Image Detection Research Articles

Evasion on general GAN-generated image detection by disentangled representation

Images generated by the Generative Adversarial Network (GAN) are too realistic to be distinguished by humans. Recently, some detection methods have been proposed to distinguish between generated and real images. However, these methods rely on specific detection techniques and can be easily detected by other types of detection methods. This study aims to investigates the security of the GAN-generated image detection method by devising a method to evade general detection. The features related and unrelated to differentiating between real and generated images are disentangled by a GAN model in our model. The unrelated features contain information about the image content, while the related feature provides useful information for identifying generated images. Our method then camouflages a generated image by using its unrelated features and the related features of real images. The main advantages of our model include its ability to generalize to different detectors and adapt to the prior information about detectors. Experimental results confirm the superior evasion capability of our proposed method compared to other detector-dependent and independent methods across different popular detection methods.

An Enhanced Deep Learning-Based Pharmaceutical Crystal Detection with Regional Filtering

In the process of pharmaceutical crystallization, the automatic detection of crystal shapes in images is important since controlling the morphology of the crystals improves the quality of pharmaceutical crystals. In this paper, a novel image detection method called RECDet is proposed. It leverages an automatically adapted binary image to bypass background regions, thereby reducing the detection field. In addition, the method greatly reduces the training time while improving the detection accuracy by using a specially designed detection box for the crystal shape. The performance of our model is evaluated through experimental analysis on a publicly available glutamate crystal dataset and a self-made entecavir pharmaceutical crystal dataset. Experimental results show that RECDet improves the accuracy of prediction bounding boxes by more than 2% compared to other popular models and achieves a classification accuracy of 98%. It can be used as a promising tool in the application of pharmaceutical crystallization control.

Convolution Neural Network Based Deep Learning Approach for MRI Based Brain Tumour Image Detection

Convolution Neural Network Based Deep Learning Approach for MRI Based Brain Tumour Image Detection

MPE-DETR: A multiscale pyramid enhancement network for object detection in low-light images

Object detection has broad applications in areas such as autonomous driving, security surveillance, and deep-sea exploration. However, the performance of current detection algorithms significantly decreases due to the loss of detail, increased noise, and color distortion in images under low-light or nighttime conditions. To address this problem, we propose a plug-and-play multiscale pyramid enhancement network (MPENet), which elegantly cascades with RT-DETR to establish an end-to-end framework for low-light object detection, named MPE-DETR. First, MPENet utilizes Gaussian blur to decompose images into Gaussian pyramids and Laplacian pyramids at different resolutions. Specifically, we designed a high-frequency texture enhancement (HTE) module to capture the edge and texture information of images, and a low-frequency noise smoothing (LNS) module to better understand the overall structure of images and capture global-scale features. Additionally, by concatenating the output features of the HTE and LNS modules along the channel dimension, feature fusion across different scales is realized. We conducted experiments on the ExDark and ExDark + LOD datasets, which are designed for low-light object detection. The results indicate that the proposed method achieved an improvement of 2.1% in mAP@.5 compared to that of existing SOTA models on the ExDark dataset, and demonstrated strong generalizability and robustness on the ExDark + LOD dataset. The code and results are available at https://github.com/PZDJL/MPENet.

Framework for psoriasis/molluscum detection in skin images using ResNetV2 variants

BackgroundComputer algorithms are extensively utilized in hospitals for the purpose of achieving expedited and precise disease identification from medical data. The objective of this study is to propose a deep-learning (DL) framework to classify the chosen digital skin image (DSI) database into psoriasis and molluscum with better accuracy. Aims and objectivesAims to develop a DL-tool using the pre-trained ResNetV2 DL-models and verify the performance of the developed tool using a chosen DSI database. Further, confirm the merit of the ResNetV2-based tool against other chosen DL-models. Methods and resultsThis study initially examines the performance of chosen pre-trained DL (PDL) methods using the DSI database using conventional and fused features. Proposed DL-tool consist the following stages; (i) image collection and resizing it 224x224x3 pixels, (ii) deep-features extraction using the selected PDL, (iii) feature reduction and serial features concatenation to get a new features vector, and (iv) the performance evaluation through three-fold cross validation and confirmation. The feature reduction and serial features fusion of this study is performed initially using feature sorting based on its rank and 50% dropout and Particle Swarm Optimization (PSO) based feature reduction. The reduced features of two chosen PDL-models are then considered to obtain the Fused Deep Features (FDF) and the classification task is executed on the DSI data to verify the performance of the developed DL-tool. The experimental outcome of this study confirms that the proposed scheme helps to provide a detection accuracy of >97%, when the K-Nearest Neighbour based classification is executed. ConclusionInvestigational outcome of this study confirms that the proposed DL-tool helps to achieve better detection accuracy when the features of ResNetV2 models are considered to generate the FDF. Further, the accuracy achieved with the PSO based FDF is better compared to the conventional method generated FDF.

