Image Processing System Research Articles

Automatic recognition of white blood cell images with memory efficient superpixel metric GNN: SMGNN.

An automatic recognizing system of white blood cells can assist hematologists in the diagnosis of many diseases, where accuracy and efficiency are paramount for computer-based systems. In this paper, we presented a new image processing system to recognize the five types of white blood cells in peripheral blood with marked improvement in efficiency when juxtaposed against mainstream methods. The prevailing deep learning segmentation solutions often utilize millions of parameters to extract high-level image features and neglect the incorporation of prior domain knowledge, which consequently consumes substantial computational resources and increases the risk of overfitting, especially when limited medical image samples are available for training. To address these challenges, we proposed a novel memory-efficient strategy that exploits graph structures derived from the images. Specifically, we introduced a lightweight superpixel-based graph neural network (GNN) and broke new ground by introducing superpixel metric learning to segment nucleus and cytoplasm. Remarkably, our proposed segmentation model superpixel metric graph neural network (SMGNN) achieved state of the art segmentation performance while utilizing at most 10000$ \times $ less than the parameters compared to existing approaches. The subsequent segmentation-based cell type classification processes showed satisfactory results that such automatic recognizing algorithms are accurate and efficient to execeute in hematological laboratories. Our code is publicly available at https://github.com/jyh6681/SPXL-GNN.

Research on the design of automatic image processing function for intelligent face management system

Abstract Around the background of rapid development of intelligent technology, an efficient image processing system oriented to the smart management of human faces is focused on. The system is mainly developed towards high speed, high definition, high integration and reliability. The article investigates a novel automatic image processing algorithm, covering three key modules: automatic exposure control, color interpolation and chromaticity space conversion. The algorithm can process the output image of CMOS sensor in Bayer format in real time and adjust the image parameters to obtain a high-quality image. In terms of face recognition performance, the algorithm has a significant advantage in recognition speed compared with other algorithms, and the average recognition accuracy reaches 94.258%. In the practical application of ID card portrait processing, the image shows a more uniform grayscale distribution in the range of 5 to 255 after automatic color adjustment, and the color quality is significantly improved. Meanwhile, in the portrait enhancement experiments, the images obtained with this image automatic processing algorithm outperform the traditional ID card image processing methods regarding information entropy, mutual information, standard deviation and peak signal-to-noise ratio (PSNR).

Design of real-time digital image processing system based on high performance computing

Design of real-time digital image processing system based on high performance computing

The role of deep learning in the diagnosis of ocular diseases

Deep Learning (DL) revolutionized a wide variety of research fields and applications of Artificial Intelligence (AI) in the last years. Computer vision is among those fields that witnessed a stronger impact, especially in some tasks like image equalization, classification and segmentation, that have several applications in medical imaging. Such applications often focus on microscopy images, but they can be successfully extended to other fields, like the detection of diseases involving the ocular surface and the cornea.One of the reasons of the success of deep learning applied to image processing relies in the end‐to‐end data‐driven approach. This means that the whole image processing and classification/segmentation pipeline can be adapted to the data being processed. This is particularly powerful when dealing with medical images, whose processing is often based on the detection of low‐ and mid‐level patterns that might be difficult to define in a formal manner. This means that deep learning has the chance to select and consider some image elements that would be nearly impossible to define using standard computer vision techniques. However, this becomes possible if large amounts of data are available for training the network, which became reality in the last years thanks to the wide digitalization of medical systems, including ophthalmology equipment.Based on a substantial amount of literature that has rapidly grown in the last years, this talk will focus on the new perspectives of eye disease diagnosis that were opened by the advent of deep learning. At the same time, the limitations and risks that must be considered in the development of DL‐based medical systems, like overfitting and lack of generalization, will be highlighted and discussed. Keeping track of such limitations is crucial in order not to consider DL as a sort of magic box, but rather, as powerful image analysis and processing tool.The talk will also provide a qualitative and quantitative evaluation of the diagnosis systems currently available that exploit DL and AI systems. The current and future impact of automatic image processing systems dedicated to ophthalmology will also be discussed. When automatic medical image analysis will be widely available, the patterns of medical diagnosis will need to change, taking advantage of the possibility to perform larger screenings that will be automatically processed.

Object Defect Detection Using Histogram Analysis and Spearman’s Correlation Coefficient

In modern manufacturing industry, Automatic defect detection is becoming an attractive alternative to Human Inspection. Automatic defect detection on object surfaces is a compelling process. For accurate automated inspection and classification, computer vision image processing system has been widely used in manufacturing industries. In this article, we proposed histogram based automatic defect detection that process three objects at a time. In the first step we collect image from the camera, perform preprocessing, segmentation then we used histogram and Spearman’s correlation coefficient to find the defect or non-defect objects. The experimental analysis was evaluated on 300 images including defective and non-defective objects.

