents a novel approach to drift-free cylindrical panorama stitching by dynamically adjusting the focal length based on the gap angle between the first and last images. The proposed method incorporates cylindrical warping, robust feature extraction using the Scale-Invariant Feature Transform (SIFT), and image alignment through Random Sample Consensus (RANSAC). Drift correction is achieved by iteratively recalibrating the focal length to minimize alignment errors and ensure seamless stitching across the panoramic sequence. Experimental results demonstrate the effectiveness of the proposed approach in reducing drift, achieving precise alignment, and producing high-quality panoramas. The dynamic focal length adjustment offers significant improvements over existing methods, addressing key challenges in panoramic imaging and enhancing its applicability in real-world scenarios.
- 9 May 2025
- Published by Springer Nature in Research Square
Open AccessDynamic Focal Length Adjustment for Drift-Free Cylindrical Panorama Stitching Using Feature-Based Image Alignment
Panoramic image stitching is a fundamental technique in computer vision and graphics , widely utilized in virtual tours, immersive experiences, and robotic vision. However , traditional cylindrical panorama stitching techniques often face challenges with accumulated drift, resulting in visual misalignments in the final output. This paper presents a novel approach to drift-free cylindrical panorama stitching by dynamically adjusting the focal length based on the gap angle between the first and last images. The proposed method incorporates cylindrical warping, robust feature extraction using the Scale-Invariant Feature Transform (SIFT), and image alignment through Random Sample Consensus (RANSAC). Drift correction is achieved by iteratively recalibrating the focal length to minimize alignment errors and ensure seamless stitching across the panoramic sequence. Experimental results demonstrate the effectiveness of the proposed approach in reducing drift, achieving precise alignment, and producing high-quality panoramas. The dynamic focal length adjustment offers significant improvements over existing methods, addressing key challenges in panoramic imaging and enhancing its applicability in real-world scenarios.
- 1 January 2011
- Published by Diva Enterprises Private Limited in International Journal of Applied Research on Information Technology and Computing
- Vol. 2 (3) , 30-40
Peak based clustering of continuous Bengali speech for medium vocabulary speech recognition system
Throughout this research work, we have introduced the peak based clustering of continuous speech in Bengali language. We have done this to fill up the noble aim of using Bengali speech recognition in various areas such as text writing in the cell-phone and computer, establishing speech-based user interface, etc. To achieve this goal, original continuous speech was recorded by two different speakers in a room environment and stored as RIFF wave (.wav) file format. First, all speech blocks were segmented by our developed algorithm into words or segments. Then we incorporated moving average algorithm into the positive half cycle of the time spectrum of these segments to obtain smooth curve representation. From this curve, the peaks were traced and clustering was done through the property called number of peaks. This medium vocabulary speech database, containing a total of 355 words, was used to evaluate the system performance. The developed system achieved average segmentation accuracy at about 99.12% and clustering accuracy at about 96.53%.
- 1 January 2011
- Published by Diva Enterprises Private Limited in International Journal of Applied Research on Information Technology and Computing
- Vol. 2 (3) , 30-40
Peak based clustering of continuous Bengali speech for medium vocabulary speech recognition system
Throughout this research work, we have introduced the peak based clustering of continuous speech in Bengali language. We have done this to fill up the noble aim of using Bengali speech recognition in various areas such as text writing in the cell-phone and computer, establishing speech-based user interface, etc. To achieve this goal, original continuous speech was recorded by two different speakers in a room environment and stored as RIFF wave (.wav) file format. First, all speech blocks were segmented by our developed algorithm into words or segments. Then we incorporated moving average algorithm into the positive half cycle of the time spectrum of these segments to obtain smooth curve representation. From this curve, the peaks were traced and clustering was done through the property called number of peaks. This medium vocabulary speech database, containing a total of 355 words, was used to evaluate the system performance. The developed system achieved average segmentation accuracy at about 99.12% and clustering accuracy at about 96.53%.