检索结果-内蒙古大学图书馆

Fusion of Deep Learning and Compressed Domain Features for Content-Based Image Retrieval

IEEE TRANSACTIONS ON IMAGE PROCESSING 2017年第12期26卷 5706-5717页

作者： Liu, Peizhong Guo, Jing-Ming Wu, Chi-Yi Cai, Danlin Huaqiao Univ Coll Engn Quanzhou 362021 Peoples R China Natl Taiwan Univ Sci & Technol Dept Elect Engn Taipei 10607 Taiwan Quanzhou Normal Univ Sch Math & Comp Sci Quanzhou 362000 Peoples R China

This paper presents an effective image retrieval method by combining high-level features from convolutional neural network (CNN) model and low-level features from dot-diffused block truncation coding (DDBTC). The low-level features, e.g., texture and color, are constructed by vector quantization -indexed histogram from DDBTC bitmap, maximum, and minimum quantizers. Conversely, high-level features from CNN can effectively capture human perception. With the fusion of the DDBTC and CNN features, the extended deep learning two-layer codebook features is generated using the proposed two-layer codebook, dimension reduction, and similarity reweighting to improve the overall retrieval rate. Two metrics, average precision rate and average recall rate (ARR), are employed to examine various data sets. As documented in the experimental results, the proposed schemes can achieve superior performance compared with the state-of-the-art methods with either low- or high-level features in terms of the retrieval rate. Thus, it can be a strong candidate for various image retrieval related applications.

关键词： Content-based image retrieval deep learning convolutional-neural network block truncation coding halftoning

来源：评论

学校读者我要写书评

暂无评论

Tamper detection and image recovery for BTC-compressed images

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2017年第14期76卷 15435-15463页

作者： Hu, Yu-Chen Choo, Kim-Kwang Raymond Chen, Wu-Lin Providence Univ Dept Comp Sci & Informat Management 200 Chung Chi RdSec 7Taiwan Blvd Taichung 43301 Taiwan Univ Texas San Antonio Dept Informat Syst & Cyber Secur San Antonio TX USA Univ South Australia Sch Informat Technol & Math Sci Adelaide SA Australia

To ensure the integrity of images compressed using block truncation coding (BTC), a tamper detection and image recovery scheme is proposed in this paper. In this scheme, the size of the authentication data can be adaptively selected according to the user's requirement. The authentication data is embedded in the value differences of the quantization levels in each BTC-compressed image block. Multiple copies of the recovery data are embedded into the bit maps of the smooth blocks. Experimental results show that the proposed scheme performs well in terms of detection precision and the embedded image quality. Meanwhile, the tampered areas can be roughly recovered by using the proposed scheme.

关键词： Tamper detection Image recovery block truncation coding Image authentication Fragile watermarking

来源：评论

学校读者我要写书评

暂无评论

Data hiding in AMBTC images using quantization level modification and perturbation technique

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2017年第3期76卷 3761-3782页

作者： Hong, Wien Chen, Tung Shou Yin, Zhaoxia Luo, Bin Ma, Yuanbo Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing Jiangsu Peoples R China Natl Taichung Univ Sci & Technol Dept Comp Sci & Informat Engn Taichung Taiwan Anhui Univ Minist Educ Key Lab Intelligent Comp & Signal Proc Hefei Peoples R China Sun Yat Sen Univ Nanfang Coll Dept Elect Commun & Software Engn Guangzhou Guangdong Peoples R China

A novel data hiding method for Absolute Moment block truncation coding (AMBTC) compressed image based on quantization level modification is proposed. blocks of AMBTC-compressed image are classified into two categories, namely smooth and complex, according to a predefined threshold. For smooth blocks, the bitmap is replaced by secret data for data embedment. Meanwhile, the corresponding quantization levels are modified to achieve a minimum distortion. If a larger payload is required, the modified quantization levels can be further perturbed for carrying two additional bits. If the blocks are complex, one data bit can be embedded with no distortion by swapping the values of the two quantization levels together with bitmap flipping. In addition, a suppress threshold mechanism is used to prevent from the application of the perturbation technique at low payload to maintain the image quality. The proposed method minimizes the distortion of each stego block while ensuring high payload, thus the embedding efficiency can be enhanced. Experimental results demonstrate the improvement of the proposed method compared with other related state-of-art works.

