Image Communication System Research Articles

Exploring AI-driven Innovations in Image Communication Systems for Enhanced Medical Imaging Applications

Artificial intelligence (AI) has emerged as a promising avenue for enhancing medical imaging systems and improving clinical workflows. This research explores innovative applications of AI and deep learning for image communication networks in healthcare. Specifically, we develop an intelligent image compression framework that optimizes data transmission and speeds interpretation of radiology scans. Our approach combines convolutional neural networks, generative adversarial networks, and specialized image filters to balance communication efficiency, diagnostic accuracy, and system latency. Rigorous experiments validate superior performance over traditional methods and commercial products across modalities including MRI, CT, and ultrasound. Crucially, the proposed methods demonstrate expert-level precision in anatomy labeling and pathology detection. By intelligently streamlining image transfer and analytics, this AI-powered system could facilitate ubiquitous, real-time diagnostics via telemedicine. Enhanced connectivity between imaging devices and clinical specialists can improve patient outcomes and reduce healthcare costs. Our solutions set the stage for more advanced AI integration in imaging networks and data-intensive medicine

A Specific Task-Oriented Semantic Image Communication System for Substation Patrol Inspection

A Specific Task-Oriented Semantic Image Communication System for Substation Patrol Inspection

Robust Deep Learning Models for OFDM-Based Image Communication Systems in Intelligent Transportation Systems (ITS) for Smart Cities

Internet of Things (IoT) ecosystem in smart cities demands fast, reliable, and efficient image data transmission to enable real-time Computer Vision (CV) applications. To fulfill these demands, an Orthogonal Frequency Division Multiplexing (OFDM)-based communication system has been widely utilized due to its higher spectral efficiency and data rate. When adapting such a system to achieve fast and reliable image transmission over fading channels, noise is introduced in the signal which heavily distorts the recovered image. This noise independently corrupts pixel values, however, certain intrinsic properties of the image, such as spatial information, may remain intact, which can be extracted as multidimensional features (in the convolution layers) and interpreted (in the top layers) by a Deep Learning (DL) model. Therefore, the current study analyzes the robustness of such DL models utilizing various OFDM-based image communication systems for CV applications in an Intelligent Transportation Systems (ITS) environment. Our analysis has shown that the EfficientNetV2-based model achieved a range of 70–90% accuracy across different OFDM-based image communication systems over the Rayleigh Fading channel. In addition, leveraging different data augmentation techniques further improves accuracy up to 18%.

MIDOM—A DICOM-Based Medical Image Communication System

Despite the existing medical infrastructure being limited in terms of interoperability, the amount of medical multimedia transferred over the network and shared through various channels increases rapidly. In search of consultations with colleagues, medical professionals with the consent of their patients, usually exchange medical multimedia, mainly in the form of images, by using standard instant messaging services which utilize lossy compression algorithms. That consultation paradigm can easily lead to losses in image representation that can be misinterpreted and lead to the wrong diagnosis. This paper presents MIDOM—Medical Imaging and Diagnostics on the Move, a DICOM-based medical image communication system enhanced with a couple of variants of our previously developed custom lossless Classification and Blending Predictor Coder (CBPC) compression method. The system generally exploits the idea that end devices used by the general population and medical professionals alike are satisfactorily performant and energy-efficient, up to a point to support custom and complex compression methods successfully. The system has been implemented and appropriately integrated with Orthanc, a lightweight DICOM server, and a medical images storing PACS server. We benchmarked the system thoroughly with five real-world anonymized medical image sets in terms of compression ratios and latency reduction, aiming to simulate scenarios in which the availability of the medical services might be hardly reachable or in other ways limited. The results clearly show that our system enhanced with the compression methods in the question pays off in nearly every testing scenario by lowering the network latency to at least 60% of the latency required to send raw and uncompressed image sets and 25% in the best-case, while maintaining the perfect reconstruction of medical images and, thus, providing a more suitable environment for healthcare applications.

