Input Image Research Articles

Image translation between human face and wayang orang using U-GAT-IT

<span lang="EN-US">Wayang orang performance is one of the Indonesian traditional cultures. The wayang orang players took about an hour to become a proper wayang orang since it takes time to have makeup and to find the appropriate costume before the performance is held. This problem can be solved by developing a computer-based simulation on applying makeup and traditional costume to the face and head of the wayang orang player, respectively. This task can be completed by using image translation. Therefore, people's images can be transformed into wayang orang images. This study aims to translate human faces into wayang orang by adding makeup and accessories using the U-GAT-IT with an unpaired dataset consisting of 1216 data trains and 240 data tests. The challenge of this research is to maintain the image background and the facial identity component in the input image. This research employs quantitative testing employ Kernel Inception Distance (KID), <em>Frèchet</em> Inception Distance (FID), and Inception Score (IS) to evaluate the quality of the output image obtained from the generator. The experimental results show that U-GAT-IT produces a better result than DCLGAN does according to the value of IS, FID, and KID. The IS, FID, and KID obtained by implementing U-GAT-IT are 2.414, 0.924, and 4.357, respectively.</span>

Structure tensor-based Gaussian kernel edge-adaptive depth map refinement with triangular point view in images

<span lang="EN-US">Image reconstruction is the process of restoring the image resolution. In 3D image reconstruction, the objects in different viewpoints are processed with the triangular point view (TPV) method to estimate object geometry structure for 3D model. This work proposes a depth refinement methodology in preserving the geometric structure of objects using the structure tensor method with a Gaussian filter by transforming a series of 2D input images into a 3D model. The computation of depth map errors can be found by comparing the masked area/patch with the distribution of the original image's greyscale levels using the error pixel-based patch extraction algorithm. The presence of errors in the depth estimation could seriously deteriorate the quality of the 3D effect. The depth maps were iteratively refined based on histogram bins number to improve the accuracy of initial depth maps reconstructed from rigid objects. The existing datasets such as the dataset tanks and unit (DTU) and Middlebury datasets, were used to build the model out of the object scene structure. The results of this work have demonstrated that the proposed patch analysis outperformed the existing state of the art models depth refinement methods in terms of accuracy.</span>

Low-resolution facial emotion recognition on low-cost devices

The low-resolution input image is a crucial challenge for applying facial emotion recognition in real-world scenarios. The critical problem is that valuable object features are relatively lost in the extraction process due to their small size. On the other hand, this vision system is required by a machine to run smoothly on low-cost devices. Facial emotion recognition using a lightweight feature extractor is proposed in this study to effectively capture crucial facial components in a low-resolution image. To compromise the running speed, this work offers an efficient feature convolution to discriminate specific facial features. In addition, the system is embedded with an attentive module to capture important features and correlate them. Our model performance is evaluated on low-resolution public datasets achieving the accuracy of 97.34\%, 81.10\%, and 80.12\% on KDEF, RFDB, and FER-plus, respectively. The practical application demands that the deep learning model can operate fast on inexpensive devices. Consequently, the model achieved a speed of 290 FPS on a CPU device.

Design and analysis of face recognition system based on VGGFace-16 with various classifiers

This research presents a face recognition system based on different classifiers that deal with various face positions. The proposed system involves the extraction of features through the VGG-Face-16 deep neural network, which only extracts essential features of input images, leading to an improved recognition step and enhanced algorithm efficiency, while the recognition involves the radial basis function in support vector machine (SVM) classifier and evaluate the performance of the system. Also, the system is designed and implemented later by using other classifiers; they are K-neareste2 neighbour (KNN) classifiers, logistic regression (LR), gradient boosting (XGBoost), decision tree classifier (DT) and Naive Bayes classifier (NB). The proposed algorithm was tested with the four face databases: AT&T, PINs Face, linear friction welding (LFW) and real database. The database was divided into two groups: One contains a percentage of images that are used for training and the second contains a percentage of images (remainder) which was used for testing. The results show that the classification by RBF in SVM has the highest recognition rate in the case of using small, medium and large databases; it was 100% in AT&T and Real database, while its efficiency appears to be lower when using large-size databases whereas it is 96% in PINs database and 60.1% in LFW database.

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.

