Single Image Research Articles

Efficient packaging defect detection: leveraging pre-trained vision models through transfer learning

The inspection of packaging defects is a crucial aspect of maintaining the quality of industrial production, especially in the case of boxed products. This study introduces a novel approach for detecting physical defects in product packaging boxes by integrating image processing with deep learning, specifically transfer learning with two images as an input. The proposed method utilizes both top view and side view images of the packaging to determine its condition, a significant departure from the conventional single image input. Our approach incorporates 16 pre-trained model variants from EfficientNetV2, MobileNetV3, and ResNetV2 for transfer learning as feature extractors. The experimental findings demonstrate that the best model that leverages EfficientNetV2 variant achieves 100% accuracy and F1 score in terms of classification performance. However, the most optimal model in terms of classification performance and inference speed was the one that leveraged ResNetV2 variant. This model scored 95% accuracy and 95.24% F1 score, with an inference speed of 91 ms per prediction.

Single image multi-scale enhancement for rock Micro-CT super-resolution using residual U-Net

Single image multi-scale enhancement for rock Micro-CT super-resolution using residual U-Net

Face mask classification using convolutional neural networks with facial image regions and super resolution

<p>Face mask classification is relevant to public health and safety, so an approach for face mask classification using Multi-Task Cascaded Convolutional Networks (MTCNN) for face detection on image data, ResNet152 architecture for feature extraction, and super-resolution method, BSRGAN, for enhanced image quality was proposed. The classification model was trained by a fully connected layer of neural networks. The goal is to classify each facial image into three classes: the image with a mask, without a mask, or with an incorrectly worn mask. The performance of each classification model on two real-world datasets was evaluated by Accuracy, Precision, Recall, and F1 score for different sets of input patterns which were features extracted from the facial image regions including their combinations. Using multiple image regions, i.e. face, nose, and mouth, as resources for preparing input features showed the improved classification performance compared to using single image regions. In addition, the super-resolution technique applied to medium or large-sized images can improve the performance of the face mask classification model. Our findings may further guide the development for greater effective models and techniques on face mask classification contributing to practical scenarios.</p>

A Case Study on Image Co-Registration of Hyper Spectral and Dual (L & S) Band SAR Data and Ore Findings Over Zewar Mines, India

The technique of superimposing two or more photographs in a way that ensures that for each image, the same pixel corresponds to the same location of the target scene is known as image coregistration It is a crucial stage in the picture enhancement process for satellite images. Different frequency bands store feature. Image fusion makes it possible to superimpose co-registered pictures taken by several sensors to get a superior image incorporating elements from both sources. On many match patches that are evenly dispersed over the two scenes, we estimate pixel offsets between possibly coherent picture pairings as image coregistration allows a more detailed single image to be obtained than many photos with distinct attributes. This study presents existing various fusion methods for ASAR (Airborne Synthetic Aperture Radar) images in the S-band and L-band to interpret urban, forestry, and agricultural areas. AVIRIS hyper spectral data also shows mining possibilities on ore of region. Hence, the seeking of ore region, and coregistration using fusion facilitates the remote sensing architecture next to drones.

Depth-Enhancement Network for Monocular 3D object detection

Abstract To accurately obtain 3D information, the correct use of depth data is crucial. Compared with radar-based methods, detecting objects in 3D space in a single image is extremely challenging due to the lack of depth cues. However, monocular 3D object detection provides a more economical solution. Traditional monocular 3D object detection methods often rely on geometric constraints, such as key points, object shape relationships, and 3D to 2D optimization, to address the inherent lack of depth information. However, these methods still make it challenging to extract rich information directly from depth estimation for fusion. To fundamentally enhance the ability of monocular 3D object detection, we propose a monocular 3D object detection network based on depth information enhancement. The network learns object detection and depth estimation tasks simultaneously through a unified framework, integrates depth features as auxiliary information into the detection branch, and then constrains and enhances them to obtain better spatial representation. To this end, we introduce a new cross-modal fusion strategy, which realizes a more reasonable fusion of cross-modal information by exploring redundant, complementary information and their interactions between RGB features and depth features. Extensive experiments on the KITTI dataset show that our method can significantly improve the performance of monocular 3D object detection.

