Search

The application of artificial intelligence (AI) based on deep learning in dental diagnostic imaging is increasing. Several popular deep learning tasks have been applied to dental diagnostic images.Classification tasks are used to classify images with and without positive abnormal findings or to evaluate the progress of a lesion based on imaging findings. Region (object) detection and segmentation tasks have been used for tooth identification in panoramic radiographs. This technique is useful for automatically creating a patient's dental chart. Deep learning methods can also be used for detecting and evaluating anatomical structures of interest from images. Furthermore, generative AI based on natural language processing can automatically create written reports from the findings of diagnostic imaging.

The application of artificial intelligence (AI) based on deep learning in dental diagnostic imaging is increasing. Several popular deep learning tasks have been applied to dental diagnostic images. Classification tasks are used to classify images with and without positive abnormal findings or to evaluate the progress of a lesion based on imaging findings. Region (object) detection and segmentation tasks have been used for tooth identification in panoramic radiographs. This technique is useful for automatically creating a patient's dental chart. Deep learning methods can also be used for detecting and evaluating anatomical structures of interest from images. Furthermore, generative AI based on natural language processing can automatically create written reports from the findings of diagnostic imaging. [ABSTRACT FROM AUTHOR]

Vehicle re-identification identifies target vehicles using images obtained by numerous non-overlapping real-time surveillance cameras. The effectiveness of re-identification is further challenging because of illumination changes, pose differences of captured images, and resolution. Fine-grained appearance changes in vehicles are recognized in addition to the coarse-grained characteristics like color of the vehicle along with model, and other custom features like logo stickers, annual service signs, and hangings to overcome these challenges. To prove the efficiency of our proposed bipartite attention framework, a novel dataset called Attributes27 which has 27 labelled attributes for each class are created. Our framework contains three major sections: The first section where the overall and semantic characteristics of every individual vehicle image are extracted by a double branch convolutional neural network (CNN) layer. Secondly, to identify the region of interests (ROIs) each branch has a self-attention block linked to it. Lastly to extract the regional features from the obtained ROIs, a partition-alignment block is deployed. The results of our proposed system’s evaluation on the Attributes27 and VeRi-776 datasets has highlighted significant regional attributes of each vehicle and improved the accuracy. Attributes27 and VeRi-776 datasets exhibits 98.5% and 84.3% accuracy respectively which are comparatively higher than the existing methods with 78.6% accuracy. [ABSTRACT FROM AUTHOR]

Hybrid rice row detection at the pollination stage is critical for the automation of in-field pollination agricultural vehicles. The parental crops of hybrid rice are planted at intervals in seed production fields with narrow inter-row spacing. During the advance of the pollination vehicle, in addition to the centerline of the crop row, information on the crop region boundaries is required to guide the vehicle and prevent it from running over the crop. For complete crop row detection, a novel machine vision-based method was presented to identify each of the individual regions of the crop rows, more than the centerlines, by line-shaped mask scanning combined with the vanishing point of the crop rows. The approach consisted of grayscale transformation, vanishing point detection, crop region identification, boundary position fine-tuning and crop region segmentation. Its region detection performance outperformed the convolutional neural network-based (CNN-based) methods with an intersection over union (IoU) of 0.832, an accuracy of 90.48%, a recall of 86.36%, a precision of 98.96% and an f1-Score of 92.23%. Its centerline extraction ability was compared with Hough Transform-based and SegNet-based methods on the basis of average lateral distance (ALD) between the ground truth line and the detected line. The proposed method resulted in an ALD of 1.943 pixels in a 640*360 resolution image, which was superior to the Hough Transform-based (5.704) and the SegNet-based (3.555) methods. [ABSTRACT FROM AUTHOR]

Vehicle re-identification (Re-ID) aims to search for a vehicle of interest in a large video corpus captured by different surveillance cameras. The identification process considers both coarse-grained similarity (e.g., vehicle Model/color) and fine-grained similarity (e.g., windshield stickers/decorations) among vehicles. Coarse-grained and fine-grained similarity comparisons usually attend to very different visual regions, which implies that two different attention modules are required to handle different granularity comparisons. In this paper, we propose a dual attention granularity network (DAG-Net) for Vehicle Re-ID. The DAG-Net consists of three main components: (1) A convolutional neural network with a dual-branch structure is proposed as the backbone feature extractor for coarse-grained recognition (i.e., vehicle Model) and fine-grained recognition (i.e., vehicle ID); (2) the self-attention model is added to each branch, which enables the DAG-Net to detect different regions of interest (ROIs) at both coarse-level and fine-level with the assistance of the part-positioning block; (3) finally, we obtain refined regional features of the ROIs from the sub-networks ROIs. As a result, the proposed DAG-Net is able to selectively attend to the most discriminative regions for coarse/fine-grained recognition. We evaluate our method on two Vehicle Re-ID datasets: VeRi-776 and VehicleID. Experiments show that the proposed method can bring substantial performance improvement and achieve state-of-the-art accuracy. In addition, we focus on the different effects of regional features and global features. We conduct experiments to verify it in the PKU dataset and discuss the effectiveness. [ABSTRACT FROM AUTHOR]