BP-YOLOv8: rotating target detection in synthetic aperture radar ship images based on improved YOLOv8

BP-YOLOv8: rotating target detection in synthetic aperture radar ship images based on improved YOLOv8

DSN-BR-Based Online Inspection Method and Application for Surface Defects of Pharmaceutical Products in Aluminum-Plastic Blister Packages

Ensuring high product quality is of paramount importance in pharmaceutical drug manufacturing, as it is subject to rigorous regulatory practices. This study presents a research focused on the development of an on-line detection method and system for identifying surface defects in pharmaceutical products packaged in aluminum-plastic blisters. Firstly, the aluminum-plastic blister packages exhibit multi-scale features and inter-class indistinction. To address this, the deep semantic network with boundary refinement (DSN-BR) model is proposed, which leverages semantic segmentation domain knowledge, to accurately segment the defects in pixel level. Additionally, a specialized image acquisition module that minimizes the impact of ambient light is established, ensuring high-quality image capture. Finally, the image acquisition module, image detection module, and data management module are designed to construct a comprehensive online surface defect detection system. To validate the effectiveness of our approach, we employ a real dataset for instance verification on the implemented system. The experimental results substantiate the outstanding performance of the DSN-BR, achieving the mean intersection over union (MIoU) of 90.5%. Furthermore, the proposed system achieves an inference speed of up to 14.12 f/s, while attaining an F1-Score of 98.25%. These results demonstrate that the system meets the actual needs of the enterprise and provides theoretical and methodological support for intelligent inspection of product surface quality. By standardizing the control process of pharmaceutical manufacturing and improving the management capability of the manufacturing process, our approach holds significant market application prospects.

Nighttime wildlife object detection based on YOLOv8‐night

AbstractMonitoring nocturnal animals in the field is an important task in ecological research and wildlife conservation, but the complexity of nocturnal images and low light conditions make it difficult to cope with traditional image processing methods. To address this problem, researchers have introduced infrared cameras to improve the accuracy of nocturnal animal behaviour observations. Object detection in nighttime images captured by infrared cameras faces several challenges, including low image quality, animal scale variations, occlusion, and pose changes. This study proposes the YOLOv8‐night model, which effectively overcomes these challenges by introducing a channel attention mechanism in YOLOv8. The model is more focused on capturing animal‐related features by dynamically adjusting the channel weights, which improves the saliency of key features and increases the accuracy rate in complex backgrounds. The main contribution of this study is the introduction of the channel attention mechanism into the YOLOv8 framework to create a YOLOv8‐night model suitable for object detection in nighttime images. When tested on nighttime images, the model performs well with a significantly higher mAP (0.854) than YOLOv8 (0.831), and YOLOv8‐night scores 0.856 on mAP_l, which is obviously better than YOLOv8 (0.833) in terms of processing large objects. The study provides a reliable technical tool for ecological research, wildlife conservation and environmental monitoring, and offers new methods and insights for the study of nocturnal animal behaviour.