TransDehaze: transformer-enhanced texture attention for end-to-end single image dehaze

TransDehaze: transformer-enhanced texture attention for end-to-end single image dehaze

Exploring the Differences in Tree Species Classification between Typical Forest Regions in Northern and Southern China

Focusing on the trend of continuously seeking high-precision tree species classification results in small areas from the perspectives of sensors and classification algorithms. This study aimed to explore the effects of data sources, classifiers, and seasons on classification accuracy in regions with significant environmental variation, examining patterns of tree species classification to enhance the transferability of classification. Considering two typical forest distribution regions in the north and south of China, this study utilized the revisitation cycle and open-source advantages of Sentinel-2 and Landsat-8. Leveraging the Google Earth Engine (GEE) platform, this study captured spectral features, vegetation indices, and texture features for single seasonal and seasonal combination images. With the assistance of Sentinel-1A and SRTM (Shuttle Radar Topography Mission) DEM (Digital Elevation Model), backscattering coefficient features and topographical features were extracted and input with features captured from Sentinel-2 and Landsat-8 into three types of classifiers: random forest (RF), support vector machine (SVM), and gradient tree boosting (GTB) for major tree species classification. In this research, we discovered that the best classification for single season in the northern study area was spring, whereas, for the southern study area, it was winter. Seasonal combination images effectively improved the classification accuracy of single seasonal images, with Sentinel-2 imagery displaying better classification performance compared to Landsat-8, and the optimal classifier differing between the north and the south. The inclusion of topographical or backscattering coefficient features in the four-season combination imagery contributed to improvements in classification accuracy, with topographical features significantly enhancing the classification performance in the topographically varied southern study area. The evaluation of feature importance indicated that elevation was the most critical feature for classification, while spectral features and vegetation indices were also significant. In the southern study area with large topographical discrepancies, subdividing into different terrain units led to improved tree species classification accuracy in medium-altitude, gentle slope areas. These findings provide insights into the regularity of enhancing tree species classification accuracy in environmentally diverse areas through the use of multi-source remote sensing data and multi-seasonal imagery. Consequently, the results offer a reference for the identification of tree species across large areas and the creation of spatial distribution maps.

Exploiting local detail in single image super-resolution via hypergraph convolution

Exploiting local detail in single image super-resolution via hypergraph convolution

Comparison between Short, Medium, and Long Fields of View in Estimating Bicep Femoris Fascicle Length

Measuring the bicep femoris long head fascicle length via the use of diagnostic ultrasound has become common practice within elite sport, using single images of between 4 and 6 cm. No study to date has compared single image estimations in terms of the varying fields of view (i.e., 4, 6, and 10 cm). Therefore, the aim of this study was to determine whether differences occur when estimating the bicep femoris long head fascicle length using short (4 cm), medium (6 cm), and long (10 cm) fields of view across three estimation equations. A total of 36 male athletes (age: 23.8 ± 3.8 years, body mass: 83.7 ± 14.0 kg, height: 1.81 ± 0.06 m) had three ultrasound images of the bicep femoris long head collected on a single occasion with the fascicle length estimated. A significant main effect was observed (p < 0.001) with moderate–very large differences (p < 0.078, d = 0.91–4.01). The smallest fields of view resulted in the greatest fascicle length. There were significant moderate–large associations between the fields of view (p < 0.001, r = 0.542–0.892). Unacceptable limits of agreement were observed, and the developed correction equations remained unacceptable. The partial measure equation is the most accurate whilst using the 10 cm fields of view, while the basic trigonometry equation had the lowest variability between fields of view and the smallest differences between fields of view; hence, this equation may be more appropriate when a <6 cm field of view is the only field of view available.

