WITHDRAWN: Multi-classifiers and deep cnns for implementing image block truncation coding in e-learning platform

Block truncation coding (BTC) is a well known lossy compression scheme. Due to its low complexity and easy implementation, BTC has gained wide interest in its further development and application for image compression. Based on simple thresholding, BTC retains sharp edges and thus leads to artifacts such as the staircase effect. The second problem encountered in BTC is the splitting of homogeneous regions, which produces false contours. In this work a fuzzy approach of BTC to avoid truncating homogeneous blocks and to preserve smooth edges in two-cluster blocks is proposed. Each image block, viewed as a fuzzy set, is segmented into two clusters using a fuzzy clustering algorithm. The block is then encoded by modified fuzzy weighted means of the two clusters. Initialization strategies of the fuzzy clustering algorithm and a contextual quantization method are proposed. Experimental results show an improvement of visual quality of reconstructed images and peak signal-to-noise ratio when compared to BTC, economical BTC (EBTC), absolute moment BTC (AMBTC), and a minimum mean square error quantizer (MMSEQ). Computation time required by AMBTC, EBTC, and fuzzy BTC methods are reported.

Image Compression based on Block Truncation Coding Using Clifford Algebra

Objective: For reducing the data redundancy to save more hardware space and transmission bandwidth, data compression is used. Methods: For image compression, we have proposed a new method based on c-mean and absolute moment Block Truncation Coding (BTC) techniques. In this technique an image is segmented into several non-overlapping blocks. For each block, calculate the weighted c-mean by means of linear combination of its arithmetic mean and c-mean. The c-mean is evaluated by expressing every pixel into a sum of largest perfect square of non-negative integer. For each image block, the pixels are classified into two range of values based on weighted c-mean. The gray values of the image block which are greater than block weighted c-mean are considered as upper range and otherwise lower range. The weighted c-mean of upper range and lower range are termed as higher c-mean and lower c-mean respectively. Then construct the binary block matrix (0/1) based on weighted c-mean as a quantization level. In the decoder part, an image block is reconstructed by replacing the 1's with upper c-mean and 0's by lower c-mean of block matrix. Findings: The newly designed method is tested some8-bit standard images. It is also compared with related works in term of Peak Signal to Noise Ratio, Bit Rate, and Structural similarity index. It shows the effectiveness of the proposed method. Applications: Image storage is required for several purposes like document, medical images, magnetic resonance imaging and radiology, motion pictures etc. All such applications are based on image compression.

The Lagrange multiplier optimization technique is used to derive an exact relationship between absolute moment block truncation coding (AMBTC) and the minimum mean square error quantizer (MMSEQ). In addition, using computer simulation it is shown that the perceptual difference between the decoded images using these two approaches is almost unnoticeable. Furthermore, AMBTC and MMSEQ are separately incorporated into a subband coding scheme. The perceptual difference between the reconstructed images with subband coding is unnoticeable. While the MMSEQ requires an iterated search for the optimum threshold AMBTC uses the local mean value as the threshold. As a result, AMBTC is more practical than the MMSEQ. >

Internet Learning Image compression is a useful approach this is inevitable to save any snapshots in compressed sample. The compressed image is reconstructed the usage of image retrieval system for any applications. This method guarantees garage performance in various content management packages. Mainly, Internet Learning resource environment deals with greater area complexity. The e-learning storage area complexity may be reduced with the assist of image compression strategies. There are extraordinary forms of image compression techniques invented for constructing compressed assets. Block Truncation Coding (BTC) is a kind of lossy compression technique for reducing grey scale quantities the usage of blocking and quantizing stages. This is powerful technique for compressing the photos. In the scope, the want for extra active and Generative image compression methods is important to enhance BTC principles. This work proposes notably complex and novel Generative Adversarial BTC (GA-BTC) compression models with more than one variances. GABTC is developed with multi-layered Deep Neural Network (DNN) structures with GA neural models. The integration of each GA fashions and BTC standards improve the best of block constructions and reconstructions notably. The proposed work evaluates the version complexity and efficiency using diverse Internet Learning images with exclusive compression fine measurements.