Regions of anomalous spatial co-locations (ROASCs) are regions where co-locations between two different features are significantly stronger or weaker than expected. ROASC discovery can provide useful insights for studying unexpected spatial associations at regional scales. The main challenges are that the ROASCs are spatially arbitrary in geographic shape and the distributions of spatial features are unknown a priori. To avoid restrictive assumptions regarding the distribution of data, we propose a distribution-free method for discovering arbitrarily shaped ROASCs. First, we present a multidirectional optimization method to adaptively identify the candidate ROASCs, whose sizes and shapes are fully endogenized. Furthermore, the validity of the candidates is evaluated through significance tests under the null hypothesis that the expected spatial co-locations between two features occur consistently across space. To effectively model the null hypothesis, we develop a bivariate pattern reconstruction method by reconstructing the spatial auto- and cross-correlation structures observed in the data. Synthetic experiments and a case study conducted using Shanghai taxi datasets demonstrate the advantages of our method, in terms of effectiveness, over an available alternative method. [ABSTRACT FROM AUTHOR]

Many medical image processing applications rely on targeted regions of interest within a larger volumetric image. Whole-body scans represent an extreme case in which large volumes must be broken into smaller sub-volumes for regional analysis. In this work, we sought automatic solutions to divide medical X-ray computed tomography (CT) images into six main anatomical regions: head, neck, chest, abdomen, pelvis and legs. We implemented and compared three methods: (1) an analytical approach which does not require training and solely relies on utilizing critical points in image intensity profiles to derive cut-planes that divide the scan into the mentioned regions, (2) a classical convolutional neural network (CNN) approach, which classifies each transaxial 2D plane independently and then concatenates classification results, and (3) CNN followed by a context-based correction algorithm (CBCA) which improves the CNN classification using positional relationships between all CT slices. The analytical approach achieved acceptable accuracy for anatomical region segmentation without the need for explicit data labeling and was effective for batch labeling whole-body CTs, greatly reducing manual labeling efforts. CNNs achieved superior accuracy and allowed for rapid development and training, but required labeled data and were susceptible to produce discontinuous anatomical regions and therefore ambiguous anatomical boundaries. Post hoc correction of CNN results using CBCA overcame these limitations, achieving nearly perfect CT slice labeling and anatomical region segmentation. [ABSTRACT FROM AUTHOR]

With the proliferation of mobile devices and location-based services, continuous generation of massive volume of streaming spatial objects (i.e., geo-tagged data) opens up new opportunities to address real-world problems by analyzing them. In this paper, we present a novel continuous bursty region detection (surge) problem that aims to continuously detect a bursty region of a given size in a specified geographical area from a stream of spatial objects. Specifically, a bursty region shows maximum spike in the number of spatial objects in a given time window. The surge problem is useful in addressing several real-world challenges such as surge pricing problem in online transportation and disease outbreak detection. To solve the problem, we propose an exact solution and two approximate solutions, and the approximation ratio is $\frac{1-\alpha }{4}$ 1 - α 4 in terms of the burst score, where $\alpha$ α is a parameter to control the burst score. We further extend these solutions to support detection of top- $k$ k bursty regions. Extensive experiments with real-world data are conducted to demonstrate the efficiency and effectiveness of our solutions. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Intervention surgery strongly requires information on the guide‐wire position under the monitoring of X‐ray video. Hence, the related researches such as guide‐wire detecting or tracking have become widespread. However, most of the existing methods require a lot of resources for computing or large data for training since the X‐ray videos have internal physicals such as anatomical skeleton contours and organs that are quite similar to a guide‐wire. This work presents a practical method that only requires a moderate number of training data for detecting a guide‐wire tip in an X‐ray video sequence during the percutaneous coronary intervention surgery. The method applies maximally stable extremal regions (MSER) combine with modified multi‐filters (region area range filter and stroke width variation filter) for region detection and local binary patterns (LBP) for guide‐wire recognition. The motivation for applying MSER and LBP are the robust efficacy and the low requirement of resources. The approach evaluated 20 different sequences of X‐ray videos, a total of 1295 frames. 50 selected frames were used as training templates and others to experiment. The method was successfully performed to the detecting guide‐wires with p‐value < 0.01 compared with conventional MSER methods, 93.7% average detection accuracy, and 21 fps average speed. [ABSTRACT FROM AUTHOR]