Image Caption Bot for Assistive Vision

It's challenging to automatically produce brief descriptions of an image's meaning because it can have diverse connotations in different languages. However, due to the vast amount of information packed into a single image, it is challenging to parse out the necessary context to use it to build sentences. It's a great way for the visually impaired to get around independently. This type of system can be built using the emerging programming technique of deep learning. This paper presents the development of an Image Caption Bot designed to aid individuals with visual impairments. We achieve enhanced accuracy in caption generation by modeling on the MSCOCO dataset using a Transformer encoder and Inception v3 for image processing. Image captioning, which entails generating textual descriptions for images, is the primary focus of our research. We achieve enhanced accuracy in caption generation by utilizing a Transformer encoder during training. The MSCOCO dataset serves as a valuable The results of the model are translated into speech for the benefit of the visually handicapped. Keywords—CNN, Google Text To Speech, MS-COCO, Inspection v3.

Patient Data Hiding and Transmitting during COVID-19 for Telemedicine Application using Image Steganography.

After the COVID-19 pandemic, every individual needs to be more aware of their health. The condition of the human body is ged based on various health reports like X-rays, CT scan, and MRI scans. Moreover, due to misplacement or loss of medical reports, there is a high probabaility of improper diagnosis. In order to avoid improper diagnosis, a novel data-hiding technique is proposed in this work. In the proposed method, the patient's health records are hidden using polynomial theory in the patient photograph. This is used by doctors in telemedicine for better treatment at the right time. Image steganography is useful for hiding secret images and also for generating secret keys. This enables only the authorized people (patient and corresponding doctor) to access the reports using secret keys. Four secret images (medical reports of the patient) are successfully embedded onto a single cover image (patient photo) with good quality. After embedding, the stego images look like cover images so that unauthorized persons will not be able to access the data, and hence, safe transmission is being carried out. A patient's medical report plays an important role in proper medical treatment. Particularly in telemedicine, the safe transmission of patient reports without any loss or damage is necessary. The proposed method embeds reports of a patient in his/her photo and transmitsthem to the destination safely with a quality of 45.5 dB. This hiding method is helpful to avoid cyber crimes, illegal transactions, malpractices etc.

Deep single image deraining using an asymmetric cyclic generative and adversarial framework

Deep single image deraining using an asymmetric cyclic generative and adversarial framework

Super-resolution reconstruction of single image for latent features

AbstractSingle-image super-resolution (SISR) typically focuses on restoring various degraded low-resolution (LR) images to a single high-resolution (HR) image. However, during SISR tasks, it is often challenging for models to simultaneously maintain high quality and rapid sampling while preserving diversity in details and texture features. This challenge can lead to issues such as model collapse, lack of rich details and texture features in the reconstructed HR images, and excessive time consumption for model sampling. To address these problems, this paper proposes a Latent Feature-oriented Diffusion Probability Model (LDDPM). First, we designed a conditional encoder capable of effectively encoding LR images, reducing the solution space for model image reconstruction and thereby improving the quality of the reconstructed images. We then employed a normalized flow and multimodal adversarial training, learning from complex multimodal distributions, to model the denoising distribution. Doing so boosts the generative modeling capabilities within a minimal number of sampling steps. Experimental comparisons of our proposed model with existing SISR methods on mainstream datasets demonstrate that our model reconstructs more realistic HR images and achieves better performance on multiple evaluation metrics, providing a fresh perspective for tackling SISR tasks.

Single slice MR image estimation of 3D supraspinatus intramuscular fatty infiltration in older adults: relevance for clinical practice and research.