Age Identification System with Panoramic Image Processing Digital Molar Dental Radiograph with Adaptive Region Growing Approach Method

Forensics plays a crucial role in legal enforcement, particularly in cases where objects or human victims undergoing forensic identification have suffered significant damage. Teeth offer a robust solution in the identification process due to their resilience to various circumstances. Forensic odontology focuses on dental identification for judicial purposes. One crucial parameter in forensic odontology is age estimation. Generally, an individual's dental development is directly related to age, which can be observed through the dental pulp. The dental pulp tends to narrow or widen with increasing age. In this study, an image processing system using the Adaptive Region Growing Approach (ARGA) method was developed for dental pulp molar radiograph images. Subsequently, the dental pulp images were classified using the Support Vector Machine (SVM) method. The research process encompassed data collection, image processing, feature extraction, and molar dental pulp size classification. The results demonstrated an accuracy of over 80% in the system, using specific parameters such as an adjustment threshold of OTSU 1.15, a clip limit histogram Equalization of 0.1, a polynomial kernel type, and one against one coding type for data classification into four classes. This study concludes that the Adaptive Region Growing Approach (ARGA) method and Support Vector Machine (SVM) classification can be effectively implemented in age estimation using panoramic radiograph images. This has the potential for significant applications in forensic odontology, supporting victim identification in legal enforcement.

Detection of Broken Almonds with Image Processing Techniques

Almond is a product with high nutritional and economic value; some quality control procedures are applied before the almonds are packaged. Applications such as product classification, faulty product detection, and non-product substance detection are widely used in quality control processes. With the development of image processing and camera control systems, these operations can be performed with computer vision systems at low costs, high speed and accuracy. In this study, to detect broken almonds; image processing techniques such as thresholding, HSV transformation and blob detection were actively used. Binary image followed by blob detection algorithm was used to detect almonds. HSV transformation was performed on the detected almonds to detect the broken area. It is aimed to detect broken areas by applying appropriate threshold values to H and S bands. When the proposed method was tested, an algorithm was developed that worked 100% as long as the broken areas were visible.

Multispectral Image Processing System for Precision Detection of Reheated Coconut Oil

In the pursuit of enhancing food safety protocols, this article explores a cutting-edge approach to quality control in the coconut oil industry. We present a multispectral image processing system designed specifically for the detection of reheated coconut oil, leveraging advancements in machine learning. Machine learning algorithms, fused with image classification techniques, provide a robust framework for accurately identifying reheated coconut oil. It is proposed to develop a spectral clustering-based classifier to determine the effect of reheating and reuse of coconut oil. Post-processing methods refine classification results, while validation ensures the system's adaptability to diverse datasets.

Machine LearningDeep Learning in Rheumatological Screening A Systematic Review

Machine learning and deep learning techniques have been used in many fields, especially automatic image processing techniques, in recent years. In light of these developments, it has become inevitable to develop applications in the medical field. This study focuses on the past few years of research using machine learning and deep learning methods in the context of image processing in the field of rheumatology. This review provides researchers with the latest information on the use of deep learning and machine learning and inspires them to generate new ideas in their research by analyzing image processing systems performed by these artificial intelligence methods. In the proposed systematic review, 28 articles covering the application of deep learning and machine learning methods in the domain of rheumatology with the aim of digital image processing in the last 18 years were evaluated. Experiments emphasize that machine learning and deep learning methods provide significant segmentation accuracy and better case classification accuracy for various rheumatologic diseases like rheumatoid arthritis, osteoarthritis, and ankylosing spondylitis. Lastly submitted review presents possible different research ideas for related researchers to concentrate on for their future studies.

Automatic Mass Waste Sorting System Using Inductive Proximity Sensor, Water Level Sensor and Image Processing using MobileNet Algorithm

The global municipal solid waste is predicted to increase by threefold in 2050. Indonesia’s most wastes are unsorted and only end up in landfill and the waste management is less than ideal. An automatic mass waste sorting system is proposed to answer such problems. The automatic mass waste sorting system is designed to be able to identify and separate metal, plastic and organic waste using electrical sensors and image processing. The electrical sensors was able to identify waste types with 65% accuracy and the image processing system was able to identify waste types with 86.67% accuracy. The result doesn’t offer much advantage compared to other research on waste management system, however it is hoped that this research may inspire other researches on mass waste sorting systems.

