Large Feature Mining With Ensemble Learning for Image Forgery Detection

The detection of different types of forgery manipulation including seam-carving in JPEG images is a hot spot in image forensics. Seam carving was originally designed for content-aware image resizing. It is also being used for forgery manipulation. It is still very challenging to effectively identify the seam carving forgery under recompression. To address the highly challenging detection problems, this chapter introduces an effective approach with large feature mining. Ensemble learning is used to deal with the high dimensionality and to avoid overfitting that may occur with some traditional learning classifier for the detection. The experimental results validate the efficacy of proposed approach to detecting JPEG double compression and exposing the seam-carving forgery while the JPEG recompression is proceeded at the same quality and a lower quality, which is generally much harder for traditional detection methods. The methodology introduced in this chapter provides a strategy and realistic approach to resolve the highly challenging problems in image forensics.

Content-aware frame interpolation (CAFI): Deep Learning-based temporal super-resolution for fast bioimaging

The development of high-resolution microscopes has made it possible to investigate cellular processes in 4D (3D over time). However, observing fast cellular dynamics remains challenging as a consequence of photobleaching and phototoxicity. These issues become increasingly problematic with the depth of the volume acquired and the speed of the biological events of interest. Here, we report the implementation of two content-aware frame interpolation (CAFI) deep learning networks, Zooming SlowMo (ZS) and Depth-Aware Video Frame Interpolation (DAIN), based on combinations of recurrent neural networks, that are highly suited for accurately predicting images in between image pairs, therefore improving the temporal resolution of image series as a post-acquisition analysis step. We show that CAFI predictions are capable of understanding the motion context of biological structures to perform better than standard interpolation methods. We benchmark CAFI's performance on six different datasets, obtained from three different microscopy modalities (point-scanning confocal, spinning-disc confocal and confocal brightfield microscopy). We demonstrate its capabilities for single-particle tracking methods applied to the study of lysosome trafficking. CAFI therefore allows for reduced light exposure and phototoxicity on the sample and extends the possibility of long-term live-cell imaging. Both DAIN and ZS as well as the training and testing data are made available for use by the wider community via the ZeroCostDL4Mic platform.