Abstract
Image recoloring is an emerging editing technique that can change the color style of an image by modifying pixel values without altering the original image content. With the rapid proliferation of social network and image editing techniques, recolored images (RIs) have raised new security issues in society. Existing detection methods have good performance in detecting RIs for certain categories of recoloring techniques. However, the performance on the handcrafted recoloring scenario is still poor due to the influence of human prior knowledge. To deal with this problem, we explore a solution from the perspective of chrominance texture artifacts to improve the generalization ability. The results of the analysis show that natural images (NIs) and RIs have textural disparities in different color components, especially in the chrominance components (i.e., Cb, Cr, and H). Based on such new prior knowledge of statistical discriminability, we propose a feature set to capture texture features in chrominance components for identifying RIs. Extensive experimental results show that the proposed method can accurately identify RIs with certain categories of recoloring techniques, and outperforms existing methods in the scenario of handcrafted recoloring.
- [1] . 2020. Media forensics and deepfakes: An overview. IEEE J. Sel. Topics Signal Process. 14, 5 (2020), 910–932.Google Scholar
Cross Ref
- [2] . 2022. Detection of AI-manipulated fake faces via mining generalized features. ACM Trans. Multimedia Comput. Commun. Appl. 18, 4 (
Mar. 2022), Article94 , 23 pages.DOI: Google ScholarDigital Library
- [3] . 2020. A serial image copy-move forgery localization scheme with source/target distinguishment. IEEE Trans. Multimedia 23 (2020), 3506–3517.Google Scholar
Digital Library
- [4] . 2021. Deep generative model for image inpainting with local binary pattern learning and spatial attention. IEEE Trans. Multimedia 24 (2021), 4016–4027.Google Scholar
- [5] . 2022. Learning adaptive patch generators for mask-robust image inpainting. IEEE Trans. Multimedia (2022).Google Scholar
- [6] . 2008. Digital image forensics via intrinsic fingerprints. IEEE Trans. Inf. Forensics Secur. 3, 1 (2008), 101–117.Google Scholar
Digital Library
- [7] . 2018. Contrast enhancement estimation for digital image forensics. ACM Trans. Multimedia Comput. Commun. Appl. 14, 2 (
May 2018), Article49 , 21 pages.DOI: Google ScholarDigital Library
- [8] . 2022. ESRNet: Efficient search and recognition network for image manipulation detection. ACM Trans. Multimedia Comput. Commun. Appl. 18, 4 (
Mar. 2022), Article111 , 23 pages.DOI: Google ScholarDigital Library
- [9] . 2011. Digital image forgery detection based on lens and sensor aberration. Int. J. Comput. Vision 92, 1 (2011), 71–91.Google Scholar
Digital Library
- [10] . 2003. Identification of bitmap compression history: JPEG detection and quantizer estimation. IEEE Trans. Image Process. 12, 2 (2003), 230–235.Google Scholar
Digital Library
- [11] . 2007. A novel method for detecting cropped and recompressed image block. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Vol. 2. II–217.Google Scholar
Cross Ref
- [12] . 2018. Recolored image detection via a deep discriminative model. IEEE Trans. Inf. Forensics Secur. 14, 1 (2018), 5–17.Google Scholar
Cross Ref
- [13] . 2001. Color transfer between images. IEEE Comput. Graph. Appl. 21, 5 (2001), 34–41.Google Scholar
Digital Library
- [14] . 2005. N-dimensional probability density function transfer and its application to color transfer. In 10th IEEE International Conference on Computer Vision (ICCV’05), Vol. 2. 1434–1439.Google Scholar
Digital Library
- [15] . 2019. Progressive color transfer with dense semantic correspondences. ACM Trans. Graph. (TOG) 38, 2 (2019), 1–18.Google Scholar
Digital Library
- [16] . 2020. Deep color transfer using histogram analogy. The Visual Comput. 36, 10 (2020), 2129–2143.Google Scholar
Digital Library
