No abstract

No abstract

No abstract

No abstract

The depth of an image is used to find out the distance from where it is taken. This is done by taking a set of images with different depths as the input and extracting Local and Global features from it. First, feature extraction based methods are utilized to evaluate image similarities. We propose a model that incorporates both of them to obtain significantly more accurate depth estimates than using either global or local properties alone. The features thus obtained are tested using support vector machines. The trained data is then used for testing to calculate the depth of any image approximately.