Welcome to the upgraded BRAC University Institutional Repository. We are currently organizing collections after a recent system upgrade. Homepage category counters may temporarily show lower numbers while syncing, but over 27,000 repository items remain safe and accessible. Please use the search bar to find theses, scholarly outputs, and institutional documents.

Conference Paper

Permanent URI for this collectionhttps://hdl.handle.net/10361/7304

Browse

Recent Submissions

Now showing 1 - 2 of 2
  • Thumbnail Image
    listelement.badge.dso-type Item ,
    Night mode face recognition using adaptively weighted sub-pattern PCA
    (© 2012 IEEE, 2012) Alom, Md. Zahangir; Khan, Arif; Biswas, Rubel; Khan, Mumit; Department of Computer Science and Engineering
    The face recognition problem is made difficult by the great variability in head rotation and tilt, lighting intensity and angle, facial expression, aging, partial occlusion (e.g. Wearing Hats, scarves, glasses etc.), etc. Principal components from the face space are used for face recognition to reduce dimensionality of database images. However, this paper discusses on adaptively weighted sub-pattern PCA (Aw-SpPCA) based face recognition system for dark images that have captured at night. It is really difficult to capture good quality picture at night for lacking of light source with traditional acquisition devices like camera or mobile phone. The computational photographic concepts have been applied to enhance the quality of the capture images at night automatically. Multi-scale retinex color restorations (MSRCR) technique has been applied for overcome this problem. Moreover, for recognition phase of this propose method, unlike PCA based on a whole image pattern, Aw-SpPCA operates directly on its sub patterns partitioned from an original whole pattern and separately extracts features from them. Aw-SpPCA can adaptively compute the contributions of each part and then endows them to a classification task in order to enhance the robustness to both expression and illumination variations. Experimental results show that the proposed method is competitive.
  • Thumbnail Image
    listelement.badge.dso-type Item ,
    Automatic slice growing method based 3D reconstruction of liver with its vessels
    (© 2014 Institute of Electrical and Electronics Engineers Inc., 2014) Alom, Md. Zahangir; Mostakim, Moin; Biswas, Rubel; Chakrabarty, Amitabha; Department of Computer Science and Engineering
    In the recent years, reconstructing 3D liver and its vessels from abdominal CT volume images becomes an inevitable and necessary research field. In this paper, a method of 3D reconstruction of liver with its vessels has been implemented, which involves volume preprocessing, de-noising, segmentation, contouring, and combination of different modalities. An advanced liver segmentation algorithms have been proposed: The first one is a 2.5D method that utilizes automatic Slice Growing Method (SGM) to segment liver part of each slice of a data set. It takes advantage of curvature control of level set segmentation method to distinguish liver and adjacent organs. It is proved that the result of this proposed method is much better than simple 3D level set method in liver segmentation. In the case of liver vessel segmentation, we have proposed an improved smoothing method dedicate to 3D vascular volume which results from region growing segmentation method. The cooperation of region growing method and proposed smoothing method has been demonstrated the possibility of efficient vessel segmentation with very accurate results. And the results indicate that our method is suitable for anatomical studying and surgical planning.