- [17] . 2005. Local color transfer via probabilistic segmentation by expectation-maximization. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), Vol. 1. 747–754.Google Scholar
- [18] . 2004. Colorization using optimization. ACM Trans. Graph. (TOG) 23, 3 (2004), 689–694.Google Scholar
Digital Library
- [19] . 2006. Manga colorization. ACM Trans. Graph. (TOG) 25, 3 (2006), 1214–1220.Google Scholar
Digital Library
- [20] . 2008. AppProp: All-pairs appearance-space edit propagation. ACM Trans. Graph. (TOG) 27, 3 (2008), 1–9.Google Scholar
Digital Library
- [21] . 2009. Efficient affinity-based edit propagation using kd tree. ACM Trans. Graph. (TOG) 28, 5 (2009), 1–6.Google Scholar
Digital Library
- [22] . 2014. Sparse dictionary learning for edit propagation of high-resolution images. In Proceedings of the IEEE Conference on Computer Vision Pattern Recognition. (CVPR’14). 2854–2861.Google Scholar
Digital Library
- [23] . 2016. DeepProp: Extracting deep features from a single image for edit propagation. In Comput. Graph. Forum. 189–201.Google Scholar
- [24] . 2017. Real-time user-guided image colorization with learned deep priors. arXiv:1705.02999. https://arxiv.org/abs/1705.02999.Google Scholar
- [25] . 2011. Color compatibility from large datasets. ACM Trans. Graph. (TOG) 30, 4 (2011), 1–12.Google Scholar
Digital Library
- [26] . 2013. Probabilistic color-by-numbers: Suggesting pattern colorizations using factor graphs. ACM Trans. Graph. (TOG) 32, 4 (2013), 1–12.Google Scholar
Digital Library
- [27] . 2015. Palette-based photo recoloring. ACM Trans. Graph. (TOG) 34, 4 (2015), 139–1.Google Scholar
Digital Library
- [28] . 2017. Palettenet: Image recolorization with given color palette. In Proceedings of the IEEE Conference on Computer Vision Pattern Recognition (CVPR’17) Workshops. 62–70.Google Scholar
Cross Ref
- [29] . 2019. Image recoloring based on object color distributions. In Eurographics (Short Papers). 33–36.Google Scholar
- [30] . 2017. Deep photo style transfer. In Proceedings of the IEEE Conference on Computer Vision Pattern Recognition (CVPR’17). 4990–4998.Google Scholar
Cross Ref
- [31] . 2018. A closed-form solution to photorealistic image stylization. In Proceedings of the European Conference on Computer Vision (ECCV’18). 453–468.Google Scholar
Digital Library
- [32] . 2019. Photorealistic style transfer via wavelet transforms. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19). 9036–9045.Google Scholar
Cross Ref
- [33] . 2016. Image style transfer using convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16).Google Scholar
Cross Ref
- [34] . 2017. Universal style transfer via feature transforms. arXiv:1705.08086. https://arxiv.org/abs/1705.08086.Google Scholar
- [35] . 2007. Edge-based color constancy. IEEE Trans. Image Process. 16, 9 (2007), 2207–2214.Google Scholar
Digital Library
- [36] . 2015. Illuminant-based transformed spaces for image forensics. IEEE Trans. Inf. Forensics Secur. 11, 4 (2015), 720–733.Google Scholar
Digital Library
- [37] . 2010. Inter-channel demosaicking traces for digital image forensics. In Proceedings of the IEEE International Conference on Multimedia and Expo. 1475–1480.Google Scholar
Cross Ref
- [38] . 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. https://arxiv.org/abs/1409.1556.Google Scholar
- [39] . 2002. Transferring color to greyscale images. In Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques. 277–280.Google Scholar
Digital Library
- [40] . 2005. Colorization by example. InProceedings of the 16th Eurographics Conference on Rendering Techniques (EGSR’05). 201–210.Google Scholar
- [41] . 2012. Image colorization using similar images. In Proceedings of the 20th ACM International Conference on Multimedia. 369–378.Google Scholar
Digital Library
- [42] . 2015. Deep colorization. In Proceedings of the IEEE International Conference on Computer Vision. 415–423.Google Scholar
Digital Library
- [43] . 2016. Learning representations for automatic colorization. In European Conference on Computer Vision. Springer, 577–593.Google Scholar
