Image Computer Vision Research Articles

Artificial intelligence in interdisciplinary life science and drug discovery research.

Artificial intelligence in interdisciplinary life science and drug discovery research.

An Artificial Intelligence Computer-vision Algorithm to Triage Otoscopic Images From Australian Aboriginal and Torres Strait Islander Children.

To develop an artificial intelligence image classification algorithm to triage otoscopic images from rural and remote Australian Aboriginal and Torres Strait Islander children. Retrospective observational study. Tertiary referral center. Rural and remote Aboriginal and Torres Strait Islander children who underwent tele-otology ear health screening in the Northern Territory, Australia between 2010 and 2018. Otoscopic images were labeled by otolaryngologists to classify the ground truth. Deep and transfer learning methods were used to develop an image classification algorithm. Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, area under the curve (AUC) of the resultant algorithm compared with the ground truth. Six thousand five hundred twenty seven images were used (5927 images for training and 600 for testing). The algorithm achieved an accuracy of 99.3% for acute otitis media, 96.3% for chronic otitis media, 77.8% for otitis media with effusion (OME), and 98.2% to classify wax/obstructed canal. To differentiate between multiple diagnoses, the algorithm achieved 74.4 to 92.8% accuracy and an AUC of 0.963 to 0.997. The most common incorrect classification pattern was OME misclassified as normal tympanic membranes. The paucity of access to tertiary otolaryngology care for rural and remote Aboriginal and Torres Strait Islander communities may contribute to an under-identification of ear disease. Computer vision image classification algorithms can accurately classify ear disease from otoscopic images of Indigenous Australian children. In the future, a validated algorithm may integrate with existing telemedicine initiatives to support effective triage and facilitate early treatment and referral.

Combination of Resnet and Spatial Pyramid Pooling for Musical Instrument Identification

Abstract Identifying similar objects is one of the most challenging tasks in computer vision image recognition. The following musical instruments will be recognized in this study: French horn, harp, recorder, bassoon, cello, clarinet, erhu, guitar saxophone, trumpet, and violin. Numerous musical instruments are identical in size, form, and sound. Further, our works combine Resnet 50 with Spatial Pyramid Pooling (SPP) to identify musical instruments that are similar to one another. Next, the Resnet 50 and Resnet 50 SPP model evaluation performance includes the Floating-Point Operations (FLOPS), detection time, mAP, and IoU. Our work can increase the detection performance of musical instruments similar to one another. The method we propose, Resnet 50 SPP, shows the highest average accuracy of 84.64% compared to the results of previous studies.

Online Classroom Attendance Marking System Using Face Recognition, Python, Computer Vision, and Digital Image Processing

Abstract: The face is the identity of someone. The tactic to appear out this physical feature has seen an exquisite change since the advent of the image processing method. The attendance is taken in every school, college and library. The regular method for attendance is teachers calling student name & marking attendance. Nowadays, AI has been highly explored for computer vision applications[1]. So, we use the concept of neural network in Face – recognition for automatic attendance marking systems. In this project, we perform the face recognition and face detection algorithms, to produce the computer systems the ability to find and recognize human faces fast and precisely in live videos so that the systems can be used in marking attendance. Keywords: Face detection, Python, Computer Vision, Attendance marking system, Image processing

DSSM: A Deep Neural Network with Spectrum Separable Module for Multi-Spectral Remote Sensing Image Segmentation

Over the past few years, deep learning algorithms have held immense promise for better multi-spectral (MS) optical remote sensing image (RSI) analysis. Most of the proposed models, based on convolutional neural network (CNN) and fully convolutional network (FCN), have been applied successfully on computer vision images (CVIs). However, there is still a lack of exploration of spectra correlation in MS RSIs. In this study, a deep neural network with a spectrum separable module (DSSM) is proposed for semantic segmentation, which enables the utilization of MS characteristics of RSIs. The experimental results obtained on Zurich and Potsdam datasets prove that the spectrum-separable module (SSM) extracts more informative spectral features, and the proposed approach improves the segmentation accuracy without increasing GPU consumption.

Pooling in convolutional neural networks for medical image analysis: a survey and an empirical study.

Convolutional neural networks (CNN) are widely used in computer vision and medical image analysis as the state-of-the-art technique. In CNN, pooling layers are included mainly for downsampling the feature maps by aggregating features from local regions. Pooling can help CNN to learn invariant features and reduce computational complexity. Although the max and the average pooling are the widely used ones, various other pooling techniques are also proposed for different purposes, which include techniques to reduce overfitting, to capture higher-order information such as correlation between features, to capture spatial or structural information, etc. As not all of these pooling techniques are well-explored for medical image analysis, this paper provides a comprehensive review of various pooling techniques proposed in the literature of computer vision and medical image analysis. In addition, an extensive set of experiments are conducted to compare a selected set of pooling techniques on two different medical image classification problems, namely HEp-2 cells and diabetic retinopathy image classification. Experiments suggest that the most appropriate pooling mechanism for a particular classification task is related to the scale of the class-specific features with respect to the image size. As this is the first work focusing on pooling techniques for the application of medical image analysis, we believe that this review and the comparative study will provide a guideline to the choice of pooling mechanisms for various medical image analysis tasks. In addition, by carefully choosing the pooling operations with the standard ResNet architecture, we show new state-of-the-art results on both HEp-2 cells and diabetic retinopathy image datasets.