A Perceptual Encryption-Based Image Communication System for Deep Learning-Based Tuberculosis Diagnosis Using Healthcare Cloud Services

Block-based perceptual encryption (PE) algorithms are becoming popular for multimedia data protection because of their low computational demands and format-compliancy with the JPEG standard. In conventional methods, a colored image as an input is a prerequisite to enable smaller block size for better security. However, in domains such as medical image processing, unavailability of color images makes PE methods inadequate for their secure transmission and storage. Therefore, this study proposes a PE method that is applicable for both color and grayscale images. In the proposed method, efficiency is achieved by considering smaller block size in encryption steps that have negligible effect on the compressibility of an image. The analyses have shown that the proposed system offers better security with only 12% more bitrate requirement as opposed to 113% in conventional methods. As an application of the proposed method, we have considered a smart hospital that avails healthcare cloud services to outsource their deep learning (DL) computations and storage needs. The EfficientNetV2-based model is implemented for automatic tuberculosis (TB) diagnosis in chest X-ray images. In addition, we have proposed noise-based data augmentation method to address data deficiency in medical image analysis. As a result, the model accuracy was improved by 10%.

Analysis of the Lowest Memory Consumption (Memory Usage) Through Running Different Cryptography Techniques for Different Types of Images

Nowadays security of image communication systems is highly important. It is essential to provide protection for image data confidentiality from illegal users. The detection and identification of unauthorized users is still a difficult and complex task. Many researchers have proposed several works to provide security of the transmission of the image. The objective of this article is to provide a comparative study of the current techniques that have been widely used. This article concentrates on various types of cryptography algorithms that are existing, like AES, MAES, DES, 3DES, RSA, and Blowfish, and investigation the lowest energy consumption (memory usage) through running several cryptographic algorithms on different image formatting.

Picture Archiving and Communication Systems (PACS) as a Solution to Inequality in the Number of Radiological Resources in West Java

Inequality of health care facilities, especially radiology resources, occurs in West Java Province. There are many class A hospitals in provincial capitals, while in areas far from the provincial capital and from DKI Jakarta Province, the quantity and quality of hospitals are still lacking. Likewise with the quantity of radio diagnostic instruments and human resources. 12 radiology specialists and an additional 192 radiographers are needed in West Java Province. Archiving and image communication systems (PACS) can be used as a solution so that health workers in hospitals located far from the city or district centers can consult, and expert conclusions can be obtained from radiology specialists at referral centers.
 Keywords: PACS, radio diagnostic, radiology specialist, radiographer, West Java

Demand-side Synergy and Firms' Competitive and Collaborative Strategies over Platform Lifecycle

The paper examines how emergence of a digital platform that bolsters demand-side synergy affects complementary product firms’ competitive and collaborative strategies and how they evolve across the platform lifecycle. Building on demand-side research and digital platform literature, I suggest the bundling of a digital platform service can be an important source of firms’ demand-side product synergy and the potential size of demand-side economies of scope may vary across different stages of platform evolution. Using the context of U.S. medical diagnostic imaging equipment manufacturers 1987-2013 and the introduction of an image communication system in 1993, I find that on average, imaging device manufacturers spanning across multiple complementary product markets are more likely to bundle a platform service as opposed to the firms specialized in a single product market, and more so in the early period of the platform lifecycle. The results also suggest that firms with product/platform bundling are likely to further increase diversity in their product lines and create walled gardens around their platform services. In terms of within-industry collaborations, the complementary product firms with platform service are more likely to engage in alliances than those without, but less so as the platform matures.

All-Solid-State Optical Phased Arrays of Mid-Infrared Based Graphene-Metal Hybrid Metasurfaces.

Optical phased arrays (OPAs) are essential optical elements in applications that require the ability to manipulate the light-wavefront, such as beam focusing and light steering. To miniaturize the optical components, active metasurfaces, especially graphene metasurfaces, are used as competent alternatives. However, the metasurface cannot achieve strong resonance effect and phase control function in the mid-infrared region only relying on a single-layer graphene. Here we present a graphene-metal hybrid metasurface that can generate a specific phase or a continuous sweep in the range of a 275°-based single-layer graphene structure. A key feature of our design is that the phase adjustment mainly depends on the combination mechanism of resonance intensity and frequency modulation. An all-solid-state, electrically tunable, and reflective OPA is designed by applying the bias voltage to a different pixel metasurface. The simulation results show that the maximum deflection angle of the OPA can reach 42.716°, and the angular resolution can reach 0.62°. This design can be widely applied to mid-infrared imaging, optical sensing, and optical communication systems.