Absolute Moment Block Truncation Coding (AMBTC) is an efficient and fast lossy compression technique for still images. It is easy to implement compared to transform coding. Interpolative AMBTC is a modified method of AMBTC compression. In this paper image data hiding in images using Interpolative AMBTC is proposed. In this method the secret image is stored in the bit plane of the AMBTC compressed image and is recovered during decompression process. Experimental results show that the proposed method achieves good quality decompressed image with low computational complexity.KeywordsData hidingCompressionBlock truncation codingAMBTCBit plane

Various eHealth applications based on the Internet of Things (IoT) contain a considerable number of medical images and visual electronic health records, which are transmitted through the Internet everyday. Information forensics thus becomes a critical issue. This paper presents a data hiding algorithm for absolute moment block truncation coding (AMBTC) images, wherein secret data, or the authentication code, can be embedded in images to enhance security. Moreover, in view of the importance of transmission efficiency in IoT, image compression is widely used in Internet-based applications. To cope with this challenge, we present a novel compression method named gradient-based (GB) compression, which is compatible with AMBTC compression. Therefore, after applying the block classification scheme, GB compression and data hiding can be performed jointly for blocks with strong gradient effects, and AMBTC compression and data hiding can be performed jointly for the remaining blocks. From the experimental results, we demonstrate that the proposed method outperforms other state-of-the-art methods.

Nowadays since the Internet is ubiquitous, the frequency of data transfer through the public network is increasing. Hiding secure data in these transmitted data has emerged broad security issue, such as authentication and copyright protection. On the other hand, considering the transmission efficiency issue, image transmission usually involves image compression in Internet-based applications. To address both issues, this paper presents a data hiding scheme for the image compression method called absolute moment block truncation coding (AMBTC). First, an image is divided into non-overlapping blocks through AMBTC compression, the blocks are classified four types, namely smooth, semi-smooth, semi-complex, and complex. The secret data are embedded into the smooth blocks by using a simple replacement strategy. The proposed method respectively embeds nine bits (and five bits) of secret data into the bitmap of the semi-smooth blocks (and semi-complex blocks) through the exclusive-or (XOR) operation. The secret data are embedded into the complex blocks by using a hidden function. After the embedding phase, the direct binary search (DBS) method is performed to improve the image quality without damaging the secret data. The experimental results demonstrate that the proposed method yields higher quality and hiding capacity than other reference methods.

Block truncation coding (BTC) is a class of image compression algorithms whose main technique is the partitioning of an image into pixel blocks that are then each encoded using a representative set of pixel values. It is commonly used because of its simplicity and low computational complexity. The Quadtree-segmented BTC (QTS-BTC), which utilizes a dynamic hierarchical segmentation technique, is among the most efficient in the BTC class. In this study, we propose a new BTC variant that introduces two ideas: (1) the use of a k -d tree for segmentation and (2) the use of a Mean Squared Error (MSE) threshold for dynamically determining the granularity of the blocks. We refer to this new BTC variant as the k -d Tree Segmented BTC (KTS-BTC), and we test this against some of the existing BTC variants by running the algorithms on a standard image compression dataset. The results show that the proposed variant yields low bit rates of the compressed images, even outperforming the state-of-the-art QTS-BTC, without a significant reduction in image quality as measured using the Peak Signal-to-Noise Ratio (PSNR). The utilization of k -d tree for image segmentation is further shown to have more impact than that of employing the MSE thresholding scheme as a block activity classifier.

This paper describes a color image compression scheme based on absolute moment block truncation coding (AMBTC) using Huffman coding. High degree of correlation between the RGB planes of a color image is reduced by transforming them to Y, Cb, Cr planes. Each plane is then encoded separately using the proposed method. The experiment has been conducted using the proposed scheme on standard color images. Experimental results show that the compression ratio of the proposed method is significantly improved when compared to color BTC and color AMBTC, with a relative distortion of reconstructed images.

