請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/22069完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 顏嗣鈞(Hsu-chun Yen) | |
| dc.contributor.author | Yu-Hsiang Yeh | en |
| dc.contributor.author | 葉昱祥 | zh_TW |
| dc.date.accessioned | 2021-06-08T04:00:49Z | - |
| dc.date.copyright | 2018-08-09 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-08-08 | |
| dc.identifier.citation | [1] C. C. Chang. A steganographic method for hiding secret data using side match vector quantization. Ieice rans.inf. & Syst.d, 88(88-D):2159–2167, 2005.
[2] C. C. Chang, G. M. Chen, and M. H. Lin. Information hiding based on search-order coding for vq indices. Pattern Recognition Letters, 25(11):1253–1261, 2004. [3] C. C. Chang and C. Y. Lin. Reversible steganography for vq-compressed images using side matching and relocation. IEEE Transactions on Information Forensics & Security, 1(4):493–501, 2006. [4] C. C. Chang, T. S. Nguyen, and C. C. Lin. A reversible compression code hiding using SOC and SMVQ indices. Elsevier Science Inc., 2015. [5] K. Cho, B. V. Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. Computer Science, 2014. [6] J. Chung, C. Gulcehre, K. H. Cho, and Y. Bengio. Empirical evaluation of gated recurrent neural networks on sequence modeling. Eprint Arxiv, 2014. [7] R. M. Gray. Vector quantization. Readings in Speech Recognition, 1(2):75–100, 1990. [8] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778, 2016. [9] G. E. Hinton, A. Krizhevsky, and S. D. Wang. Transforming auto-encoders. 6791:44–51, 2011. [10] G. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504–507, 2006. [11] M. Jo. A digital image watermarking scheme based on vector quantisation. Ieice Trans.inf. & Syst.d, 85(6):1054–1056, 2002. [12] T. Kim. Side match and overlap match vector quantizers for images. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 1(2):170–85, 1992. [13] A. Krizhevsky and G. E. Hinton. Using very deep autoencoders for content-based image retrieval. In Esann 2011, European Symposium on Artificial Neural Networks, Bruges, Belgium, April 27-29, 2011, Proceedings, 2012. [14] J. D. Lee and Y. H. Chiou. Lossless data hiding for vq indices based on neighboring correlation. Information Sciences, 221(2):419–438, 2013. [15] I. C. Lin, Y. B. Lin, and C. M. Wang. Hiding data in spatial domain images with distortion tolerance. Elsevier Science Publishers B. V., 2009. [16] B. Y. Linde, A. Buzo, and R. M. Gray. An algorithm for vector quantizier design. [17] A. Malik, G. Sikka, and H. K. Verma. An ambtc compression based data hiding scheme using pixel value adjusting strategy. Multidimensional Systems & Signal Processing, (3):1–18, 2017. [18] Z. Pan, X. Ma, X. Deng, and S. Hu. Low bit-rate information hiding method based on search-order-coding technique. Journal of Systems & Software, 86(11):2863–2869, 2013. [19] C. Qin, C. C. Chang, and Y. P. Chiu. A novel joint data-hiding and compression scheme based on smvq and image inpainting. IEEE Transactions on Image Processing, 23(3):969–978, 2014. [20] P. Rahmani, M. S. Norouzzadeh, and G. Dastghaibyfard. A novel legitimacy preserving data hiding scheme based on las compressed code of vq index tables. Multidimensional Systems & Signal Processing, 27(2):433–452, 2016. [21] A. Shaik, V. Thanikaise, and R. Amitharaja. Data security through data hiding in images: A review. Journal of Artificial Intelligence, 10(1):1–21, 2014. [22] J. Tian. Reversible data embedding using a difference expansion. IEEE Transactions on Circuits & Systems for Video Technology, 13(8):890–896, 2003. [23] Y. S. Tsai and P. Tsai. Adaptive data hiding for vector quantization images based on overlapping codeword clustering. Information Sciences, 181(15):3188–3198, 2011. [24] P. Vincent, H. Larochelle, Y. Bengio, and P. A. Manzagol. Extracting and composing robust features with denoising autoencoders. In International Conference on Machine Learning, pages 1096–1103, 2008. [25] K. Wang, Z. M. Lu, and Y. J. Hu. A high capacity lossless data hiding scheme for jpeg images. Journal of Systems & Software, 86(7):1965–1975, 2013. [26] W. J. Wang, C. T. Huang, C. M. Liu, P. C. Su, and S. J. Wang. Data embedding for vector quantization image processing on the basis of adjoining state-codebook mapping. Information Sciences An International Journal, 246(14):69–82, 2013. [27] G. Xuan, Q. Yao, C. Yang, J. Gao, P. Chai, Y. Q. Shi, and Z. Ni. Lossless data hiding using histogram shifting method