Wear of the knee is an important indicator of the health status of dairy cows. However, the complex cattle environment and the presence of mud, excrement, and other interferences make examination of the lesion area difficult. We utilised a region detection method based on colour edge detection and bilateral projection to detect the knee area of cows. First, edge information of colour images was obtained by colour edge extraction. Second, most of the background was removed and the leg region was obtained using an open operation, vertical projection, and convex hull processing. Finally, threshold processing and horizontal projection were applied to determine the centre of the target region and the overall target region. To verify the validity of the proposed algorithm, a K-means algorithm and salient region detection were performed. In total, 81 test samples were randomly selected from 300 images, and the results showed that the average overlap rate (OR) was 6.5% and 17.3% higher than that of the K-means and saliency methods, respectively. The false-positive rate (FPR) was 0.8% higher than that of the K-means method and 6.2% lower than that of the saliency method, and the false-negative rate (FNR) decreased by 6.5% and 17.3%, respectively. The present method showed good robustness when background obstructions or ground reflection was present in the images. The results of the present work imply that our method can effectively extract the target region and could stimulate further analysis of cow knees containing swelling and scars. Highlights • Colour edge detection and bilateral projection are combined to examine the knee. • The leg was first divided from a colour image and then the knee area was separated. • The proposed detection method performed better than K-means and saliency. [ABSTRACT FROM AUTHOR]

Road scene model construction is an important aspect of intelligent transportation system research. This paper proposes an intelligent framework that can automatically construct road scene models from image sequences. The road and foreground regions are detected at superpixel level via a new kind of random walk algorithm. The seeds for different regions are initialized by trapezoids that are propagated from adjacent frames using optical flow information. The superpixel level region detection is implemented by the random walk algorithm, which is then refined by a fast two-cycle level set method. After this, scene stages can be specified according to a graph model of traffic elements. These then form the basis of 3D road scene models. Each technical component of the framework was evaluated and the results confirmed the effectiveness of the proposed approach.

Dark slope streaks (DSSs) on the Martian surface are one of the active geologic features that can be observed on Mars nowadays. The detection of DSS is a prerequisite for studying its appearance, morphology, and distribution to reveal its underlying geological mechanisms. In addition, increasingly massive amounts of Mars high resolution data are now available. Hence, an automatic detection method for locating DSSs is highly desirable. In this research, we present an automatic DSS detection method by combining interest region extraction and machine learning techniques. The interest region extraction combines gradient and regional grayscale information. Moreover, a novel recognition strategy is proposed that takes the normalized minimum bounding rectangles (MBRs) of the extracted regions to calculate the Local Binary Pattern (LBP) feature and train a DSS classifier using the Adaboost machine learning algorithm. Comparative experiments using five different feature descriptors and three different machine learning algorithms show the superiority of the proposed method. Experimental results utilizing 888 extracted region samples from 28 HiRISE images show that the overall detection accuracy of our proposed method is 92.4%, with a true positive rate of 79.1% and false positive rate of 3.7%, which in particular indicates great performance of the method at eliminating non-DSS regions. [ABSTRACT FROM AUTHOR]

A color sketch creates a vivid depiction of a scene using sparse pencil strokes and casual colored brush strokes. The interactive drawing system ColorSketch can help novice users generate color sketches from photos. To preserve artistic freedom and expressiveness, the proposed system gives users full control over pencil strokes, while automatically augmenting pencil sketches using color mapping, brush stroke rendering, and blank area creation. Experimental and user study results demonstrate that users, especially novices, can create better color sketches with our system than when using traditional manual tools. [ABSTRACT FROM PUBLISHER]

In this paper, a new multiphase segmentation which has two stages is proposed. At the first stage, independent from the kind of image, k equidistant real numbers within [0, 1] interval are set as the labels of k main regions. At the second stage, two factors are used, which consist of the intensity function for distinguishing similar regions, as well as the eigenvector of Hessian matrix for distinguishing similar ridges with an auxiliary parameter for controlling the influence of this factor in different images. Also, an iterative algorithm is applied for gradually growing the region. Numerical experiences are given to illustrate the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

