Time filter

Source Type

Riaz S.,Computer Vision and Image Processing Laboratory | Park U.,Computer Vision and Image Processing Laboratory | Lee S.-W.,Computer Vision and Multimedia Laboratory
Multimedia Tools and Applications | Year: 2015

In digital photography, composition rules are essential for capturing highly aesthetic photographs. Aesthetic images create a response of visual appreciation to the viewers. Rule-of-thirds (RoT) is the most important and basic rule accepted by photographers for taking aesthetically pleasing shots. In this paper, a novel computational approach, “Retarget Object for Implementation of Rule-of-Thirds”, (ROI-RT) is presented. The ROI-RT technique automatically improves the composition of the photographs according to the photo composition guidelines. For achieving the mentioned task, the key adopted steps are main object segmentation by alpha matting, texture synthesis for occluded background, features extraction for ROI-RT, and retargeting the main object on synthesized background to reproduce a photograph which respects the composition rule RoT, in photography. Experimental results performed on various sets of photographs achieve a compositional accuracy rate of 95 % by proposed approach. Aesthetic scores for the resultant reconstructed photographs are attained by average subjective rating (SR) of 30 people and also computed by online evaluation methods of OSCAR and ACQUINE. Statistical significant test is applied and obtained P–value = 0.0001 < 0.05 shows a promising performance of our ROI-RT compositional scheme. A comparison with existing photo composition techniques shows that ROI-RT provides us a better aesthetic photographic composition. © 2015 Springer Science+Business Media New York Source

Ali A.M.,Assiut University | Ali A.M.,Computer Vision and Image Processing Laboratory | Aslan M.S.,Wayne State University | Aslan M.S.,Computer Vision and Image Processing Laboratory | Farag A.A.,Computer Vision and Image Processing Laboratory
Computerized Medical Imaging and Graphics | Year: 2014

We propose a novel vertebral body segmentation approach, which is based on the graph cuts technique with shape constraints. The proposed approach depends on both image appearance and shape information. Shape information is gathered from a set of training shapes. Then we estimate the shape variations using a new distance probabilistic model which approximates the marginal densities of the vertebral body and its background in the variability region using a Poisson distribution refined by positive and negative Gaussian components. To segment a vertebral body, we align its 3D shape with the training 3D shape so we can use the distance probabilistic model. Then its gray level is approximated with a Linear Combination of Gaussians (LCG) with sign-alternate components. The spatial interaction between the neighboring voxels is identified using a new analytical approach. Finally, we formulate an energy function using both appearance models and shape constraints. This function is globally minimized using s/. t graph cuts to get the optimal segmentation. Experimental results show that the proposed technique gives promising results compared to other alternatives. Applications on Bone Mineral Density (BMD) measurements of vertebral body are given to illustrate the accuracy of the proposed segmentation approach. © 2014 Elsevier Ltd. Source

Farag A.,Computer Vision and Image Processing Laboratory | Ali A.,Computer Vision and Image Processing Laboratory | Graham J.,Computer Vision and Image Processing Laboratory | Elshazly S.,Computer Vision and Image Processing Laboratory | Falk R.,Computer Vision and Image Processing Laboratory
Proceedings - International Symposium on Biomedical Imaging | Year: 2011

This paper examines the effectiveness of geometric feature descriptors, common in computer vision, for false positive reduction and for classification of lung nodules in low dose CT (LDCT) scans. A data-driven lung nodule modeling approach creates templates for common nodule types, using active appearance models (AAM); which are then used to detect candidate nodules based on optimum similarity measured by the normalized cross-correlation (NCC). Geometric feature descriptors (e.g., SIFT, LBP and SURF) are applied to the output of the detection step, in order to extract features from the nodule candidates, for further enhancement of output and possible reduction of false positives. Results on the clinical ELCAP database showed that the descriptors provide 2% enhancements in the specificity of the detected nodule above the NCC results when used in a k-NN classifier. Thus quantitative measures of enhancements of the performance of CAD models based on LDCT are now possible and are entirely model-based. Most importantly, our approach is applicable for classification of nodules into categories and pathologies. © 2011 IEEE. Source

Discover hidden collaborations