Top Research Papers on Image Processing

Nonlinear filters morphological segmentation for textures and particles multispectral image segmentation in magnetic resonance imaging thinning and skeletonizing syntactic image pattern recognition heuristic parallel approach for 3D articulated line-drawing object pattern representation and recognition.

An Invertible Image Signal Processing (InvISP) pipeline is designed, which not only enables rendering visually appealing sRGB images but also allows recovering nearly perfect RAW data.

A reconfigurable metasurface that can be dynamically tuned to provide a range of processing modalities including bright-field imaging, low-pass and high-pass filtering, and second-order differentiation is demonstrated.

The first model watermarking framework for protecting image processing models, which can resist surrogate models learned with different network structures and objective functions is proposed and is easy to be extended to protect data and traditional image processing algorithms.

Dr Donald Bailey starts with introductory material considering the problem of embedded image processing, and how some of the issues may be solved using parallel hardware solutions. Field programmable gate arrays (FPGAs) are introduced as a technology that provides flexible, fine-grained hardware that can readily exploit parallelism within many image processing algorithms. A brief review of FPGA programming languages provides the link between a software mindset normally associated with image processing algorithms, and the hardware mindset required for efficient utilization of a parallel hardwar...

Wavelet analysis is among the newest additions to the arsenals of mathematicians, scientists, and engineers, and offers common solutions to diverse problems. However, students and professionals in some areas of engineering and science, intimidated by the mathematical background necessary to explore this subject, have been unable to use this powerful tool.The first book on the topic for readers with minimal mathematical backgrounds, Wavelet Analysis with Applications to Image Processing provides a thorough introduction to wavelets with applications in image processing. Unlike most other works o...

This survey introduces a review of existing relatively mature and representative underwater image processing models, which are classified into seven categories including enhancement, fog removal, noise reduction, segmentation, salient object detection, colour constancy and restoration.

To maximally excavate the capability of transformer, the IPT model is presented to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs and the contrastive learning is introduced for well adapting to different image processing tasks.

As the computing power of modern hardware is increasing strongly, pre-trained deep learning models (e.g., BERT, GPT-3) learned on large-scale datasets have shown their effectiveness over conventional methods. The big progress is mainly contributed to the representation ability of transformer and its variant architectures. In this paper, we study the low-level computer vision task (e.g., denoising, super-resolution and deraining) and develop a new pre-trained model, namely, image processing transformer (IPT). To maximally excavate the capability of transformer, we present to utilize the well-kn...

MCMICRO is a modular and open-source computational pipeline for transforming highly multiplexed whole-slide images of tissues into single-cell data that can be used with CODEX, mxIF, CyCIF, mIHC and H&E staining data.

The proposed MAXIM model achieves state-of-the-art performance on more than ten benchmarks across a range of image processing tasks, including denoising, deblurring, de raining, dehazing, and enhancement while requiring fewer or comparable numbers of parameters and FLOPs than competitive models.

This work uses eleven full-reference IQA models to train deep neural networks for four low-level vision tasks: denoising, deblurring, super-resolution, and compression, and uses subjective testing on the optimized images to rank the competing models in terms of their perceptual performance, elucidate their relative advantages and disadvantages.

Fruits are vulnerable to mechanical damages and physiological disorders caused by the static and dynamic forces acting on them during transportation and abiotic stresses throughout their growth and development, respectively. Identifying these defects is central to quality monitoring in the fruit processing industry. Conventionally, industries employ manual separation to segregate damaged fruits in the processing line. However, manual sorting is laborious, time-consuming, skilled labor-intensive, and destructive. Besides, it is incapable of inspecting every fruit on a fast-moving conveyor belt....

Floods are among the most destructive natural hazards that affect millions of people across the world leading to severe loss of life and damage to property, critical infrastructure, and the environment. Deep learning algorithms are exceptionally valuable tools for collecting and analyzing the catastrophic readiness and countless actionable flood data. Convolutional neural networks (CNNs) are one form of deep learning algorithms widely used in computer vision which can be used to study flood images and assign learnable weights and biases to various objects in the image. Here, we leveraged and d...

This work proposes an Efficient Attention Pyramid Transformer (EAPT), which first proposes the Deformable Attention, which learns an offset for each position in patches, and designs the Encode-Decode Communication module (En-DeC module), which can obtain communication information among all patches to get more complete global attention information.

An integrated workflow for multiplexed tissue image processing and analysis, including interactive inspection of raw data, cell segmentation, feature extraction, single-cell analysis and spatial analysis is presented.

Proposed method describes different strategies utilized for rice leaf disease classification purpose and various features are separated utilizing “Local Binary Patterns (LBP)” and “Histogram of Oriented Gradients (HOG”.