Multiclass Segmentation of Pulmonary Diseases using Convolutional Neural Network

Pulmonary disease has affected tens of millions of people in the world. This disease has also become the cause of death of millions of its sufferers every year. In addition, lung disease has also become the cause of other respiratory complications, which also causes the death of the sufferer. The diagnosis of pulmonary diseases through medical imaging is a significant challenge in computer vision and medical image processing. The difficulty is due to the wide variety in infected areas' shape, dimension, and location. Another challenge is to differentiate one lung disease from the other. Discriminating pulmonary diseases is a notable concern in the diagnosis of pulmonary disease. We have adopted the deep learning convolutional neural network in this study to address these challenges. Seven models were constructed using the Mask Region-based Convolutional Neural Network (Mask-RCNN) architecture to detect and segment infected areas within the lung region from CT scan imagery. The evaluation results show that the best model obtained scores of 91.98%, 85.25%, and 93.75% for DSC, MIoU, and mAP, respectively. The segmentation results are then visualized.

Guest Editorial: Non-Euclidean Machine Learning

Over the past decade, deep learning has had a revolutionary impact on a broad range of fields such as computer vision and image processing, computational photography, medical imaging and speech and language analysis and synthesis etc. Deep learning technologies are estimated to have added billions in business value, created new markets, and transformed entire industrial segments. Most of today’s successful deep learning methods such as Convolutional Neural Networks (CNNs) rely on classical signal processing models that limit their applicability to data with underlying Euclidean grid-like structure, e.g., images or acoustic signals. Yet, many applications deal with non-Euclidean (graph- or manifold-structured) data. For example, in social network analysis the users and their attributes are generally modeled as signals on the vertices of graphs. In biology protein-to-protein interactions are modeled as graphs. In computer vision & graphics 3D objects are modeled as meshes or point clouds. Furthermore, a graph representation is a very natural way to describe interactions between objects or signals. The classical deep learning paradigm on Euclidean domains falls short in providing appropriate tools for such kind of data. Until recently, the lack of deep learning models capable of correctly dealing with non-Euclidean data has been a major obstacle in these fields. This special section addresses the need to bring together leading efforts in non-Euclidean deep learning across all communities. From the papers that the special received twelve were selected for publication. The selected papers can naturally fall in three distinct categories: (a) methodologies that advance machine learning on data that are represented as graphs, (b) methodologies that advance machine learning on manifold-valued data, and (c) applications of machine learning methodologies on non-Euclidean spaces in computer vision and medical imaging. We briefly review the accepted papers in each of the groups.

Hybrid Facial Chaotic-based Graphical Encryption Technique for Cloud Environment

Pictographic representations are everywhere in this digital world. IoT, Cloud, Fog, and 5G systems are becoming data transfer boosters for each user. In a real-world situation, secure data transmission is critical through open networks. Many conventional cryptosystems are inadequate for graphical data privacy in terms of computational overhead, latency, and more sensitive to the unknown attacks. In this paper, the secured and low-complex chaotic-based facial image cryptosystem has been developed for computer vision image data. The proposed crypto system utilizes the facial features, Lorentz chaotic maps for private keys production during the encoding process and the same is decrypted using the diffusion process. Facial depictions are merged with chaotic maps that are segmented and decrypted with mutual keys. The performance of the proposed hybrid cryptosystem is validated using the standard facial datasets and NCPR, UACI metrics are measured. Entropy and adjacent pixels correlation metrics also evaluated through proposed cryptosystems.

Study on the Prescription of Acupuncture in the Treatment of Cervical Spondylotic Radiculopathy Based on Computer Vision Image Analysis.