Retracted: Distributed Network Image Processing System and Transmission Control Algorithm

Retracted: Distributed Network Image Processing System and Transmission Control Algorithm

Advancements in condition monitoring and fault diagnosis of rotating machinery: A comprehensive review of image-based intelligent techniques for induction motors

Recently, condition monitoring (CM) and fault detection and diagnosis (FDD) techniques for rotating machinery (RM) have witnessed substantial advancements in recent decades, driven by the increasing demand for enhanced reliability, efficiency, and safety in industrial operations. CM of valuable and high-cost machinery is crucial for performance tracking, reducing maintenance costs, enhancing efficiency and reliability, and minimizing mechanical failures. While various FDD methods for RM have been developed, these predominantly focus on signal processing diagnostics techniques encompassing time, frequency, and time-frequency domains, intelligent diagnostics, image processing, data fusion, data mining, and expert systems. However, there is a noticeable knowledge gap regarding the specific review of image-based CM and FDD. The objective of this research is to address the aforementioned gap in the literature by conducting a comprehensive review of image-based intelligent techniques for CM and fault FDD specifically applied to induction motors (IMs). The focus of the study is to explore the utilization of image-based methods in the context of IMs, providing a thorough examination of the existing literature, methodologies, and applications. Furthermore, the integration of image-based techniques in CM and FDD holds promise for enhanced accuracy, as visual information can provide valuable insights into the physical condition and structural integrity of the IMs, thereby facilitating early FDD and proactive maintenance strategies. The review encompasses the three main faults associated with IMs, namely bearing faults, stator faults, and rotor faults. Furthermore, a thorough assessment is conducted to analyze the benefits and drawbacks associated with each approach, thereby enabling an evaluation of the efficacy of image-based intelligent techniques in the context of CM and FDD. Finally, the paper concludes by highlighting key issues and suggesting potential avenues for future research.

Створення активних оптичних метаповерхонь на плівках халькогенідних напівпровідників зі зміною фазового стану

The development of meta-optics is due to human aspirations for the maximum miniaturization of optical elements, the design and control of light fluxes, as well as the improvement of visualization and image processing. Metasurfaces, i.e. arrays with subwavelength distances (smaller than the wavelength of light), and optically thin elements trigger new physical mechanism and phenomena that are very different from those observed in three-dimensional bulk materials. Thus, meta-devices perform complete control and management of the characteristics of the light flux (phase, amplitude, polarization) with the help of one flat layer. Compared to traditional bulky lenses, metasurface lenses have advantages such as flatness, light weight, and compatibility with semiconductor manufacturing technology. The use of active (reconfigurable) metasurfaces, the characteristics of which can be dynamically rearranged after manufacturing, makes it possible to significantly expand the capabilities of meta-optics. The paper presents the results of the analysis of the properties and technologies of creating optically active metasurfaces for optical image processing and transformation systems. Generalized methods of forming metasurfaces are described: self-organization, selective chemical etching, holographic and lithographic. To implement the work of active (reconfigured) metasurfaces based on materials with a change in phase state (amorphous/crystalline), heating technologies with electric current pulses of various amplitudes and durations and the action of direct optical radiation are used. The analysis of materials for the formation of optically active metasurfaces and devices based on them that simulate the front of a light wave and work on reflection and transmission is presented. Special attention is paid to the use of photosensitive chalcogenide semiconductors as metamaterials with a phase change. Examples of materials such as Ge2Sb2Te5 (GST) and AgxInSb2Te (AIST), which have been used for decades in optical data storage and electronic memory devices, are given. A series of novel compositions of optical phase change materials such as Ge2Sb2Se4Te (GSST), Sb2S3, Sb2Se3, Ge2Sb2Te3S2 and In3SbTe2 for optical and photonic applications are also proposed. Direct laser recording on photosensitive films of chalcogenide semiconductors with the use of technological equipment for laser recording of master disks is proposed as a promising method of forming arrays with submicron distances and realizing the work of active metasurfaces.

Consideration of image processing system for high visibility of display using aerial imaging optics

Consideration of image processing system for high visibility of display using aerial imaging optics

Deblur Image Processing System for Full Color Aerial Imaging Optics

Deblur Image Processing System for Full Color Aerial Imaging Optics

Real Time FPGA Implementation of an Efficient High Speed Harris Corner Detection Algorithm Based on High-Level Synthesis

