Abstract
Similarity learning plays a fundamental role in the fields of multimedia retrieval and pattern recognition. Prediction of perceptual similarity is a challenging task as in most cases we lack human labeled ground-truth data and robust models to mimic human visual perception. Although in the literature, some studies have been dedicated to similarity learning, they mainly focus on the evaluation of whether or not two images are similar, rather than prediction of perceptual similarity which is consistent with human perception. Inspired by the human visual perception mechanism, we here propose a novel framework in order to predict perceptual similarity between two texture images. Our proposed framework is built on the top of Convolutional Neural Networks (CNNs). The proposed framework considers both powerful features and perceptual characteristics of contours extracted from the images. The similarity value is computed by aggregating resemblances between the corresponding convolutional layer activations of the two texture maps. Experimental results show that the predicted similarity values are consistent with the human-perceived similarity data.
Highlights
A S a widely studied visual element in computer vision, computer graphics and pattern recognition, texture can be found everywhere in the real world
Both contour maps together with their corresponding original input textures are used inspired by visual perception studies, and our experiments show that contour information is beneficial for estimating fine-grained perceptual texture similarity, which is consistent with that of human observers[24]
The deep features learned by convolutional neural networks show comparable or even stronger performance in many computer vision tasks than those extracted by traditional methods [49], [50], for example, in image classification tasks, higher-level features can highlight the useful information of the original input that play an important role in the final classification discrimination, while suppressing insignificant differences between the data
Summary
A S a widely studied visual element in computer vision, computer graphics and pattern recognition, texture can be found everywhere in the real world. Similarity is the measurement of the likeness of two samples. It has been widely used in texture and material recognition [1], [2], semantic segmentation [3], aerial imagery classification [4], and person re-identification[5], and play important.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call