Appl.This paper introduces a new benchmark for large-scale image similarity detection. Zhu Qianqian, W.D.: A SVM recommendation IoT model based on similarity evaluation and collaborative filtering of multi-angle knowledge units. Zhang, K., Liao, Q.: FPGA implementation of eight-direction Sobel edge detection algorithm based on adaptive threshold. Zhang, X., Chen, F.: Lane line edge detection based on improved adaptive canny algorithm. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015) Zagoruyko, S., Komodakis, N.: Learning to compare image patches via convolutional neural networks. Xu, Z., Ji, X., Wang, M., Sun, X.: Edge detection algorithm of medical image based on canny operator. Wei, Z., Zhang, X.: Feature extraction and retrieval of ecommerce product images based on image processing. Wang, G., Wang, S., Chi, W., Liu, S., Fan, D.A.: person reidentification algorithm based on improved Siamese network and hard sample. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016) Wang, F., Zuo, W., Lin, L., Zhang, D., Zhang, L.: Joint learning of single-image and cross-image representations for person re-identification. Jurnal RESTI Rekayasa Sistem dan Teknologi Informasi 4(2), 345–51 (2020)

Sulistyo, W.Y., Riadi, I., Yudhana, A.: Comparative analysis of image quality values on edge detection methods. Shi, W., Liu, S., Jiang, F., Zhao, D., Tian, Z.: Anchored neighborhood deep network for single-image super-resolution. Niizumi, D., Takeuchi, D., Ohishi, Y., Harada, N., Kashino, K.: BYOL for audio: self-supervised learning for general-purpose audio representation (2021) Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. Jiang, F., Grigorev, A., Rho, S., Tian, Z., Fu, Y., Jifara, W., Adil, K., Liu, S.: Medical image semantic segmentation based on deep learning.

In: International Conference on Machine Learning (2020) 20(2), 629–42 (2020)Ĭhen, T., Kornblith, S.N.: A simple framework for contrastive learning of visual representations. 11(2), 66 (2017)Ĭao, Y., Wu, D., Duan, Y.: A new image edge detection algorithm based on improved Canny. The similarity measurement is carried out with the line diagram in the library in which the similarity measurement accuracy of cross-type images can reach 92%.Īkbas, C., Günay, O., Tasdemir, K., Cetin, A.: Energy efficient cosine similarity measures according to a convex cost function. The original image is imported into the autoencoder to obtain the edge feature map of the original map, and then the resulting edge feature map is imported into the similarity measurement network. In terms of similarity measurement, similar to twin neural networks, two deep network models are established for similarity measurement, and image data classification training is used instead of the training method used in traditional twin neural networks. Taking advantage of the good effect of the autoencoder in feature extraction, an autoencoder that can efficiently extract edge feature maps is trained.

This article describes an image similarity measurement method across types, focusing on the image edge feature autoencoder and the edge feature map similarity measurement network. At this stage, due to the different methods of expressing attribute characteristics between cross-type images, the performance measurement accuracy is low, only approximately 78%.

Image similarity