Cervical spondylosis (CS) is a common clinical orthopedic disease. Among cervical spondyloses, cervical spondylotic radiculopathy (CSR) is the most common. Its clinical manifestations are localized neck pain and radial numbness of the shoulder, upper arm, forearm, and even fingers. As far as the status quo is concerned, with the change of lifestyle and working style, the popularity of computer and other entertainment devices, people's neck flexion time has increased significantly compared with the past, the incidence rate of CSR has also increased year by year, and the group of onset has become younger and younger. According to the symptoms, CSR in Chinese medicine belongs to the category of “arthralgia syndrome” and “bone arthralgia.” Western medicine has many side effects in the treatment of CSR, while surgical treatment is painful and expensive. Most patients are not willing to accept it. Traditional Chinese medicine acupuncture can relieve the pain, numbness, and other discomforts of CSR, and the acupuncture treatment has less trauma and is a simple operation. At present, there are few acupoint prescriptions for acupuncture in the treatment of CSR. Therefore, the analysis of acupuncture point selection based on computer vision image has important practical significance for the scientific and progressive exploration of CSR acupuncture treatment. In this paper, the etiology, pathology, and clinical manifestations of radical treatment of CS are deeply studied by using literature data and mathematical statistics. The prescription research experiment of acupuncture in the treatment of CSR based on computer was established, and the treatment method was studied by observing VAS, NPQ, and other indexes. The total effective rate was 95.13% in the experimental group and 85.72% in the control group. It is hoped that the research direction of this paper can provide reference for the diversified development of acupuncture and moxibustion and for the treatment ideas and methods of cervical spondylotic radiculopathy.

An intelligent detection method of local feature points in computer vision image

An intelligent detection method of local feature points in computer vision image

РАСПОЗНАВАНИЕ ПОКАЗАНИЙ АНАЛОГОВЫХ ПРИБОРОВ НА ПРИМЕРЕ АВИАЦИОННЫХ ПРИБОРОВ ВЫСОТНО-СКОРОСТНОЙ ГРУППЫ

The article considers the issue of analog instrument reading using the example of high-altitude and high-speed flight instruments. The article provides a detailed description of the software that can read analog gauge data through the example of flight instruments during their verification. The article describes the main functions of computer vision library, image processing, and general-purpose numerical algorithms with open source (OpenCV), used for instrument readings. The software is developed in the high-level universal programming language Python 3.7.7. The results of the program are presented, showing this method performance of checking high altitude flight instruments.

A Survey of Wound Image Analysis Using Deep Learning: Classification, Detection, and Segmentation

Wounds not only harm the physical and mental health of patients, but also introduce huge medical costs. Meanwhile, there is a shortage of physicians in some areas, and clinical examinations are sometimes unreliable in wound diagnosis. Reliable wound analysis is of great importance in its diagnosis, treatment, and care. Currently, deep learning has developed rapidly in the field of computer vision and medical imaging and has become the most commonly used technique in wound image analysis. This paper studies the current research on deep learning in the field of wound image analysis, including classification, detection, and segmentation. We first review the publicly available datasets from various research, and study the preprocessing methods used in wound image analysis. Second, various models used in different deep learning tasks (classification, detection, and segmentation) and their applications in different types of wounds (e.g., burns, diabetic foot ulcers, pressure ulcers) are investigated. Finally, we discuss the challenges in the field of wound image analysis using deep learning, and provide an outlook on the research and development prospects.

Multiexpert Adversarial Regularization for Robust and Data-Efficient Deep Supervised Learning

Deep neural networks (DNNs) can achieve high accuracy when there is abundant training data that has the same distribution as the test data. In practical applications, data deficiency is often a concern. For classification tasks, the lack of enough labeled images in the training set often results in overfitting. Another issue is the mismatch between the training and the test domains, which results in poor model performance. This calls for the need to have robust and data efficient deep learning models. In this work, we propose a deep learning approach called Multi-Expert Adversarial Regularization learning (MEAR) with limited computational overhead to improve the generalization and robustness of deep supervised learning models. The MEAR framework appends multiple classifier heads (experts) to the feature extractor of the legacy model. MEAR aims to learn the feature extractor in an adversarial fashion by leveraging complementary information from the individual experts as well as the ensemble of the experts to be more robust for an unseen test domain. We train state-of-the-art networks with MEAR for two important computer vision tasks, image classification and semantic segmentation. We compare MEAR to a variety of baselines on multiple benchmarks. We show that MEAR is competitive with other methods and more successful at learning robust features.

Simultaneous Segmentation and Motion Estimation of Left Ventricular Myocardium in 3D Echocardiography Using Multi-task Learning.

Motion estimation and segmentation are both critical steps in identifying and assessing myocardial dysfunction, but are traditionally treated as unique tasks and solved as separate steps. However, many motion estimation techniques rely on accurate segmentations. It has been demonstrated in the computer vision and medical image analysis literature that both these tasks may be mutually beneficial when solved simultaneously. In this work, we propose a multi-task learning network that can concurrently predict volumetric segmentations of the left ventricle and estimate motion between 3D echocardiographic image pairs. The model exploits complementary latent features between the two tasks using a shared feature encoder with task-specific decoding branches. Anatomically inspired constraints are incorporated to enforce realistic motion patterns. We evaluate our proposed model on an in vivo 3D echocardiographic canine dataset. Results suggest that coupling these two tasks in a learning framework performs favorably when compared against single task learning and other alternative methods.

