Fully Unsupervised Salient Object Detection
Narges Fatemi, Hedieh Sajedi, Mohammad Ebrahim Shiri Ahmadabadi · 2019
Object detection is one of the most important components of machine vision. Today, object detection is used in a variety of areas, including guidance, driving, industry, and other key areas. For this reason, many algorithms have been proposed in this regard, with the aim of increasing the quality of detecting objects in an image. Since the correct representation of the object in the image is considered an essential requirement, in this article, a five-step algorithm is proposed for object detection. Experiments are performed on a given database in comparison with other methods in this area. In this algorithm, a color space is used to extract the feature and from self-encoder to remove the noise in the property matrix. Then, by scoring the clusters created based on the features, using the mean shift algorithm, the maximum pixels of the object are detected and separated from the background. The results of the experiments show performance of the proposed method in dealing with photos that involve challenges from multiple objects to changes the image.