Leaf Disease Detection Using Convolutional Neural Network

Leaf Disease Detection Using Convolutional Neural Network

Micronutrient Deficiency Using Image Processing and Neural Network

Abstract: Vitamin and micronutrient deficiencies are a significant global health concern, leading to various adverse health consequences. Early detection and intervention are essential in addressing these issues. The project introduces an intelligent system that utilizes advanced deep learning techniques to identify and differentiate vitamin deficiencies in human tissue through image analysis. The approach involves an initial step of image clustering to separate and isolate problem areas from the input images. The goal is to evaluate the productivity ofimage segmentation methods, extract relevant characteristics, and compare classification results with other methods. To accomplish the objectives, a diverse dataset of facial images is gathered and preprocessed, focusing on individuals both with and without visible signs of vitamin deficiencies Following this, a CNN algorithm, inspired by models like Alex Net, is created and trained using the pre-processed dataset. The CNN isused to identify and classify features based on different types of vitamin deficiencies, enabling an automated andaccurate assessment based on facial images

Moving Vehicle Number Plate Detection

Abstract: The ability to detect and recognize vehicle license plates is a crucial task in various applications such as traffic management, law enforcement, and parking systems. In this project, we propose a system for moving vehicle license plate detection using image and video processing techniques. The system employs a combination of computer vision algorithms and machine learning models to accurately locate and recognize license plates from moving vehicles in real-time. The input images or video frames are preprocesses to enhance the regions containing license plates and reduce noise. This preprocessing step may include operations such as resizing, grayscale conversion, noise reduction, and contrast enhancement. Next, object detection algorithms such as Haar cascades or deep learning-based techniques like YOLO (You Only Look Once) are utilized to detect candidate regions in the image/frame that potentially contain license plates. After candidate regions are identified, a series of image processing techniques such as morphological operations, contour detection, and character segmentation are employed to isolate and extract the license plate characters. Machine learning models like Support Vector Machines (SVM), Convolutional Neural Networks (CNNs) are then applied to recognize the characters on the license plate.

Botanic Shield: A Deep Learning Solution for Early Detection of Plant Disease

Abstract: Plant diseases threaten both food security and the botanical system of the environment which canlead to low- grade food quality and life style. Early detection of plants diseases is the key feature in plantproduction which increase the better growth of plant, results in best yield and better food quality andquantity. The plant condition can be determined byusing the photos of the plant which will be in the formof jpg using digital image processing and the current emerging technology Deep Learning. DeepLearning has made breakthroughs in the field of digital image processing, far superior to traditional methods. The Digital image processing process happens through convolution neural network (CNN) and computer vision techniques, the image recognition technology based on deep learning does not need to extractspecificfeatures, and only through iterative learning can find appropriate features, which can acquire global andcontextual features of images, and has strong robustness and higher recognition accuracy. By inputting a test image into the classification network, the network analyses the input image and returns a label that classifiesthe image. The added feature is thatit also suggeststhe required pesticides after the detection

ICC-BiFormer: A Deep-Learning Model for Near-Earth Asteroid Detection via Image Compression and Local Feature Extraction

Detecting near-Earth asteroids (NEAs) is crucial for research in solar system and planetary science. In recent year, deep-learning methods have almost dominated the task. Since NEAs represent only one-thousandth of the pixels in images, we proposed an ICC-BiFormer model that includes an image compression and contrast enhancement block and a BiFormer model to capture local features in input images, which is different from previous models based on Convolutional Neural Network (CNN). Furthermore, we utilize a larger input size of the model, which corresponds to the side length of the input image matrix, and design a cropping algorithm to prevent NEAs from being truncated and better divide NEAs and satellites. We apply our ICC-BiFormer model into a dataset of approximately 20,000 streak and 40,000 non-streak images to train a binary classification model. The ICC-BiFormer achieves 99.88% accuracy, which is superior to existing models. Focusing on local features has been proven effective in detecting NEAs.

A light-weight rectangular decomposition large kernel convolution network for deformable medical image registration

The performance and speed of medical image registration have been greatly boosted by advanced deep-learning based methods. However, most current methods are challenged by large deformations between input images, which necessitate a compromise in computational cost to enhance the model’s receptive field and its ability to model long-range spatial relationships for improving registration performance. In order to enhance the performance of registration for images with large deformations at a lower computational cost, in this paper, we propose a light-weight registration model with the ability to model large receptive fields and long-range spatial relationships, named LL-Net. The core components of LL-Net consist of a Rectangular Decomposition Large Kernel Attention (RD-LKA) layer and a Spatial and Channel Fusion Attention (SC-Fusion) layer. The RD-LKA layer utilizes anisotropic depth-wise large kernel convolutions to capture large receptive fields with an extremely low parameter count while modeling long-range spatial relationships. Moreover, the SC-Fusion layer enhances the model’s feature fusion capability and strengthens feature representations at critical locations. Our LL-Net exhibits state-of-the-art performance across multiple datasets. Specifically, it achieves a Dice score of 76.7% and an HD95 of 2.983 mm on the IXI dataset, and a Dice score of 87.8% and an HD95 of 1.042 mm on the OASIS dataset. Experimental results substantiate the efficacy of LL-Net in capturing large receptive fields and modeling long-range spatial relationships. The code for LL-Net is available at https://github.com/BoyOfChu/LL_Net.