In recent years, more than 300 sets of Trouble of Running Freight Train Detection Systems (TFDSs) have been installed on railway to monitor the safety of running freight trains in China. However, TFDS is simply responsible for capturing, transmitting, and storing images, and fails to recognize faults automatically. Motivated by the success of convolutional neural networks (CNNs) in the tasks of image recognition, this paper makes essential use of CNN models and proposes an automatic fault recognition system (AFRS) for recognizing four typical faults in TFDS simultaneously. AFRS is a two-stage system: In the first stage, a coarse-to-fine scheme based on CNN model is adopted to detect the target regions of side frame keys (SFKs) and shaft bolts (SBs) simultaneously. In the second stage, we establish another CNN model for multi-fault determination to recognize four typical faults emerged in the target regions of SFKs and SBs. The experimental results show that this system has an excellent performance of multi-fault recognition in TFDS. High recognition accuracy rates, low false ratios and low omission ratios are obtained for all the four typical faults, demonstrating the high recognition ability and robustness against various low quality imaging situations. [ABSTRACT FROM AUTHOR]

Feature extraction from observed noisy samples is a common important problem in statistics and engineering. This paper presents a novel general statistical approach to the region detection problem in long data sequences. The proposed technique is a multiscale kernel regression in conjunction with statistical multiple testing for region detection while controlling the false discovery rate (FDR) and maximizing the signal-to-noise ratio via matched filtering. This is achieved by considering a one-dimensional region detection problem as its equivalent zero-dimensional peak detection problem. The detection method does not require a priori knowledge of the shape of the nonzero regions. However, if the shape of the nonzero regions is known a priori, e.g., rectangular pulse, the signal regions can also be reconstructed from the detected peaks, seen as their topological point representatives. Simulations show that the method can effectively perform signal detection and reconstruction in the simulated data under high noise conditions, while controlling the FDR of detected regions and their reconstructed length. [ABSTRACT FROM AUTHOR]

Road junctions are important parts of the road network, and have a major role in GIS database updating, image matching, object detecting, and so on. In high resolution SAR images, there exist various kinds of interference on the road, and the contrast is not obvious between roads and surroundings. It is difficult to extract road junctions by traditional methods. A new method is proposed for directly detecting and identifying road junctions in this paper. Firstly, based on the junctions gray feature, global searching is done for the center positions of the road junctions’ candidate regions, by using morphological transformation methods. Secondly, the center positions are set as the local windows centers, road targets are segmented by using the multi-threshold Otsu method in the local windows. Thirdly, according to the geometric characteristics of junctions, we obtain the angle-mean figure in the rectangular template rotation process, and then get the number of the roads connected to a junction. Finally, the style of the junction is recognized. In 1 m high-resolution airborne SAR image experiment, the results indicate that this method is effective to detect and identify the junctions with various interferences.

Aim. Alzheimer’s disease (AD) is a chronic neurodegenerative disease. Recently, computer scientists have developed various methods for early detection based on computer vision and machine learning techniques.Method. In this study, we proposed a novel AD detection method by displacement field (DF) estimation between a normal brain and an AD brain. The DF was treated as the AD-related features, reduced by principal component analysis (PCA), and finally fed into three classifiers: support vector machine (SVM), generalized eigenvalue proximal SVM (GEPSVM), and twin SVM (TSVM). The 10-fold cross validation repeated 50 times.Results. The results showed the “DF + PCA + TSVM” achieved the accuracy of 92.75 ± 1.77, sensitivity of 90.56 ± 1.15, specificity of 93.37 ± 2.05, and precision of 79.61 ± 2.21. This result is better than or comparable with not only the other proposed two methods, but also ten state-of-the-art methods. Besides, our method discovers the AD is related to following brain regions disclosed in recent publications: Angular Gyrus, Anterior Cingulate, Cingulate Gyrus, Culmen, Cuneus, Fusiform Gyrus, Inferior Frontal Gyrus, Inferior Occipital Gyrus, Inferior Parietal Lobule, Inferior Semi-Lunar Lobule, Inferior Temporal Gyrus, Insula, Lateral Ventricle, Lingual Gyrus, Medial Frontal Gyrus, Middle Frontal Gyrus, Middle Occipital Gyrus, Middle Temporal Gyrus, Paracentral Lobule, Parahippocampal Gyrus, Postcentral Gyrus, Posterior Cingulate, Precentral Gyrus, Precuneus, Sub-Gyral, Superior Parietal Lobule, Superior Temporal Gyrus, Supramarginal Gyrus, and Uncus.Conclusion. The displacement filed is effective in detection of AD and related brain-regions.

This paper is concerned with selective color feature for detecting salient regions. In contrast to most existing methods related to detection in one color space, the proposed algorithm pre-segments the input image into superpixels in both RGBY color space and Lab color space. Next, to calculate color contrast we not only consider the local feature, but also compute the difference between the pixel and the whole image. In the meanwhile, based on the center-surrounding scheme, a new computational model of color distribution features is presented to detect salient regions. Finally, 2D entropy is employed as an evaluation criterion to select and integrate the proper color features. Experimental results show that the proposed method outperforms the state-of-the-art methods on salient region detection. [ABSTRACT FROM AUTHOR]