A novel approach is proposed, called mGANprior, to incorporate the well-trained GANs as effective prior to a variety of image processing tasks, by employing multiple latent codes to generate multiple feature maps at some intermediate layer of the generator and composing them with adaptive channel importance to recover the input image.

A comprehensive understanding of the strengths and limitations across methodologies is offered, paving the way for informed decisions in practical applications.

This Roadmap article on three-dimensional integral imaging provides an overview of some of the research activities in the field of integral imaging including sensing of 3D scenes, processing of captured information, and 3D display and visualization of information.

This work proposes a Gaussian Process-based semi-supervised learning framework which enables the network in learning to derain using synthetic dataset while generalizing better using unlabeled real-world images.

Common infections along with the research landscape at different stages of such detection systems are discussed and the modern feature extraction techniques are analyzed for identifying those that appear to work well covering several crop categories.

A highly accurate and computationally efficient model for the swift and accurate diagnosis of lung and colon cancers as an alternative to current cancer detection methods is proposed and has not only improved the overall accuracy from 89% to 98.4% but has also proved Computationally efficient.

The implementation and use of an algorithm that quantifies and combines two visual aspects – roughness and color – in order to locate the corroded area in a given image and shows that the developed algorithm can efficiently locate corroded areas.

A Fourier-based metaprocessor to impart customized highly flexible transfer functions for analog computing upon the authors' single-layer Huygens’ metasurface is presented and differentiation and cross-correlation are performed to substantiate the ultracompact and high-throughput kernel processor.

The area of concern of this paper is using the digital image processing to develop a face recognition system which is considered to be one of the most extremely deliberated biometric technology.

The related studies are compared based image segmentation, feature extraction, feature selection and classification and the current achievements, limitations, and suggestions for future research associated with the diagnosis of rice plant diseases are outlined.

The proposed wrapper-based approach of feature selection in combination with the Random Forest classifier gives promising results as compared to other commonly used classifiers.

Optical analog computing using metasurfaces has been the subject of numerous studies, aimed at implementing highly efficient and ultrafast image processing in a compact device.

Combining rich spectral and spatial information, a hyperspectral image (HSI) can provide a more comprehensive characterization of the Earth's surface. To better exploit HSIs, a large number of algorithms have been developed during the past few decades. Due to their very high correlation between spectral channels and spatial pixels, HSIs have intrinsically sparse and low-rank structures. The sparse representation (SR) and low-rank representation (LRR)-based methods have proven to be powerful tools for HSI processing and are widely used in different HS fields. In this article, we present a surve...

Using computer decision-making rather than human decision-making is one of the top priorities of prosperous nations around the world. The reduction of traffic infractions is one area that requires this field. Identifying the type of vehicle will significantly reduce traffic infractions. The aim of using image processing in the context of driving violations is to minimize time wastage, reduce human errors and optimize the use of resources. However, there is still a certain error rate associated with capturing images of offending vehicles and reading their plates, whether done manually or automa...

Recent advances in the bio‐inspired artificial vision and neuromorphic image processing devices, aimed at providing efficient image recognition, are reviewed.

An evolutionary approach for classifying and detecting breast cancer that is based on machine learning and image processing that is advantageous for accurately identifying breast cancer disease using image analysis is discussed.

The contributions of ImageJ2 to enhancing multidimensional image processing and interoperability in the ImageJ ecosystem are discussed, reflecting a shift in the bioimage analysis community towards exploiting artificial intelligence.

This article has studied the development of microorganism counting methods using digital image analysis, which consists of digital image processing, image segmentation, image classification and so on, and found that image analysis-based microorganisms counting methods are efficient comparing with traditional plate counting methods.

Reactive oxygen species (ROS) and reactive nitrogen species (RNS) play their essential roles in regulating biological events. Their aberrant behaviors are mostly associated with pathophysiological processes. A better understanding of these processes can assuredly help us in examining the pathogenesis and progression of diseases and is beneficial for the ultimate clinical therapy. Numerous fluorescent probes have been developed in the last 5 years for detecting ROS and RNS involved in diverse pathophysiological processes, and these are summarized in this review. Optical properties of the fluore...

This article reviews both datasets and visual attention modelling approaches for 360° video/image, which either utilize the spherical characteristics or visual attention models, and overviews the compression approaches.

Future efforts need to focus on combining disaster management knowledge, image processing techniques and machine learning tools to ensure effective and holistic disaster management across all phases.

Residual neural networks have made strides and have had success in the clinical auxiliary diagnosis of serious illnesses such as lung tumors, breast cancer, skin conditions, and cardiovascular and cerebrovascular diseases.

RLN combines the traditional Richardson–Lucy iteration with a fully convolutional network structure, establishing a connection to the image formation process and thereby improving network performance, and is more generalizable, offers fewer artifacts and requires less computing time than alternative approaches.