(1) To compare older adults stratified by supraspinatus tendon tear status (STT status)-no tear (Intact), partial-thickness (PT) tear, full-thickness (FT) tear-by 3D Dixon fat fraction (3D-FF); 2D fat fraction (2D-FF); and 2D Goutallier grade (2D-GG) at the Y-shaped view, and 1.4cm and 2.8cm medial to the Y-shaped view. Stratified by STT status to determine (2) correlation of 3D-FF with 2D-FF and 2D-GG and (3) inter-rater reliability at and medial to the Y-shaped view. Forty-five volunteers ≥ 60years recruited prospectively received shoulder MRI. 3D-FF and 2D-FF were measured on 6-point-Dixon MRI by three trainees. Goutallier grade was assessed on T1-weighted MRI by three fellowship-trained diagnostic radiologists. Descriptive, reliability, and correlation analyses were performed. Groups showed no difference in age. The FT group showed higher (p < 0.05) mean 3D-FF (14.09% ± 10.99%), mean 2D-FF (1.4cm medial to Y-shaped view, 14.91% ± 12.11%; 2.8cm medial to Y-shaped view, 13.32% ± 9.48%), and mean 2D-GG (Y-shaped view, 1.71 ± 0.78; 1.4cm medial to Y-shaped view, 1.71 ± 0.69; 2.8cm medial to Y-shaped view, 1.71 ± 0.72), relative to Intact/PT groups. 3D-FF showed strong correlation with 2D-FF among all groups/all analyses (rho, 0.80-0.98; p < 0.001). 3D-FF showed strong correlation with 2D-GG for all FT group analyses (rho, 0.85-0.91; p < 0.05). 3D-FF showed moderate-to-strong correlation considering all Intact/PT group analyses (rho, 0.51-0.79; p < 0.50). Dixon fat fraction showed excellent reliability for all groups (≥ 0.884, intraclass correlation coefficient). Goutallier grade showed excellent reliability for FT group (0.771, weighted Fleiss's kappa) but poor (0.294) and fair (0.502) for Intact and PT groups, respectively. Single slice MR image estimation of 3D supraspinatus intramuscular fatty infiltration has merit for continued use in clinical populations requiring potential rotator-cuff-repair surgery. However, Dixon fat fraction should be prioritized for use in research over Goutallier grade due to superior reliability.

Weakly Supervised Pose Estimation of Surgical Instrument from a Single Endoscopic Image

Instrument pose estimation is a key demand in computer-aided surgery, and its main challenges lie in two aspects: Firstly, the difficulty of obtaining stable corresponding image feature points due to the instruments’ high refraction and complicated background, and secondly, the lack of labeled pose data. This study aims to tackle the pose estimation problem of surgical instruments in the current endoscope system using a single endoscopic image. More specifically, a weakly supervised method based on the instrument’s image segmentation contour is proposed, with the effective assistance of synthesized endoscopic images. Our method consists of the following three modules: a segmentation module to automatically detect the instrument in the input image, followed by a point inference module to predict the image locations of the implicit feature points of the instrument, and a point back-propagatable Perspective-n-Point module to estimate the pose from the tentative 2D–3D corresponding points. To alleviate the over-reliance on point correspondence accuracy, the local errors of feature point matching and the global inconsistency of the corresponding contours are simultaneously minimized. Our proposed method is validated with both real and synthetic images in comparison with the current state-of-the-art methods.

A Novel Multi-camera Fusion Approach at Plant Scale: From 2D to 3D

Non-invasive crop phenotyping is essential for crop modeling, which relies on image processing techniques. This research presents a plant-scale vision system that can acquire multispectral plant data in agricultural fields. This paper proposes a sensory fusion method that uses three cameras, Two multispectral and a RGB depth camera. The sensory fusion method applies pattern recognition and statistical optimization to produce a single multispectral 3D image that combines thermal and near-infrared (NIR) images from crops. A multi-camera sensory fusion method incorporates five multispectral bands: three from the visible range and two from the non-visible range, namely NIR and mid-infrared. The object recognition method examines about 7000 features in each image and runs only once during calibration. The outcome of the sensory fusion process is a homographic transformation model that integrates multispectral and RGB data into a coherent 3D representation. This approach can handle occlusions, allowing an accurate extraction of crop features. The result is a 3D point cloud that contains thermal and NIR multispectral data that were initially obtained separately in 2D.

