RECORD
Validating the Contextual Information of Outdoor Images for Photo Misuse Detection
Cryptography and Security · Submitted 21 Nov 2018
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The experimental results show that our method can successfully estimate sun position and detect the time-location inconsistency with high accuracy.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
The contextual information (i.e., the time and location) in which a photo is taken can be easily tampered with or falsely claimed by forgers to achieve malicious purposes, e.g., creating fear among the general public. A rich body of work has focused on detecting photo tampering and manipulation by verifying the integrity of image content. Instead, we aim to detect photo misuse by verifying the capture time and location of photos. This paper is motivated by the law of nature that sun position varies with the time and location, which can be used to determine whether the claimed contextual information corresponds with the sun position that the image content actually indicates. Prior approaches to inferring sun position from images mainly rely on vanishing points associated with at least two shadows, while we propose novel algorithms which utilize only one shadow in the image to infer the sun position. Meanwhile, we compute the sun position by applying astronomical algorithms which take as input the claimed capture time and location. Only when the two estimated sun positions are consistent can the claimed contextual information be genuine. We have developed a prototype called IMAGEGUARD. The experimental results show that our method can successfully estimate sun position and detect the time-location inconsistency with high accuracy. By setting the thresholds to be 9.4 degrees and 5 degrees for the sun position distance and the altitude angle distance, respectively, our system can correctly identify 91.5% of falsified photos with fake contextual information.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | The contextual information (i.e., the time and location) in which a photo is taken can be easily tampered with or falsely claimed by forgers to achieve malicious purposes, e.g., creating fear among the general public. | background 1.00 | 0.05 | 0.02 | asserted 0.82 |
| s1 | A rich body of work has focused on detecting photo tampering and manipulation by verifying the integrity of image content. | background 0.99 | 0.02 | 0.02 | asserted 1.00 |
| s2 | Instead, we aim to detect photo misuse by verifying the capture time and location of photos. | contribution 0.89 | 0.38 | 0.04 | asserted 0.92 |
| s3 | This paper is motivated by the law of nature that sun position varies with the time and location, which can be used to determine whether the claimed contextual information corresponds with the sun position that the image content actually indicates. | background 0.50 | 0.08 | 0.04 | asserted 0.98 |
| s4 | Prior approaches to inferring sun position from images mainly rely on vanishing points associated with at least two shadows, while we propose novel algorithms which utilize only one shadow in the image to infer the sun position. | contribution 0.90 | 0.76 | 0.04 | asserted 1.00 |
| s5 | Meanwhile, we compute the sun position by applying astronomical algorithms which take as input the claimed capture time and location. | method 0.99 | 0.92 | 0.03 | asserted 1.00 |
| s6 | Only when the two estimated sun positions are consistent can the claimed contextual information be genuine. | method 0.98 | 0.37 | 0.22 | asserted 0.98 |
| s7 | We have developed a prototype called IMAGEGUARD. | contribution 0.81 | 0.91 | 0.03 | asserted 0.99 |
| s8 | The experimental results show that our method can successfully estimate sun position and detect the time-location inconsistency with high accuracy. | result 1.00 | 0.97 | 0.71 | asserted 0.99 |
| s9 | By setting the thresholds to be 9.4 degrees and 5 degrees for the sun position distance and the altitude angle distance, respectively, our system can correctly identify 91.5% of falsified photos with fake contextual information. | result 1.00 | 0.97 | 0.33 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
The contextual information (i.e., the time and location) in which a photo is taken can be easily tampered with or falsely claimed by forgers to achieve malicious purposes, e.g., creating fear among the general public. A rich body of work has focused on detecting photo tampering and manipulation by verifying the integrity of image content. Instead, we aim to detect photo misuse by verifying the capture time and location of photos. This paper is motivated by the law of nature that sun position varies with the time and location, which can be used to determine whether the claimed contextual information corresponds with the sun position that the image content actually indicates. Prior approaches to inferring sun position from images mainly rely on vanishing points associated with at least two shadows, while we propose novel algorithms which utilize only one shadow in the image to infer the sun position. Meanwhile, we compute the sun position by applying astronomical algorithms which take as input the claimed capture time and location. Only when the two estimated sun positions are consistent can the claimed contextual information be genuine. We have developed a prototype called IMAGEGUARD. The experimental results show that our method can successfully estimate sun position and detect the time-location inconsistency with high accuracy. By setting the thresholds to be 9.4 degrees and 5 degrees for the sun position distance and the altitude angle distance, respectively, our system can correctly identify 91.5% of falsified photos with fake contextual information.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.