Knowledge-informed randomized machine learning and data fusion for anomaly areas detection in multimodal 3D images

We consider a long-standing yet hard and largely open machine learning problem of anomaly areas detection in multimodal 3D images. Purely data-driven methods often fail in such tasks because rarely incorporating domain-specific knowledge into the algorithm and do not fully utilize information from multiple modalities. We address these issues by proposing a novel framework with data fusion technology to leverage domain-specific knowledge and multimodal labeled data, as well as employ the power of randomized learning techniques. To demonstrate the proposed framework efficiency, we apply it to the challenging task of detecting subtle pathologies in MRI scans. A distinct feature of the resulting solution is that it explicitly incorporates evidence-based medical knowledge about pathologies into the feature maps. Our experiments show that the method is capable of achieving lesion detection in 71% of subjects by using just one such feature. Integrating information from all feature maps and data modalities enhances detection rate to 78%. Using stochastic configuration networks to initialize the weights of the classification model enables to increase precision metric by 18% as compared to deterministic approaches. This demonstrates the possibility and practical viability of building efficient and interpretable randomised algorithms for automated anomaly detection in complex multimodal data.

A Hessian-Based Technique for Specular Reflection Detection and Inpainting in Colonoscopy Images.

In the field of Computer-Aided Detection (CADx), the use of AI-based algorithms for disease detection in endoscopy images, especially colonoscopy images, is on the rise. However, these algorithms often encounter performance issues due to obstructions like specular reflection, resulting in false positives. This paper presents a novel algorithm specifically designed to tackle the challenges posed by high specular reflection regions in colonoscopy images. The proposed algorithm identifies these regions and applies precise inpainting for restoration. The process entails converting the input image from RGB to HSV color space and focusing on the Saturation (S) component in convex regions detected using a Hessian-based method. This step creates a binary mask that pinpoints areas of specular reflection. The inpainting function then uses this mask to guide the restoration of these identified regions and their borders. To ensure a seamless blend of the restored regions with the background and adjacent pixels, a feathering process is applied to the repaired regions. This enhances both the accuracy and aesthetic coherence of the inpainted images. The performance of our algorithm was rigorously tested on five unique colonoscopy datasets and various endoscopy images from the Kvasir dataset, using an extensive set of evaluation metrics and a comparative analysis with existing methods consistently highlighted the superior performance of our algorithm.

Image augmentation approaches for small and tiny object detection in aerial images: a review

Image augmentation approaches for small and tiny object detection in aerial images: a review

Very fast, high-resolution aggregation 3D detection CAM to quickly and accurately find facial fracture areas

Background and objective:The incidence of facial fractures is on the rise globally, yet limited studies are addressing the diverse forms of facial fractures present in 3D images. In particular, due to the nature of the facial fracture, the direction in which the bone fractures vary, and there is no clear outline, it is difficult to determine the exact location of the fracture in 2D images. Thus, 3D image analysis is required to find the exact fracture area, but it needs heavy computational complexity and expensive pixel-wise labeling for supervised learning. In this study, we tackle the problem of reducing the computational burden and increasing the accuracy of fracture localization by using a weakly-supervised object localization without pixel-wise labeling in a 3D image space. Methods:We propose a Very Fast, High-Resolution Aggregation 3D Detection CAM (VFHA-CAM) model, which can detect various facial fractures. To better detect tiny fractures, our model uses high-resolution feature maps and employs Ablation CAM to find an exact fracture location without pixel-wise labeling, where we use a rough fracture image detected with 3D box-wise labeling. To this end, we extract important features and use only essential features to reduce the computational complexity in 3D image space. Results:Experimental findings demonstrate that VFHA-CAM surpasses state-of-the-art 2D detection methods by up to 20% in sensitivity/person and specificity/person, achieving sensitivity/person and specificity/person scores of 87% and 85%, respectively. In addition, Our VFHA-CAM reduces location analysis time to 76 s without performance degradation compared to a simple Ablation CAM method that takes more than 20 min. Conclusion:This study introduces a novel weakly-supervised object localization approach for bone fracture detection in 3D facial images. The proposed method employs a 3D detection model, which helps detect various forms of facial bone fractures accurately. The CAM algorithm adopted for fracture area segmentation within a 3D fracture detection box is key in quickly informing medical staff of the exact location of a facial bone fracture in a weakly-supervised object localization. In addition, we provide 3D visualization so that even non-experts unfamiliar with 3D CT images can identify the fracture status and location.

Visually Salient Region Detection in Omnidirectional Images Using Wavelet Textural Feature Map

Visually Salient Region Detection in Omnidirectional Images Using Wavelet Textural Feature Map

Involution Transformer Based U-Net for Landmark Detection in Ultrasound Images for Diagnosis of Infantile DDH.

