Robust image hashing

By Ramarathnam Venkatesan, S. Koon, Mariusz H. Jakubowski, Pierre Moulin. Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101), 2000

586 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7ae30ebbd2dbc7a0c78bec78f33df95c32c8f468

How researchers see this paper

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

In Artificial Intelligence

1. Assa Naveh
2. Min Wu
3. Tianqi Liu
4. Eran Tromer
5. Jialu Liu
6. Vishal Monga
7. Cong Yu
8. Eli Ben-Sasson

In Computer Vision and Pattern Recognition

1. Vishal Monga
2. M. K. Mihçak
3. Min Wu
4. Brian L. Evans
5. Ashwin Swaminathan
6. Assa Naveh
7. Tianqi Liu
8. Eran Tromer

Citations in the corpus

• Robust and Secure Image Hashing via Non-Negative Matrix Factorizations (2007, background): “Consider the following abstract setting for image hashing: (7) Essentially, (7) means that hashing is a noninvertible dimensionality reduction problem, where noninvertibility implies that cannot be used to resynthesize even an approximation to .”
• PhotoProof: Cryptographic Image Authentication for Any Set of Permissible Transformations (2016, background): “, [46], [20], [55], [33], [48], [17], [59], [34], [60]).”
• Robust and secure image hashing (2006, methodology): “Uniform, Lloyd–Max, or key-dependent randomized quantizers have been used for hash quantization [4], [5]; and the decoding stages of error-correcting codes have been used for compressing the quantized hash [4], [32], [33].”
• Perceptual Image Hashing Via Feature Points: Performance Evaluation and Tradeoffs (2006, background): “The underlying techniques for constructing image hashes can roughly be classified into methods based on image statistics [3], [4] [5], relations [6], [7], preservation of coarse image representation [8], [9], [10], and low-level image feature extraction [11], [12].”
• Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm (2005, unknown): “Attempts to develop automated computer routines to efficiently search parameter space in order to find unique values for the spectral parameters that reproduce an observed NMR spectrum were made at an early stage, initially for isotropic liquids.”
• Implementation and Benchmarking of Perceptual Image Hash Functions (2010, background): “5 (Equality Percentage (EP)): Another metric, as defined in [42], that can be derived is the Equality Percentage (EP):”
• NewsEmbed: Modeling News through Pre-trained Document Representations (2021, methodology): “• Image embedding: Thumbnail embedding is derived using wavelet hashing [56].”