based on integer wavelets. In International Conference on Digital Watermarking, pages 323–332, 2006. [28] B. Yang. Reversible watermarking in the vq-compressed domain. In Proc. Fifth Iasted International Conference on Visualization, Imaging, and Image Processing, 2005. [29] C. H. Yang, C. T. Huang, and S. J. Wang. Reversible steganography based on side match and hit pattern for vq-compressed images. Information Sciences An International Journal, 181(11):2218–2230, 2009. [30] C. H. Yang and Y. C. Lin. Reversible data hiding of a vq index table based on referred counts. Journal of Visual Communication & Image Representation, 20(6):399–407, 2009. [31] C. H. Yang and Y. C. Lin. Fractal curves to improve the reversible data embedding for VQ-indexes based on locally adaptive coding. Academic Press, Inc., 2010. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/22069 | - |
| dc.description.abstract | 資料隱藏是資訊安全裡重要的研究領域。為了隱藏機密資料的存在，我們將機密資料藏於不相關的圖片中。一般而言，我們希望能藏入大量的資料，並減少對圖片造成的失真。
本篇論文提出一個基於神經網路，並結合資訊隱藏與壓縮的方法。在傳送端，我們用編碼器壓縮圖片，並轉換成二進位資料。接著，我們從二進位資料選出對圖片品質影響較少的部分，並用機密資料取代。在解壓縮階段，接收者可以直接取出隱密質料，並用解碼器來還原圖片。實驗結果顯示出我們能放入更多的機密資料，並保有較佳的還原品質。 | zh_TW |
| dc.description.abstract | Data hiding is an important research field in information security. In order to keep the confidential information from being discovered, we conceal the information in unrelated images. In general, the goal of data hiding is to embed a large amount of information without causing visual distortion.
In this thesis, we propose a joint data hiding and compression scheme based on neural networks. On the sender side, we use the encoder to compress the image, and then use the binarizer to generate binary codes. Next, we select parts of the binary codes that have less influence on image quality and replace them with the hidden data. During the decompressing phase, the receiver can extract the hidden data directly and restore the image with the decoder. Experimental results show that the proposed scheme has better hiding capacity and visual quality. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-08T04:00:49Z (GMT). No. of bitstreams: 1 ntu-107-R05921080-1.pdf: 10332008 bytes, checksum: 8cab216fde25ac6291d232af73022f08 (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 口試委員會審定書 iii
誌謝 v Acknowledgements vii 摘要 ix Abstract xi 1 Introduction 1 2 Related works 5 2.1 JPEG-based data hiding . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.2 SMVQ-based data hiding . . . . . . . . . . . . . . . . . . . . . . . . . . 6 3 Proposed scheme 9 3.1 Autoencoder . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.2 Residual Autoencoder . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2.1 Residual unit . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2.2 Residual autoencoder . . . . . . . . . . . . . . . . . . . . . . . . 12 3.3 LSTM Residual Autoencoder . . . . . . . . . . . . . . . . . . . . . . . . 12 3.3.1 Recurrent neural networks . . . . . . . . . . . . . . . . . . . . . 12 3.3.2 Gated recurrent unit . . . . . . . . . . . . . . . . . . . . . . . . 13 3.3.3 LSTM residual autoencoder . . . . . . . . . . . . . . . . . . . . 15 3.4 Image compression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 3.4.1 Training process . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.5 Binarizer and data embedding . . . . . . . . . . . . . . . . . . . . . . . 18 3.6 Image decompression and data extraction . . . . . . . . . . . . . . . . . 19 4 Experimental results 21 4.1 Performance comparison . . . . . . . . . . . . . . . . . . . . . . . . . . 21 5 Conclusion 29 Bibliography 31 | |
| dc.language.iso | en | |
| dc.subject | 遞歸神經網絡 | zh_TW |
| dc.subject | 資訊隱藏 | zh_TW |
| dc.subject | 影像壓縮 | zh_TW |
| dc.subject | data hiding | en |
| dc.subject | image compression | en |
| dc.subject | recurrent neural networks | en |
| dc.title | 基於神經網路之結合資訊壓縮隱藏方法 | zh_TW |
| dc.title | A Joint Data Hiding and Compression Scheme Based on Neural Networks | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 郭斯彥(Sy-Yen Kuo),雷欽隆(Chin-Laung Lei) | |
| dc.subject.keyword | 資訊隱藏,影像壓縮,遞歸神經網絡, | zh_TW |
| dc.subject.keyword | data hiding,image compression,recurrent neural networks, | en |
| dc.relation.page | 34 | |
| dc.identifier.doi | 10.6342/NTU201802591 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2018-08-08 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-107-1.pdf 未授權公開取用 | 10.09 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。