The B-mode ultrasound based computer-aided diagnosis (CAD) has demonstrated its effectiveness for diagnosis of Developmental Dysplasia of the Hip (DDH) in infants, which can conduct the Graf's method by detecting landmarks in hip ultrasound images. However, it is still necessary to explore more valuable information around these landmarks to enhance feature representation for improving detection performance in the detection model. To this end, a novel Involution Transformer based U-Net (IT-UNet) network is proposed for hip landmark detection. The IT-UNet integrates the efficient involution operation into Transformer to develop an Involution Transformer module (ITM), which consists of an involution attention block and a squeeze-and-excitation involution block. The ITM can capture both the spatial-related information and long-range dependencies from hip ultrasound images to effectively improve feature representation. Moreover, an Involution Downsampling block (IDB) is developed to alleviate the issue of feature loss in the encoder modules, which combines involution and convolution for the purpose of downsampling. The experimental results on two DDH ultrasound datasets indicate that the proposed IT-UNet achieves the best landmark detection performance, indicating its potential applications.

Cross-Scene Joint Classification of Multisource Data With Multilevel Domain Adaption Network.

Domain adaption (DA) is a challenging task that integrates knowledge from source domain (SD) to perform data analysis for target domain. Most of the existing DA approaches only focus on single-source-single-target setting. In contrast, multisource (MS) data collaborative utilization has been extensively used in various applications, while how to integrate DA with MS collaboration still faces great challenges. In this article, we propose a multilevel DA network (MDA-NET) for promoting information collaboration and cross-scene (CS) classification based on hyperspectral image (HSI) and light detection and ranging (LiDAR) data. In this framework, modality-related adapters are built, and then a mutual-aid classifier is used to aggregate all the discriminative information captured from different modalities for boosting CS classification performance. Experimental results on two cross-domain datasets show that the proposed method consistently provides better performance than other state-of-the-art DA approaches.

Object-based image retrieval and detection for surveillance video

With technological advancement worldwide, the video surveillance market is growing drastically in a versatile field. Monitoring, browsing, and retrieving a specific object in a long video becomes difficult due to the enormous amount of data produced by the surveillance camera. With limitations on human resources and browsing time, there is a need for a new video analytics model to handle more complex tasks, such as object detection and query retrieval. The current approach involves techniques like unsupervised segmentation, multiscale segmentation, and feature-based descriptions. However, these methods often encounter extensive space and time consumption challenges. A solution has been developed for retrieving targeted objects from surveillance videos via user queries, employing a graphical interface for input. Extracting relevant frames based on user-entered text queries is enabled through using YOLOv8 for object detection. Users interact through a graphical user interface deployed on a Jetson Xavier Development board. The system's outcome is a time-efficient and highly accurate automated model for object detection and query retrieval, eliminating human errors associated with manually locating objects in videos upon user queries.

Critical Image Detection (CiD) and Single Image Detail Analysis (SiDA) – A practical approach to AI in NDT

Artificial Intelligence (AI) is gaining momentum in consumer and business applications and many approaches have changed the perspective on AI in Non-Destructive Testing (NDT). Most current discussions about AI in NDT revolve around automated defect detection / recognition (ADR), leaving the enormous potential of AI-based automation in other areas of the inspector's work process unexplored. It is in the nature of NDT that the human inspector's attention should be primarily focused on the parts that show indications or defects. These usually make up only a fraction of the components to be tested, as it is unknown which components actually show defects. This leads to a highly inefficient process that requires an evaluation of all components and thus ties up massive inspection capacities of human experts. The researchers of the German software company sentin have developed a system to process critical findings first and present those to the human inspector. NDT data such as images can be processed as batches leading to a (pre-) sorted dataset considering various indicators such as potential defects, duplicates, missing labels or references and many more. Such a resource-saving, high accuracy Critical Image Detection (CiD) system allows evaluators to find anomalies in complex and extensive datasets fast. After identification further automation can be achieved using a Single Image Detail Analysis system (SiDA), which is more resource intensive, but gives detailed information about the findings, potential defects and their location. The integration of these systems holds significant promises for the future application of AI in NDT. By streamlining the inspection process, they can generate substantial business value through time and cost savings.