A Technique for In-Situ Displacement and Strain Measurement with Laboratory-Scale X-Ray Computed Tomography

Abstract Purpose: Establish a technique for simultaneous interrupted volumetric imaging of internal structure and time-resolved full-field surface strain measurements during in-situ X-ray micro-computed tomography (XCT) experiments. This enables in-situ testing of stiff materials with large forces relative to the compliance of the in-situ load frame, which might exhibit localization (e.g., necking, compaction banding) and other inhomogeneous behaviors.Methods: The system utilizes a combination of in-situ XCT, 2D X-ray imaging, and particle tracking to conduct volumetric imaging of the internal structure of a specimen with interrupted loading and surface strain mapping during loading. Critically, prior to the laboratory-scale XCT experiments, specimens are speckled with a high-X-ray-contrast powder that is bonded the surface. During in-situ loading, the XCT system is programmed to capture sequential 2D X-ray images orthogonal to the speckled specimen surface. A single particle tracking (SPT) or digital image correlation (DIC) algorithm is used to measure full-field surface strain evolution throughout the time-sequence of images. At specified crosshead displacements, the motion and 2D image sequence is paused for volumetric XCT image collection. Results: We show example results on a micro-tensile demonstration specimen additive manufactured from Inconel 718 nickel-chrome alloy. Results include XCT volume reconstructions, crosshead-based engineering stress, and full-field strain maps. Conclusion: We demonstrate an in-situ technique to obtain surface strain evolution during laboratory-scale XCT testing and interrupted volumetric imaging. This allows closer investigation of, for example, the effect of micro-pores on the strain localization behavior of additive manufactured metal alloys. In addition to describing the method using a representative test piece, the dataset and code are published as open-source resources for the community. Graphical abstract

Frequency-oriented hierarchical fusion network for single image raindrop removal.

Single image raindrop removal aims at recovering high-resolution images from degraded ones. However, existing methods primarily employ pixel-level supervision between image pairs to learn spatial features, thus ignoring the more discriminative frequency information. This drawback results in the loss of high-frequency structures and the generation of diverse artifacts in the restored image. To ameliorate this deficiency, we propose a novel frequency-oriented Hierarchical Fusion Network (HFNet) for raindrop image restoration. Specifically, to compensate for spatial representation deficiencies, we design a dynamic adaptive frequency loss (DAFL), which allows the model to adaptively handle the high-frequency components that are difficult to recover. To handle spatially diverse raindrops, we propose a hierarchical fusion network to efficiently learn both contextual information and spatial features. Meanwhile, a calibrated attention mechanism is proposed to facilitate the transfer of valuable information. Comparative experiments with existing methods indicate the advantages of the proposed algorithm.

Enhanced collapsible linear blocks for arbitrary sized image super-resolution

AbstractImage up-scaling and super-resolution (SR) techniques have been a hot research topic for many years due to its large impact in the field of medical imaging, surveillance etc. Especially single image super-resolution (SISR) become very popular because of the fast development of deep convolution neural network (DCNN) and the low requirement on the input. They are achieving outstanding performance. However, there are still problems in the state-of-the-art works, especially from two perspectives: 1. failed at exploiting the hierarchical characteristics from the input, resulting in loss of information and artifacts in the final high resolution (HR) image; 2. failed to handle arbitrary-sized images; the existing research works are focused on fixed size input images. To address these challenges, this paper proposed a residual dense network (RDN) and multi-scale sub-pixel convolution network (MSSPCN) which are integrated into a Collapsible Linear Block Super Efficient Super-Resolution (SESR) network. The RDNs aims to tackle the first challenge, carrying the hierarchical features from end-to-end. An adaptive cropping strategy (ACS) technique is introduced before feature extraction targeting at the image size challenge. The novelty of this work is extracting the hierarchical features and integrating RDNs with MSSPCNs. The proposed network can upscale any arbitrary-sized image (1080p) to ×2 (4K) and ×4 (8K). To secure ground truth for evaluation, this paper follows the opposite flow, generating the input LR images by down-sampling the given HR images (ground truth). To evaluate the performance, the proposed algorithm is compared with eight state-of-the-art algorithms, both quantitatively and qualitatively. The results are verified on six benchmark datasets. The extensive experiments justify that the proposed architecture performs better than other methods and upscales the images satisfactorily.

Feature decoupling and reorganization network for single image deraining

Feature decoupling and reorganization network for single image deraining