Computer vision systems use corner detection to identify features in an image. In applications such as motion detection, tracking, picture registration, and object recognition, corner detection is often one of the initial steps. In this paper, a real-time image processing system based on Harris corner detection was designed and implemented using Zynq architecture and model-based design tools. The system was based on a development board containing the Zynq-7000 chip, which consists of a combination of FPGA and microprocessor, and the image taken with a high-resolution camera was processed in real-time by applying color conversion and Harris corner detection. The filter hardware designs used in the system were made using the HDL Coder tool in Matlab/Simulink without writing HDL code. The hardware that receives images from the camera was designed on a model-based basis with the Xilinx Vivado 2020. The HDL code that was implemented on the Xilinx ZedBoard using Vivado software was then validated to ensure real-time operation with the incoming video stream. The results achieved exhibited superiority compared to prior implementations in terms of area efficiency (reduced number of gates on the target FPGA) and speed performance on an identical target card. Using the rapid prototyping approach, two alternative hardware accelerator designs were created using various high-level synthesis tools. This design used less than 50% of the host FPGA's logic resources and was at least 30% faster than current implementations.

Restoration of Obscured Images

Abstract: For the aim of exploring the deep undersea world map, a picture of high quality without interfering objects is preferred. However, within the water, the image quality tends to be hampered by light scattering, water density, and light attenuation. effects. Besides, the dynamic interference may affect the important underwater map. during this paper, we proposed a multi-step and all-around underwater image processing system, especially for the underwater images taken in succession to enhance the image quality, remove the dynamic interference, and reconstruct the image. The first step involves utilizing the dark channel approach together with the improved gray world algorithm for brightness adaptation and color correction. Initially, it identifies and removes a dynamic interference regarding image enhancement. Secondly, we applied an upgraded total variation model to patch the blank at the value of resolution. Finally, the super-resolution of the small print is realized by applying an improved BP network. After simulation and experiments, our system proved to realize ideal results of image enhancement and reconstruction.

Polarization Reversal of Group IV-VI Semiconductors with Pucker-Like Structure: Mechanism Dissecting and Function Demonstration.

Polarization imaging presents advantages in capturing spatial, spectral, and polarization information across various spectral bands. It can improve the perceptual ability of image sensors and has garnered more applications. Despite its potential, challenges persist in identifying band information and implementing image enhancement using polarization imaging. These challenges often necessitate integrating spectrometers or other components, resulting in increased complexities within image processing systems and hindering device miniaturization trends. Here, the characteristics of anisotropic absorption reversal are systematically elucidated in pucker-like group IV-VI semiconductors MX (M=Ge, Sn; X=S, Se) through theoretical predictions and experimental validations. Additionally, the fundamental mechanisms behind anisotropy reversal in different bands are also explored. The photodetector is constructed by utilizing MX as a light-absorbing layer, harnessing polarization-sensitive photoresponse for virtual imaging. The results indicate that the utilization of polarization reversal photodetectors holds advantages in achieving further multifunctional integration within the device structure while simplifying its configuration, including band information identification and image enhancement. This study provides a comprehensive analysis of polarization reversal mechanisms and presents a promising and reliable approach for achieving dual-band image band identification and image enhancement without additional auxiliary components.

High-Speed Wavelet Image Processing Using the Winograd Method with Downsampling

Wavelets are actively used to solve a wide range of image processing problems in various fields of science and technology. Modern image processing systems cannot keep up with the rapid growth in digital visual information. Various approaches are used to reduce the computational complexity and increase computational speeds. The Winograd method (WM) is one of the most promising. However, this method is used to obtain sequential values. Its use for wavelet image processing requires expanding the calculation methodology to cases of downsampling. This paper proposes a new approach to reduce the computational complexity of wavelet image processing based on the WM with decimation. Calculations have been carried out and formulas have been derived that implement digital filtering using the WM with downsampling. The derived formulas can be used for 1D filtering with an arbitrary downsampling stride. Hardware modeling of wavelet image filtering on an FPGA showed that the WM reduces the computational time by up to 66%, with increases in the hardware costs and power consumption of 95% and 344%, respectively, compared to the direct method. A promising direction for further research is the implementation of the developed approach on ASIC and the use of modular computing for more efficient parallelization of calculations and an even greater increase in the device speed.

Design and implementation of 4-bit absolute value detector based on verilog HDL

Absolute value detectors are widely utilized in many disciplines, such as image processing, speech recognition, and control systems, due to the advancement of digital signal processing and computer vision technologies. This paper presents a 4-bit absolute value detector based on the Verilog HDL programming language. Absolute value detectors are extensively used in signal processing, computer vision, and other fields to determine if the absolute value of the input signal meets specific conditions. This paper describes in detail the design process, including module analysis, the drawing of state transfer diagrams, the writing of Verilog HDL code, and simulation verification with a focus on practical applications. The results demonstrate that the absolute value detector is accurate and reliable in determining whether the absolute value of the input signal is greater than or equal to the threshold value.