Trajectory Grouping With Curvature Regularization for Tubular Structure Tracking.

Tubular structure tracking is a crucial task in the fields of computer vision and medical image analysis. The minimal paths-based approaches have exhibited their strong ability in tracing tubular structures, by which a tubular structure can be naturally modeled as a minimal geodesic path computed with a suitable geodesic metric. However, existing minimal paths-based tracing approaches still suffer from difficulties such as the shortcuts and short branches combination problems, especially when dealing with the images involving complicated tubular tree structures or background. In this paper, we introduce a new minimal paths-based model for minimally interactive tubular structure centerline extraction in conjunction with a perceptual grouping scheme. Basically, we take into account the prescribed tubular trajectories and curvature-penalized geodesic paths to seek suitable shortest paths. The proposed approach can benefit from the local smoothness prior on tubular structures and the global optimality of the used graph-based path searching scheme. Experimental results on both synthetic and real images prove that the proposed model indeed obtains outperformance comparing with the state-of-the-art minimal paths-based tubular structure tracing algorithms.

Fog Model-Based Hyperspectral Image Defogging

Fog in hyperspectral images severely limits the visibility of imaging scene and reduces the image contrast, which has a negative effect on the following image interpretation. Defogging methods aim at restoring a high-quality image from the degraded image. Currently, most dehazing methods mainly depend on the atmospheric scattering model in computer vision and multispectral image communities. However, when these approaches are directly used to remove the fog from HSIs, they cannot produce satisfactory defogging performance. To alleviate this issue, we develop a novel fog model to achieve fog removal from hyperspectral images. First, a fog density map is calculated by differentiating the averaged bands falling into visible and infrared spectral ranges. Then, haze abundance in different spectral bands is estimated based on the pixel reflectance between two selected pixels with different haze levels. Finally, the high-quality hyperspectral image is restored by solving the defogging model. Experiments performed on a new benchmark created by ourselves demonstrate that the proposed method obtains favorable dehazing performance in contrast to other approaches in computer vision and remote sensing fields.

A Review on Online Classroom Attendance Marking System Using Face Recognition, Python, Computer Vision, and Digital Image Processing

Abstract: The face is that the identity of someone. The tactic to appear out this physical feature has seen an exquisite change since the advent of the image processing method. Attendance is monitored in every school, college and library. The regular method for attendance is for teachers to call student name & mark attendance. Nowadays, AI has been explored for computer vision-related applications. So, we use the neural network concept in Face recognition for automatically attendance marking systems. This project will perform the face recognition and face detection algorithms, to generate the computer systems strength of acquiring and recognizing human faces fast, accurately, and precisely in live streams so that the systems can be used in the marking attendance

Prototyping an Autonomous Face Controlled System using Raspberry Pi on Wheelchairs

Quadriplegics are people who cannot use their extremities. Existing aiding devices are costly, complex, not user friendly and they are guardian dependent for movement. In this paper, a Raspberry Pi enabled wheelchair movement control by head movement detection is presented. A head movement detection technique based on Open - Computer Vision image processing is used which detects the user's facial movement in real time using the camera. Using this, the wheelchair motors are controlled and are driven in the indicated direction. Also, numerous sensors such as temperature sensor, pulse rate sensor, accelerometer sensor and fire sensor are added to monitor patient health, safety and well-being.

Shape registration with learned deformations for 3D shape reconstruction from sparse and incomplete point clouds.

Shape reconstruction from sparse point clouds/images is a challenging and relevant task required for a variety of applications in computer vision and medical image analysis (e.g. surgical navigation, cardiac motion analysis, augmented/virtual reality systems). A subset of such methods, viz. 3D shape reconstruction from 2D contours, is especially relevant for computer-aided diagnosis and intervention applications involving meshes derived from multiple 2D image slices, views or projections. We propose a deep learning architecture, coined Mesh Reconstruction Network (MR-Net), which tackles this problem. MR-Net enables accurate 3D mesh reconstruction in real-time despite missing data and with sparse annotations. Using 3D cardiac shape reconstruction from 2D contours defined on short-axis cardiac magnetic resonance image slices as an exemplar, we demonstrate that our approach consistently outperforms state-of-the-art techniques for shape reconstruction from unstructured point clouds. Our approach can reconstruct 3D cardiac meshes to within 2.5-mm point-to-point error, concerning the ground-truth data (the original image spatial resolution is ∼1.8×1.8×10mm3). We further evaluate the robustness of the proposed approach to incomplete data, and contours estimated using an automatic segmentation algorithm. MR-Net is generic and could reconstruct shapes of other organs, making it compelling as a tool for various applications in medical image analysis.