Recently, the task of validating the authenticity of images and the localization of tampered regions has been actively studied. In this paper, we go one step further by providing solid evidence for image manipulation. If a certain image is proved to be the spliced image, we try to retrieve the original authentic images that were used to generate the spliced image. Especially for the image retrieval of spliced images, we propose a hybrid image-retrieval method exploiting Zernike moment and Scale Invariant Feature Transform (SIFT) features. Due to the symmetry and antisymmetry properties of the Zernike moment, the scaling invariant property of SIFT and their common rotation invariant property, the proposed hybrid image-retrieval method is efficient in matching regions with different manipulation operations. Our simulation shows that the proposed method significantly increases the retrieval accuracy of the spliced images.

In the last decade, deep learning (DL) has emerged as a dominant technique for solving challenging problems in various fields. Consequently, a large and growing body of literature with reports of investigations into DL-based methods for image-forgery detection, classification, and localization is available. Owing to advances in DL, DL-based approaches have yielded promising results in image forgery detection and localization tasks. This survey provides a comprehensive list of state-of-the-art DL-based methods for image-forgery detection. Copy-move images and spliced images, two of the most popular types of forged images, were considered.

Recent studies on image stitching have been extensively conducted to stitch panoramic or 360° images using a small number of input images. The stitching of aerial images, that are captured by unmanned aerial vehicles (UAVs), has various practical applications. In this paper, we propose a fast adaptive stitching algorithm for handling numerous aerial images. First, the proposed method analyzes the relative positions and overlapping regions of the UAV image footprints by exploiting their geotag information. Based on the analysis, an adaptive selection algorithm is proposed to eliminate the densely overlapped images from among all the UAV images. Then, the proposed method sequentially performs fast feature extraction and feature matching. Finally, a local warp method, with a smooth transition for overlapping regions, is introduced to alleviate the blurring artifacts and achieve highly accurate image alignment. The experiments are conducted for various scenarios to generate seamless terrestrial mosaic images of large areas. The proposed method improves the visual quality of the stitched image, by decreasing the estimated reprojection error and the number of observed visual distortions. In addition, the proposed method can substantially reduce the processing time compared with conventional stitching methods.

In the elderly population, falls are one of the leading causes of fatal and non-fatal injuries. Fall detection and early alarms play an important role in mitigating the negative effects of falls, especially given the growing proportion of the elderly population. Due to their non-intrusive nature, data availability, and low deployment costs, RGB videos have been used in many previous studies to detect falls. The RGB data, however, can be affected by background environment changes, resulting in non-recognition. To overcome these challenges, many researchers propose extracting skeleton data from RGB videos and using it for fall detection. Although there have been multiple surveys on fall detection, most of them focus on assessing fall detection systems using different kinds of sensors, and a comprehensive evaluation of skeleton-based fall detection in RGB videos is lacking. In this paper, we examine the most recent advances in skeleton-based fall detection in RGB videos, from handcrafted feature-based methods to advanced deep learning algorithms. Further, we present several skeleton-based fall detection techniques and their performance results on various benchmark datasets, along with challenges and future directions in this field.

In the image forgery problems, previous works has been chiefly designed considering only one of two forgery types: copy-move and splicing. In this paper, we propose a scheme to handle both copy-move and splicing image forgery by concurrently classifying the image forgery types and localizing the forged regions. The structural correlations between images are employed in the forgery clustering algorithm to assemble relevant images into clusters. Then, we search for the matching of image regions inside each cluster to classify and localize tampered images. Comprehensive experiments are conducted on three datasets (MICC-600, GRIP, and CASIA 2) to demonstrate the better performance in forgery classification and localization of the proposed method in comparison with state-of-the-art methods. Further, in copy-move localization, the source and target regions are explicitly specified.