FAST FRACTAL IMAGE ENCODER DESIGN

Fractal theory has been widely applied in the filed of image compression due to the advantage of resolution independence, fast decoding, and high compression ratio. However, it has a fatal shortcoming of intolerant encoding time because that every range block is need to find its corresponding best matched domain block in the full image. Therefore, it has not been widely applied as other coding schemes in the field of image compression. In this paper, an algorithm is proposed to improve this time-consuming encoding drawback by the adaptive searching window, partial distortion elimination and characteristic exclusion algorithms. Proposed can efficient decrease the encoding time significantly. In addition, the compression ratio is also raised due to the reduced searching window. Conventional fractal encoding for a 512 by 512 image need search 247009 domain blocks for every range block. Experimental results show that our proposed method only search 120 domain blocks which is only 0.04858% compared to conventional fractal encoder for every range block to encode Lena 512 by 512 8-bit gray image at the bit rate of 0.2706 bits per pixel (bpp) while maintaining almost the same decoded quality as conventional fractal encoder does. This paper contributes to the research of encoder of fast image communication system.

Broadband efficient focusing on-chip integrated nano-lens

As a basic optical element, optical lens is widely used for realizing the focusing, imaging and optical communication systems. Light of different wavelengths will propagate at different speeds. A beam of polychromatic light will produce chromatic dispersion after passing through a single optical device, which prevents the ordinary lenses from focusing the light of different wavelengths into a point. This means that the light of different wavelengths cannot be focused ideally. Traditional focusing systems can solve this problem by superimposing multiple lenses, but this is at the expense of increasing the complexity, weight, and cost of the system, and is not suitable for highly integrated nano-optical systems. At present, a better solution is to use the plane metalens, that is, using the metasurface to control the amplitude, phase and polarization at each point in space. However, the plane metalens is difficult to directly integrate on the chip. An intelligent algorithm developed by combining finite element method with genetic algorithm is used to optimize the design of multi-channel on-chip wavelength router devices and polarization router devices. In this paper, combining with years’ research results of the theory of multiple scattering coherent superposition of disordered media, the use of intelligent algorithm to design an on-chip integrated nano-lens that can achieve efficient focusing from the visible to the near infrared band. In the lens structure SiO<sub>2</sub> serves as a substrate, and the arrangement structure of SiC rectangular column is designed. The substrate size is only 2 μm × 2 μm. The lens achieves low-dispersion focusing in the band from 470 nm to 1734 nm, with a focusing efficiency of over 55% at the highest level and 30% at the lowest level, and an average focusing efficiency of 42.1%. A 200-nm waveguide is added behind the focusing region. After refocusing through the waveguide, the laser beam with a size of 2 μm can be focused by the coupling of the lens and the waveguide into a beam below 200 nm in size. The focusing efficiency goes up to 80%. At the same time, the intelligent algorithm can be applied to different types of structures. The focusing lens structures composed of triangle, diamond, or circular nano columns are designed, which can achieve an approximate focusing effect and efficient coupling propagation efficiency. This work provides important ideas for developing broadband and efficient focusing nano-lens, as well as a new way to achieve the high-density integrated nanophotonic devices.

Implementation of a Real Time Analog Secure Image Communication System via a Chaotic Circuit

A new secure image communication system has been designed and implemented based on a synchronized chaotic circuit. The new chaotic circuit, which has recently proposed by one of the authors contains a resistor, two inductors, and two diodes (i.e. R2L2D). The synchronization part operates with a master – slave configuration. In order to achieve the real-time communication, initially the analog master circuit has been implemented to generate chaotic sequences of numbers. Then, that analog tool has been transmitted to a computer via an analog/digital converter and a hidden image has been obtained. Besides, the slave circuit has also received a copy of that chaotic sequences in order to use it in subtraction process of image gray levels. The digital chaotic image has been transmitted to the slave circuit via a digital/analog converter with an efficient method and the decrypted image has been obtained in real-time. The advantage of that technique over the conversional ones is that it does not require any saved copy of the digital data, even for sending them in gray images to the receiver, since it is real-time. The conventional techniques use the stored and processed data and that can cause security problems in today’s advanced web media. Thus to send the encrypted image in a real-time device by using an analog chaotic equipment has certain security superiority. The analyses on the preliminary decrypted images proves that the process is efficient in time and secure.

