Implementation and Benchmarking of Perceptual Image Hash Functions

364 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

RemoteCLIP: A Vision Language Foundation Model for Remote Sensing (2023, methodology): “P-Hash [74] serves as a method used for image retrieval and similarity calculation by representing image features by converting the image into a fixed-length hash value.”
Reproducible Scaling Laws for Contrastive Language-Image Learning (2022, methodology): “Figure 7: Duplicate images detected using pHash[81] between downstream datasets and LAION-400M.”
Images and Misinformation in Political Groups: Evidence from WhatsApp in India (2020, methodology): “We also grouped together similar images into clusters, using an image hashing technique that identifies perceptually similar images (Zauner [2010]).”
TGIF: A New Dataset and Benchmark on Animated GIF Description (2016, methodology): “We compute 64bit DCT image hash using pHash [45] and apply multiple index hashing [24] to perform k nearest neighbor search ( k = 100 ) in the Hamming space.”