关键词： block truncation coding Data hiding Threshold mechanism

来源：评论

学校读者我要写书评

暂无评论

A Cost and Power Efficient Image Compressor VLSI Design With Fuzzy Decision and block Partition for Wireless Sensor Networks

引用

IEEE SENSORS JOURNAL 2017年第15期17卷 4999-5007页

作者： Chen, Shih-Lun Wu, Guei-Shian Chung Yuan Christian Univ Dept Elect Engn Taoyuan 32023 Taiwan

This paper presents a novel hardware-oriented image compression algorithm and its very large- scale integration (VLSI) implementation for wireless sensor networks. The proposed novel image compression algorithm consists of a fuzzy decision, block partition, digital halftoning, and block truncation coding (BTC) techniques. A novel variable-size block partition technique was used in the proposed algorithm to improve image quality and compression performance. In addition, eight different types of blocks were encoded by Huffman coding according to probability to increase the compression ratio further. In order to achieve the low-cost and low-power characteristics, a novel iteration-based BTC training module was created to get representative levels and meet the requirement of wireless sensor networks. A prediction and a modified Golomb-Rice coding modules were designed to encode the information of representative levels to achieve higher compression performance. The proposed algorithm was realized by a VLSI technique with an UMC 0.18-mu m CMOS process. The synthesized gate counts and core area of this design were 6.4 k gate counts and 60 000 mu m2, respectively. The operating frequency and power consumption were 100 MHz and 3.11 mW respectively. Compared with previous JPEG, JPEG-LS, and fixed-size BTC-based designs, this work reduced 20.9% gate counts more than previous designs. Moreover, the proposed design required only a one-linebuffer memory rather than a frame-buffer memory required by previous designs.

关键词： block partition block truncation coding digital halftoning fuzzy decision Golomb-Rice coding image compression wireless camera wireless sensor network VLSI

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding in Encrypted AMBTC Compressed Images 15th

Reversible Data Hiding in Encrypted AMBTC Compressed Images

引用

15th International Workshop on Digital-Forensics and Watermarking 2016 (IWDW)

作者： Niu, Xuejing Yin, Zhaoxia Zhang, Xinpeng Tang, Jin Luo, Bin Anhui Univ Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230601 Anhui Peoples R China Shanghai Univ Sch Commun & Informat Engn Shanghai 200072 Peoples R China

ISBN: (纸本)9783319534640;9783319534657

Signal processing in encrypted domain has attracted high attention during the needs of content security and privacy protection. Reversible data hiding in encrypted images (RDH-EI) also becomes a hot topic. However, most of the published techniques are designed for uncompressed images rather than JPEG-, VQ- and BTC-compressed images. In this paper, for the first time, a RDH-EI method for AMBTC images is proposed. In this method, the higher mean and lower mean of a triple in AMBTC compressed image is encrypted by using stream cipher with the same random bits. Therefore, the spatial correlation of a nature image is preserved and redundant space can be exploited by using the histogram of prediction error. Experimental results demonstrate that the proposed method can embed considerable bits while leave little distortion.

关键词： Signal processing in encrypted domain Privacy protection block truncation coding Reversible Data Hiding in Encrypted Images

来源：评论

学校读者我要写书评

暂无评论

Improve Information Rate in Thien and Lin's Image Secret Sharing Scheme Using Huffman coding Technique

Improve Information Rate in Thien and Lin's Image Secret Sha...

引用

3rd International Conference on Computing, Communication, Control and Automation (ICCUBEA)

作者： Markandeya, Nehal Patil, Sonali Pimpri Chinchwad Coll Engn Dept Comp Engn Pune 44 Maharashtra India

ISBN: (纸本)9781538640081

Shares in image secret sharing play a vital role. These image shares has size greater than or equal to size of original image, it require high bandwidth while transmission. Because of the excessive bandwidth requirements of image there is need to reduce the bandwidth of images. To reduce the size of image, Huffman compression coding techniques are used. By reducing the image share size in Thien and Lin's secret sharing scheme using Huffman coding technique leads to reduced bandwidth overhead. In proposed approach Huffman coding is applied on secret image before applying secret sharing. This approach helps to increase the compression ratio of share images by 14% than existing system.

关键词： Absolute moment block truncation coding block truncation coding Huffman coding Image secret sharing Image compression

来源：评论

学校读者我要写书评

暂无评论

Distributed Content Based Image Search Engine using Hadoop Framework 6

Distributed Content Based Image Search Engine using Hadoop F...