Quality assessment of images with multiple distortions based on phase congruency and gradient magnitude

In image communication systems, images are often contaminated by multiple types of distortions. However, most existing image quality assessment (IQA) methods mainly focused on a single type of distortions. In this paper, we proposed a no-reference (NR) IQA method for images with multiple distortions. Image distortions not only destroy the intensity of low-level image features, but also alter their distribution, to both of which the human vision system (HVS) is sensitive. Based on these observations, low-level features are represented by phase congruency (PC) which is consistent with human perception. The distribution of low-level features is extracted using local binary pattern (LBP) in PC domain at multiple scales, which can effectively characterize the impact of multiple distortions on images. Given that PC is contrast invariant while the contrast does affect perceptual image quality of the HVS, image gradient magnitude (GM) is employed as a weighting factor for LBP histogram creation. Finally a support vector regression model is trained to map the gradient-weighted LBP histograms in PC domain at multi-scale to quality scores. Experimental results on two benchmark databases demonstrate that the proposed method achieves high consistency with subjective perception and performs better than other state-of-the-art full-reference (FF) and NR IQA methods.

Efficient and Secure Image Communication System Based on Compressed Sensing for IoT Monitoring Applications

The Internet of Things (IoT) has attracted extensive attention in the information field. Its rapid development has promoted several monitoring application domains. However, the resource constraint of sensor nodes and the security of data transmission have emerged as significant issues. In this paper, an image communication system for IoT monitoring applications is exploited to solve the above-mentioned problems simultaneously. The proposed system can satisfy the requirements of sensor nodes for low computational complexity, low-energy consumption, and low storage overhead. We also present a new compressed sensing (CS) model, as well as the corresponding parallel reconstruction algorithm, which help to reduce the image encryption/decryption time. Based on chaotic systems, we integrate the quantization and diffusion operations into the system to further enhance the transmission security. The simulations are executed to demonstrate the feasibility and the effectiveness of the proposed method. Compared with the traditional CS, our numerical results indicate that the proposed model reduces 413 ms computation time and 3.13 × 10 6 elements stored for large-scale images. Besides, we verify the flexibility and the diversity of choosing two submatrices for different-sized images. Experimental results also show the proposed system performs well in terms of security performance. Particularly the key space reaches 2253.

Adaptive compression method for underwater images based on perceived quality estimation

Underwater image compression is an important and essential part of an underwater image transmission system. An assessment and prediction method of effectively compressed image quality can assist the system in adjusting its compression ratio during the image compression process, thereby improving the efficiency of the image transmission system. This study first estimates the perceived quality of underwater image compression based on embedded coding compression and compressive sensing, then builds a model based on the mapping between image activity measurement (IAM) and bits per pixel and structural similarity (BPP-SSIM) curves, next obtains model parameters by linear fitting, and finally predicts the perceived quality of the image compression method based on IAM, compression ratio, and compression strategy. Experimental results show that the model can effectively fit the quality curve of underwater image compression. According to the rules of parameters in this model, the perceived quality of underwater compressed images can be estimated within a small error range. The presented method can effectively estimate the perceived quality of underwater compressed images, balance the relationship between the compression ratio and compression quality, reduce the pressure on the data cache, and thus improve the efficiency of the underwater image communication system.

OFDM-ML-IDM System for Efficient Wireless Image Transmission

In this paper, orthogonal frequency division multiplexing multi-layer interleaved division multiplexing (OFDM-ML-IDM) system is proposed as an efficient image communication system. Regardless the image compression technique, in the proposed image communication system the digital image signal is represented with the digital data of non-compressed image format. Recently, coded IDM communications never got much attention as a promising image transmission technique. The main idea is to use both multi-layer coded IDM and chip-by-chip iterative detection concepts for both bandwidth efficiency and efficient detection, respectively. Different simulation parameters effect such as number of IDM layers, number of receiver iterations and non-linear power amplifier effects are studied. The system performance is also investigated in wireless Additive White Gaussian Noise (AWGN) and Rayleigh fading channels. The key performance indicators that are used for measuring the system performance are the visual quality metric in-terms of Peak Signal to Noise Ratio (PSNR) performance and the system reliability in-terms of bit error rate performance. The main contribution in this paper is to prove that: based on the application requirement and at definite SNR points; the multi-layer IDM reflects a slight performance change compared with the bandwidth consumption. Simulation results show that at low $$SNR = 6 \;{\text{dB}}$$ for single and double layers case study, the PSNR performance is $$51.1073 \;{\text{dB}}$$ and $$48.5636\; {\text{dB}}$$ respectively at wireless AWGN channel, but the double layer IDM achieves $$50\%$$ efficient bandwidth than single layer for exchange only $$2.5437\; {\text{dB}}$$ which is considered a minor PSNR performance compared with single layer IDM, as well as the quad layers PSNR performance is $$36.1849\; {\text{dB}}$$ with $$25\varvec{\% }$$ bandwidth consumption. For high $$SNR$$ , the performance has an excellent visual quality metric with efficient bandwidth consumption. Signal distortion technique such as clipping and companding methods are used to overcome the originated high peak to average power ratio based ML-IDM with large OFDM envelope fluctuations; hence we study the clip ratio and companding parameter effect on the visual quality metric performance.

