Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries

About

With advanced image journaling tools, one can easily alter the semantic meaning of an image by exploiting certain manipulation techniques such as copy-clone, object splicing, and removal, which mislead the viewers. In contrast, the identification of these manipulations becomes a very challenging task as manipulated regions are not visually apparent. This paper proposes a high-confidence manipulation localization architecture which utilizes resampling features, Long-Short Term Memory (LSTM) cells, and encoder-decoder network to segment out manipulated regions from non-manipulated ones. Resampling features are used to capture artifacts like JPEG quality loss, upsampling, downsampling, rotation, and shearing. The proposed network exploits larger receptive fields (spatial maps) and frequency domain correlation to analyze the discriminative characteristics between manipulated and non-manipulated regions by incorporating encoder and LSTM network. Finally, decoder network learns the mapping from low-resolution feature maps to pixel-wise predictions for image tamper localization. With predicted mask provided by final layer (softmax) of the proposed architecture, end-to-end training is performed to learn the network parameters through back-propagation using ground-truth masks. Furthermore, a large image splicing dataset is introduced to guide the training process. The proposed method is capable of localizing image manipulations at pixel level with high precision, which is demonstrated through rigorous experimentation on three diverse datasets.

Jawadul H. Bappy, Cody Simons, Lakshmanan Nataraj, B.S. Manjunath, Amit K. Roy-Chowdhury• 2019

Related benchmarks

TaskDatasetResultRank
Image Manipulation LocalizationNIST16--
42
Pixel-level Manipulation DetectionNIST
F1 Score46.6
34
Pixel-level Manipulation DetectionCOVER
F1 Score21.3
34
Pixel-level Manipulation DetectionColumbia
F1 Score14.2
34
Pixel-level Manipulation DetectionDEFACTO 12k
F1 Score12.5
32
Pixel-level Manipulation DetectionCASIA v1+
F1 Score20.9
22
Pixel-level Manipulation DetectionIMD
F1 Score31
20
Pixel-level Manipulation DetectionMEAN Across datasets
F1 Score24.4
20
Image-level manipulation detectionCASIA v1+
AUC0.498
19
Image Manipulation DetectionGeneral Inference Speed Evaluation Images
FPS6.5
16
Showing 10 of 17 rows

Other info

Follow for update