引用

IEEE International Conference on Communication and Signal Processing (ICCSP)

作者： Uttarwar, Dhananjay Agarwal, Aakash Kadiwar, Riyaz Katkar, Vijay D. Pimpri Chinchwad Coll Engn Dept Informat Technol Pune Maharashtra India

ISBN: (纸本)9781509038008

With decrease in cost of multimedia capturing and storage devices;amount of multimedia data present on WWW has increased exponentially. Content Based Visual data Retrieval is an ongoing research area for efficient data handling on Internet-scale. This paper presents a Hadoop based image search engine framework for extracting similar images from huge volume of available images. Performance of presented approach is evaluated using various image visual feature extraction methods like block truncation coding, Fuzzy Edge Detection and Local Binary Patterns.

关键词： block truncation coding Content-based Image Retrieval Fuzzy Edge Detection Hadoop Image Search Engine Local Binary Pattern MapReduce

来源：评论

学校读者我要写书评

暂无评论

Ratio‐modified block truncation coding algorithms for reduced bitrates

引用

The Journal of Photographic Science 2011年第1期59卷 25-31页

block truncation coding (BTC) technique is a simple and fast image compression algorithm since complicated transforms are not used. The principle used in BTC algorithm is to use two‐level quantiser that adapts to local properties of the image while preserving the first‐ or first‐ and second‐order statistical moments. The parameters transmitter or stored in the BTC algorithm are statistical moments and bitplane yielding good quality images at a bitrate of 2 bits per pixel (bpp). In this paper, two algorithms for modified BTC (MBTC) are proposed for reducing the bitrate below 2 bpp. The principal used in the proposed algorithms is to use the ratio of moments which is a smaller value when compared to absolute moments. The ratio values are then entropy coded. The bitplane is also coded to remove the correlation among the bits. The proposed algorithms are compared with MBTC and the algorithms obtained by combining JPEG standard with MBTC in terms of bitrate, peak signal‐to‐noise ratio (PSNR) and subjective quality. It is found that the reconstructed images obtained using the proposed algorithms yield better results.

关键词： image coding block truncation coding JPEG arithmetic coding bitplane coding

来源：评论

学校读者我要写书评

暂无评论

An adaptive image steganography using AMBTC compression and interpolation technique

引用

OPTIK 2016年第1期127卷 471-477页

作者： Tang, Mingwei Zeng, Shenke Chen, Xiaoliang Hu, Jie Du, Yajun Xihua Univ Sch Math & Comp Sci Technol Chengdu 610039 Peoples R China Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 610031 Peoples R China

It is a hot topic in the design of information hiding algorithm by a combination of compressed technique and interpolation technique in the future. Higher capacity and better image quality are one of the foremost research contents of information hiding. In recent years, an adaptive information hiding has been a hot content of research in the field of information hiding and network security. This paper proposed an adaptive image steganography using absolute moment block truncation coding compression (AMBTC compression) and interpolation technique (ASAI), which can improve the performance of information hiding scheme. The ASAI scheme proposed can offer the benefits of high embedding capacity with low computational complexity and good image quality. The experimental results demonstrate that the proposed ASAI scheme has superior performance than others. (C) 2015 Elsevier GmbH. All rights reserved.

关键词： Steganography Compression technique Interpolation technique High capacity block truncation coding

来源：评论

学校读者我要写书评

暂无评论

Joint Compression/Watermarking Scheme Using Majority-Parity Guidance and Halftoning-Based block truncation coding

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2010年第8期19卷 2056-2069页

作者： Guo, Jing-Ming Liu, Yun-Fu Natl Taiwan Univ Sci & Technol Dept Elect Engn Taipei Taiwan

In this paper, a watermarking scheme, called majority-parity-guided error-diffused block truncation coding (MPG-EDBTC), is proposed to achieve high image quality and embedding capacity. EDBTC exploits the error diffusion to effectively reduce blocking effect and false contour which inherently exhibit in traditional BTC. In addition, the coding efficiency is significantly improved by replacing high and low means evaluation with extreme values substitution. The proposed MPG-EDBTC embeds a watermark simultaneously during compression by evaluating the parity value in a predefined parity-check region (PCR). As documented in the experimental results, the proposed scheme can provide good robustness, image quality, and processing efficiency. Finally, the proposed MPG-EDBTC is extended to embed multiple watermarks and achieves excellent image quality, robustness, and capacity. Nowadays, most multimedia is compressed before it is stored. It is more appropriate to embed information such as watermarks during compression. The proposed method has been proved to solve effectively the inherent problems in traditional BTC, and provide excellent performance in watermark embedding.

关键词： block truncation coding digital halftoning digital watermarking error diffusion

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：