Interactive Surgical Training in Neuroendoscopy: Real-Time Anatomical Feature Localization using Natural Language Expressions.

This study addresses challenges in surgical education, particularly in neuroendoscopy, where the demand for optimized workflow conflicts with the need for trainees' active participation in surgeries. To overcome these challenges, we propose a framework that accurately identifies anatomical structures within images guided by language descriptions, facilitating authentic and interactive learning experiences in neuroendoscopy. Utilizing the encoder-decoder architecture of a conventional transformer, our framework processes multimodal inputs (images and language descriptions) to identify and localize features in neuroendoscopic images. We curate a dataset from recorded endoscopic third ventriculostomy (ETV) procedures for training and evaluation. Utilizing evaluation metrics, including "R@n," "IoU= θ," "mIoU," and top-1 accuracy, we systematically benchmark our framework against state-of-the-art methodologies. The framework demonstrates excellent generalization, surpassing the compared methods with 93.67 % accuracy and 76.08 % mIoU on unseen data. It also exhibits better computational speed compared with other methods. Qualitative results affirms the framework's effectiveness in precise localization of referred anatomical features within neuroendoscopic images. The framework's adeptness at localizing anatomical features using language descriptions positions it as a valuable tool for integration into future interactive clinical learning systems, enhancing surgical training in neuroendoscopy. The exemplary performance reinforces the framework's potential in enhancing surgical education, leading to improved skills and outcomes for trainees in neuroendoscopy.

Comprehensive study on the development of an automatic helmet violator detection system (AHVDS) using advanced machine learning techniques

The number of motorcycle accidents has increased rapidly due to different causes. Helmet is a one of the major safety equipment that helps to reduce the fatal accidents even though many of the motorcyclists are not used that. Currently many researchers have focused on traffic violator detection but they are yet to identify the violated person details as it requires high resolution cameras and expensive sensors for number plate extraction. This research article is focused on comprehensive study on the development of an automated helmet violation detection with number plate extraction in real time. This study divides the dataset into rider with helmet, rider without helmet, passenger with helmet and passenger without helmet classes, and four training model was created to detect helmet in rider and passengers. The proposed model was constructed in three stages to attain high accuracy with a vast amount of training dataset. In the first stage, the helmet was detected in the input image using the deep learning object-detection model .In the second stage, if the helmet identification confirmed in the input image then the entire motorcyclist image is segmented based on object segmentation model. In the third stage, number plate training model is deployed into the same object detection and object segmentation model to identify and segment the license plates in the motorcyclist image. This study primarily incorporates the Mask Region based Convolution Neural Networks (Mask R-CNN) for object detection and segmentation Further, it incorporates the three different deep neural networks like Dense block Network (DenseNet-121), Residual Network (ResNet-101) and Inception Residual Network architecture V2layers (Inception Res Net V2) to create accurate helmet violator detections with more extensive information. The experimental results indicates that this comprehensive helmet violator detection study improves the helmet detection accuracy by 6.2 %.In addition, the above three comprehensive proposed models are evaluated under Wilcoxon rank test for better sensitive information. Further, the less object detection loss (2 %) and significant computational time variation (69 %) indicates the performance of the comprehensive helmet violator detection system was good compared to existing study.

A Retinex-based network for image enhancement in low-light environments.

Most of the existing low-light image enhancement methods suffer from the problems of detail loss, color distortion and excessive noise. To address the above-mentioned issues, this paper proposes a neural network-based low-light image enhancement network. The network is divided into three parts: decomposition network, reflection component denoising network, and illumination component enhancement network. In the decomposition network, the input image is decomposed into a reflection image and an illumination image. In the reflection component denoising network, the Unet3+ network improved by fusion CA attention is adopted to denoise the reflection image. In the illumination component enhancement network, the adaptive mapping curve is adopted to enhance the illumination image iteratively. Finally, the processed illumination and reflection images are fused based on Retinex theory to obtain the final enhanced image. The experimental results show that the proposed network achieves excellent visual effects in subjective evaluation. Additionally, it shows a significant improvement in objective evaluation metrics, including PSNR, SSIM, NIQE, and so on, when compared to the results in several public datasets.