HiSEG: Human assisted instance segmentation

Instance segmentation is a form of image detection which has a range of applications, such as object refinement, medical image analysis, and image/video editing, all of which demand a high degree of accuracy. However, this precision is often beyond the reach of what even state-of-the-art, fully automated instance segmentation algorithms can deliver. The performance gap becomes particularly prohibitive for small and complex objects. Practitioners typically resort to fully manual annotation, which can be a laborious process. In order to overcome this problem, we propose a novel approach to enable more precise predictions and generate higher-quality segmentation masks for high-curvature, complex and small-scale objects. Our human-assisted segmentation method, HiSEG, augments the existing Strong Mask R-CNN network to incorporate human-specified partial boundaries. We also present a dataset of hand-drawn partial object boundaries, which we refer to as “human attention maps”. In addition, the Partial Sketch Object Boundaries (PSOB) dataset contains hand-drawn partial object boundaries which represent curvatures of an object’s ground truth mask with several pixels. Through extensive evaluation using the PSOB dataset, we show that HiSEG outperforms state-of-the art methods such as Mask R-CNN, Strong Mask R-CNN, Mask2Former, and Segment Anything, achieving respective increases of +42.0, +34.9, +29.9, and +13.4 points in APMask metrics for these four models. We hope that our novel approach will set a baseline for future human-aided deep learning models by combining fully automated and interactive instance segmentation architectures.

MPE-YOLO: enhanced small target detection in aerial imaging

Aerial image target detection is essential for urban planning, traffic monitoring, and disaster assessment. However, existing detection algorithms struggle with small target recognition and accuracy in complex environments. To address this issue, this paper proposes an improved model based on YOLOv8, named MPE-YOLO. Initially, a multilevel feature integrator (MFI) module is employed to enhance the representation of small target features, which meticulously moderates information loss during the feature fusion process. For the backbone network of the model, a perception enhancement convolution (PEC) module is introduced to replace traditional convolutional layers, thereby expanding the network’s fine-grained feature processing capability. Furthermore, an enhanced scope-C2f (ES-C2f) module is designed, utilizing channel expansion and stacking of multiscale convolutional kernels to enhance the network’s ability to capture small target details. After a series of experiments on the VisDrone, RSOD, and AI-TOD datasets, the model has not only demonstrated superior performance in aerial image detection tasks compared to existing advanced algorithms but also achieved a lightweight model structure. The experimental results demonstrate the potential of MPE-YOLO in enhancing the accuracy and operational efficiency of aerial target detection. Code will be available online (https://github.com/zhanderen/MPE-YOLO).

Early detection of metastatic disease through screening ultrasound

Screening ultrasound is crucial in emergency care, providing precise guidance for patients in various situations. Its versatility, real-time imaging, and lack of radiation make it invaluable, especially in settings lacking diagnostic resources and specialized expertise. The widespread use of screening ultrasound among health professionals, regardless of their level of sonographic expertise, emphasizes the need for them to manage clinical uncertainties as part of their daily practice." This article emphasizes the crucial role of screening ultrasound, especially in acute abdomen cases. Its integration alongside conventional radiology significantly improves clinical orientation, facilitating prompt treatment decisions and specialist referrals. In a specific case, we reviewed screening ultrasound images, basic abdominal X-rays, and Computed Tomography scans alongside clinical reports to assess initial evaluations made at a peripheral emergency service. Our patient presented with acute abdominal symptoms, revealing suspected liver metastases, free fluid, and signs of intestinal obstruction on ultrasound. These findings were confirmed through Computed Tomography at a referral hospital, showing ultrasound's role in prompt patient triage and transfer. Operator skill is crucial, but comprehensive training minimizes errors. Screening sonography may revolutionize patient safety saving time by detecting pathologies early, preventing overcrowding in emergency departments of reference hospitals. The ultrasonographic detection of images suspected to be metastases is a common occurrence in hospital settings where various advanced diagnostic means, and medical specialties are present. However, the detection of suspicious images of metastases in a pre-hospital context is innovative and provides clinicians with a much better understanding of the patient's clinical landscape.