Blind image separation using pyramid technique

Signal and image separation is an important processing step for accurate image reconstruction, which is increasingly applied to many medical imaging applications and communication systems. Most of the conventional separation approaches are based on frequency domain and time domain. These approaches, however, are sensitive to noise and thus often produce undesirable results.In this paper, we propose a novel method of image separation. It incorporates the property of pyramid component extracted from the image and a finite ridgelet transform (FRT) to obtain a precise analysis of the images and thus correctly separate the images even in a highly noisy environment. We obtain the multiple components of the target images by employing a pyramid processing, which operates in the various domains and thus can decompose the image into multiple components.In addition, the pyramid decomposition in the proposed method can eliminate information redundancy in the target image and thus can substantially enhance the quality of image separation. We have conducted extensive simulations, which demonstrate that the proposed pyramid structure with FRT outperforms the conventional methods based on time domain and trigonometric transforms.

A Genetic Algorithm for the Generation of Packetization Masks for Robust Image Communication.

Image interleaving has proven to be an effective solution to provide the robustness of image communication systems when resource limitations make reliable protocols unsuitable (e.g., in wireless camera sensor networks); however, the search for optimal interleaving patterns is scarcely tackled in the literature. In 2008, Rombaut et al. presented an interesting approach introducing a packetization mask generator based in Simulated Annealing (SA), including a cost function, which allows assessing the suitability of a packetization pattern, avoiding extensive simulations. In this work, we present a complementary study about the non-trivial problem of generating optimal packetization patterns. We propose a genetic algorithm, as an alternative to the cited work, adopting the mentioned cost function, then comparing it to the SA approach and a torus automorphism interleaver. In addition, we engage the validation of the cost function and provide results attempting to conclude about its implication in the quality of reconstructed images. Several scenarios based on visual sensor networks applications were tested in a computer application. Results in terms of the selected cost function and image quality metric PSNR show that our algorithm presents similar results to the other approaches. Finally, we discuss the obtained results and comment about open research challenges.

Application of cloud storage in mega image-text data of hospital imaging archiving and communication systems

Architectural changes with Tianyi cloud storage of China Telecom were made to the up/down loading of the image-text mega data created in the picture archiving and communication systems(PACS)of the hospital.Thanks to the changes, the data volume uploaded by the PACS of the hospital reached 160G per day, with average upload speed up to 5.3M/second; supporting online query of all image-text data of patients.The authors hold cloud storage technology as safe and reliable, and such other merits as supporting data encryption, automatic offsite redundancy, almost online real-time read/write access, almost infinite extendibility, fast self-healing and off-site disaster-tolerant backup. Key words: Picture archiving and communication systems(PACS); Mega data; Imaging center; Cloud storage; Security

Evaluation of the wavelet image two-line coder: A low complexity scheme for image compression

This paper introduces the wavelet image two-line (Wi2l) coding algorithm for low complexity compression of images. The algorithm recursively encodes an image backwards reading only two lines of a wavelet subband, which are read in blocks of 512 bytes from flash memory. It thus only requires very little memory, i.e., a memory array for two wavelet subband lines, an array to store intermediate tree level data, and an array for writing binary data. A picture of 256×256 pixels would require 1152 bytes of memory. Computation time for the coding is derived analytically and measured on a real system. The times on a low-cost microcontroller for 256×256 grayscale pictures are measured as 0.25–0.6s for encoding and 0.22–0.77s for decoding. The algorithm can thus realize a low complexity system for compression of images when combined with a customized scheme for the wavelet transform; low complexity here refers to low memory, minimum write access to flash memory, usage of integer operations only, and low conceptual complexity (ease of implementation). As demonstrated in this paper, a compression performance similar to JPEG 2000 and the more recent Google WebP picture compression is achieved. The compression system uses flash memory (SD or MMC card) and a small camera sensor thus building an image communication system. It is also suitable for mobile devices or satellite communication. The underlying C source code is made publicly available.