Cross Ref
- [44] . 2016. Let there be color! Joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification. ACM Trans. Graphics (ToG) 35, 4 (2016), 1–11.Google Scholar
Digital Library
- [45] . 2018. Fake colorized image detection. IEEE Trans. Inf. Forensics Secur. 13, 8 (2018), 1932–1944.Google Scholar
Cross Ref
- [46] . 2018. Fake colorized image detection with channel-wise convolution based deep-learning framework. In Proceedings of the 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC’18). IEEE, 733–736.Google Scholar
Cross Ref
- [47] . 2019. Detecting colorized images via convolutional neural networks: Toward high accuracy and good generalization. arXiv:1902.06222. https://arxiv.org/abs/1902.06222.Google Scholar
- [48] . 2021. Distinguishing between natural and recolored images via lateral chromatic aberration. J. Vis. Commun. Image Rep. 80 (2021), 103295.Google Scholar
Digital Library
- [49] . 2002. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24, 7 (2002), 971–987.Google Scholar
Digital Library
- [50] . 2007. Local features and kernels for classification of texture and object categories: A comprehensive study. Int. J. Comput. Vis. 73, 2 (2007), 213–238.Google Scholar
Digital Library
- [51] . 2011. LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 3 (2011), 1–27.Google Scholar
Digital Library
- [52] . 2007. Automated colour grading using colour distribution transfer. Comput. Vis. Image Understand. 107, 1–2 (2007), 123–137.Google Scholar
Digital Library
- [53] . 2015. Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 3 (2015), 211–252.Google Scholar
Digital Library
- [54] . 2014. Microsoft COCO: Common objects in context. In Proceedings of the Eurpean Conference on Computer Vision (ECCV’14). 740–755.Google Scholar
Cross Ref
- [55] . 2020. Identification of deep network generated images using disparities in color components. Signal Process. 174 (2020), 107616.Google Scholar
Cross Ref
- [56] . 2019. Noiseprint: A CNN-based camera model fingerprint. IEEE Trans. Inf. Forensics Secur. 15 (2019), 144–159.Google Scholar
Cross Ref
- [57] . 2014. Rich model for steganalysis of color images. In IEEE International Workshop on Information Forensics and Security (WIFS’14). 185–190.Google Scholar
- [58] . 2012. Object recoloring based on intrinsic image estimation. In International Conference on Computer Vision (ICCV’12). 327–334.Google Scholar
- [59] . 2007. The linear Monge-Kantorovitch linear colour mapping for example-based colour transfer. In Proceedings of IET CVMP. 1–9.Google Scholar
Cross Ref
- [60] . 2015. L2 registration for colour transfer. In Proceedings of the European Signal Processing Conference. 1–5.Google Scholar
Cross Ref
Index Terms
Detection of Recolored Image by Texture Features in Chrominance Components
Recommendations
Deep Palette-Based Color Decomposition for Image Recoloring with Aesthetic Suggestion
MultiMedia ModelingAbstractColor edition is an important issue in image processing and graphic design. This paper presents a deep color decomposition based framework for image recoloring, allowing users to achieve professional color edition through simple interactive ...
Colorization of Mountainous Landscape Images in Grayscale Using Texture Feature Analysis
ICVISP 2018: Proceedings of the 2nd International Conference on Vision, Image and Signal ProcessingColorization of black and white images is a difficult task due to the lack of color information in the monochrome space. In this paper, we propose an automated approach to produce realistic colorizations using texture classification. We limit our ...
Content-based image retrieval using color and texture fused features
This paper presents a method to extract color and texture features of an image quickly for content-based image retrieval (CBIR). First, HSV color space is quantified rationally. Color histogram and texture features based on a co-occurrence matrix are ...






Comments