One of the most active fields in Image processing and machine vision is saliency detection. While Human beings can easily perceive the distinction between parts of an image and concentrate on a specific part of it, this is a hard and complicated task for computers. Considering saliency as a psychological phenomenon, this issue was firstly studied by researchers in cognitive science and psychology. But nowadays, this subject has attracted interest in computational sciences such as machine learning. The reason of this interest is its application in such domains as object detection, image compression and target detecting and tracking. One of the saliency detection areas is salient object detection. The purpose of salient object detection is to determine and segment the first meaningful object, at first glance, by majority of people. At first, researches used basic features such as color, light intensity, color contrast, and other low-level features in their In this research, the theoretical and basic foundations for salient object detection is studied Then, the relevant databases and evaluation criteria of them have been investigated. In this research, we chose UNet as the basic architecture for salient object detection. It was shown that this architecture has some shortcomings in salient object detection. Thus, we developed four new architectures. In the first network, we increased the convergence and trainability of the network by adding residual blocks and batch norm layers. In the second network, in order to improve the up-sampling procedure and increase the accuracy of segmentation, we used new blocks composed of traosed convolution and cubic spline up sampling. On the third architecture, we used multiscale feature by adding Inception-ResNet blocks with pre-trained weights in each step of encoder path. In the final proposed architecture, the Atreus spatial pyramid pooling was added in the last layer of the encoder to use global features as well as local features. The final model showed its superiority to other models in most of the evaluation criteria. Key Words: Saliency, Salient Object Detection, Deep Learning, Convolutional Neural Network