An improved version of Block Truncation Coding (BTC) termed Multitone Block Truncation Coding (MTBTC) is proposed. The presented framework exploits the digital multi toning strategy to obtain a superior quality BTC images. Previously, the halftone techniques such as ordered dithering, error diffusion and dot diffusion are extended to obtain different version of BTC. Though it performs good, there are still many scope for improvements. In recent times digital multitoning is gaining prominence and advanced multitone screens such as direct multibit search and clustered dot screens are developed. This multitone screen can enhance the visual quality significantly and offer more homogenous and noise free output for halftone images. Considering this properties, an upgradation to the halftone based BTC is proposed in this paper through the use of sophisticated multitone screens. From the simulation results, it is concluded that the proposed framework can provide very high quality output than any existing BTC techniques. Another highlighting aspect is that the proposed technique can facilitate higher block size processing and it is computationally very simple. In overall, the proposed scheme is an ideal candidate to implement compression for high resolution images and can be exploited further to adopt in artificial intelligent tasks.

Block Truncation Coding (BTC) is a lossy data compression technique used for compression of images. BTC is a simple and fast image compression algorithm with less computational complexity than former schemes proposed. In this paper we propose a modified three-level BTC with an improved compression factor. Experimental results show that the suggested image compression methodology yields an image with better quality, low bit rate and lower computational complexity than the conventional three-level BTC.

Data hiding encompasses a wide range of applications related to hiding messages in digital images. The visual redundancy of images makes it possible to embed data in the images without attracting attention. Increasing the hiding capacity and decreasing the hiding distortion are prime objectives that data hiding intends to achieve. In this paper, we propose a high-payload data hiding scheme based on absolute moment block truncation coding (AMBTC) to minimize the impact of hiding. A two-level minimum mean square error (MMSE) quantizer generated by AMBTC is used to decrease the distortion associated with hiding. Also, we present a lookup table based on the symmetric property for adaptively hiding secrets in pixels to achieve high hiding capacity. We can embed almost 1.9 bits per pixel (bpp) with a high image quality of an average of 31 dB. Only 5.3% of pixels are changed during the data-hiding process. Compared with other schemes, we can use 1 bpp more relative payload for embedding with the same stego image quality. The experimental results show that the proposed scheme has better hiding performance because it allows a huge amount of secret data to be hidden while maintaining the high visual quality of the stego image.

In this paper, an optimized data embedding method based on Huang et al.’s work for absolute moment block truncation coding (AMBTC) is proposed. Huang et al.’s work successfully exploits the difference of quantization levels (QLs) for data embedment and has an excellent embedding performance. However, the modified QLs are not adjusted to minimize the distortion. In some rare cases, they might exceed the grayscale range. Moreover, the order of QLs in smooth blocks is not utilized for data embedment, losing the chance to embed one additional bit without deteriorating the image block. We propose a method to give analytical solutions to adjust QLs such that the distortions in both smooth and complex blocks are minimized. A subtle mechanism is also provided to ensure that no QLs will overflow or underflow. Moreover, the order of QLs is utilized in data embedment to further increase the payload without sacrificing the image quality. The experimental results reveal that the proposed method offers a better image quality over Huang et al.’s and other state-of-the-art works while providing a comparable or larger payload.

Block truncation coding (BTC) is an efficient technology for color image compression. An improved BTC algorithm, luminance bit-map based BTC (LBBBTC), is presented in this paper. The LBB-BTC employs luminance bit-map to represent the three R, G and B bit-maps more exactly. Moreover, by adding 3 bits to indicate the entirely differences between Y and R, G or B bit-maps, respectively, the coding performance is improved obviously. Simulation results show that the proposed LBB-BTC performs as well as the BTC in terms of subject visual quality and PSNR, and significantly improve the compression ratio of BTC.