Context-aware saliency detection for image retargeting using convolutional neural networks

Image retargeting is the task of making images capable being displayed on screens with different sizes. This work should be done so that high-level visual information and low-level features such as texture remain intact possible to human system. At same time, output image may have dimensions. Thus, simple methods scaling cropping are not adequate for this purpose. In recent years, researchers tried improve existing methods, they introduced new ones. However, a specific method cannot utilized retarget all types images. other words, require methods. has close relationship saliency detection, which relatively processing task. Earlier detection were based local global but information. These called bottom-up processes. On hand, newer approaches top-down mixed consider high level semantic knowledge too. paper, we introduce proposed in both retargeting. For use context segmentation examined, novel introduced. After modified version an technique The results suggest pipeline excellent performance compared tested Also, subjective evaluations Pascal dataset can used quality assessment further research.