Image retargeting is an image processing task to make images of arbitrary sizes capable of 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 as intact as possible to the human visual system, while the output image may have different dimensions. Thus, simple methods such as scaling and cropping are not adequate for this purpose. In recent years, researchers have tried to improve the existing methods and introduce new ones. However, a specific method cannot be utilized to retarget all images. In other words, different images require different retargeting methods. Image retargeting has a close relationship to image saliency detection which is relatively a new image processing task. Earlier saliency detection methods were based on local and global but low-level image information. These methods are called bottom-up methods. On the other hand, newer methods are top-down and mixed methods. In this thesis, after reviewing the existing methods in both saliency detection and retargeting, we introduce the proposed methods in both of them. In saliency detection, the concept of image context and a saliency detection method based on semantic segmentation are introduced. The proposed saliency detection method is mixed bottom-up and top-down. After saliency detection, a modified version of an existing retargeting method is utilized to retarget the images. The results suggest that the proposed image retargeting pipeline has a good performance compared to other tested methods. Also, the subjective evaluations on the Pascal dataset can be used as a dataset to image retargeting quality assessment. Keywords: Image Retargeting, Human Visual System, Semantic Segmentation, Neural Networks, Saliency Detection.