Fuzzy Contrast Enhancement Techniques Using Rule-Based System and Intensification Operator

Contrast enhancement is a crucial step in digital image processing to ensure the production of high-quality images. This paper presents two distinct fuzzy techniques designed to address the nuanced concept of contrast. that utilize rule-based system and intensification operator, respectively, to handle the inherent vagueness associated with the concept of contrast. The fuzzy rule-based system calculates the intensity value of the output image based on the contrast measure (standard deviation) of the input image, thereby enabling effective contrast enhancement for low contrast images. Meanwhile, the fuzzy intensification operator aims to accentuate the differences in intensity levels within the image, thereby enhancing the contrast between various features and details. The experimental results show better image contrast is obtained using both methods. However, fuzzy rule-based approach shows more images with better quality compared to the intensification operator approach. The performance of these techniques is evaluated both visually and quantitatively.

ER‐Mapping: An extrinsic robust coloured mapping system using residual evaluation and selection

AbstractThe colour‐enhanced point cloud map is increasingly being employed in fields such as robotics, 3D reconstruction and virtual reality. The authors propose ER‐Mapping (Extrinsic Robust coloured Mapping system using residual evaluation and selection). ER‐Mapping consists of two components: the simultaneous localisation and mapping (SLAM) subsystem and the colouring subsystem. The SLAM subsystem reconstructs the geometric structure, where it employs a dynamic threshold‐based residual selection in LiDAR‐inertial odometry to improve mapping accuracy. On the other hand, the colouring subsystem focuses on recovering texture information from input images and innovatively utilises 3D–2D feature selection and optimisation methods, eliminating the need for strict hardware time synchronisation and highly accurate extrinsic parameters. Experiments were conducted in both indoor and outdoor environments. The results demonstrate that our system can enhance accuracy, reduce computational costs and achieve extrinsic robustness.

Hybrid Classifier for Crowd Anomaly Detection with Bernoulli Map Evaluation

Automatically detecting unusual behavior in a crowded environment greatly improves public safety. Unusual behaviors are those that depend on the rules established in the environment under consideration and cannot be properly described. This paper proposes a new deep feature-based crowd anomaly detection method. Priorly, the input image is preprocessed using the Weiner filtering method. Subsequently, AlexNet, VGGnet, and ResNet-based deep features are extracted. During this process, all three models were optimally tuned. For optimization, a new hybrid optimization method called Hybrid COOT and Bald Eagle with Bernoulli Map Evaluation (HCBEBME) is introduced in this work. This improves the performance of extracting features from the input. Finally, based on the proposed feature set, anomalies are detected by the hybrid detection model that combines LSTM and Bi-GRU models, respectively. Finally, the performance of the proposed model is validated over the conventional models. The detection accuracy of the suggested approach is 96.59%, whereas the minimal accuracy scores for the other methods BRCASO, GNNN, CNN-BILSTM, LSTM, BIGRU, BILSTM, CNN, and RNN are 93.63%, 79.16%, 87.57%, 73.85%, 70.59%, 77.08%, 81.44%, and 84.66% respectively.

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.

Advancing Hyperspectral and Multispectral Image Fusion: An Information-Aware Transformer-Based Unfolding Network.

In hyperspectral image (HSI) processing, the fusion of the high-resolution multispectral image (HR-MSI) and the low-resolution HSI (LR-HSI) on the same scene, known as MSI-HSI fusion, is a crucial step in obtaining the desired high-resolution HSI (HR-HSI). With the powerful representation ability, convolutional neural network (CNN)-based deep unfolding methods have demonstrated promising performances. However, limited receptive fields of CNN often lead to inaccurate long-range spatial features, and inherent input and output images for each stage in unfolding networks restrict the feature transmission, thus limiting the overall performance. To this end, we propose a novel and efficient information-aware transformer-based unfolding network (ITU-Net) to model the long-range dependencies and transfer more information across the stages. Specifically, we employ a customized transformer block to learn representations from both the spatial and frequency domains as well as avoid the quadratic complexity with respect to the input length. For spatial feature extractions, we develop an information transfer guided linearized attention (ITLA), which transmits high-throughput information between adjacent stages and extracts contextual features along the spatial dimension in linear complexity. Moreover, we introduce frequency domain learning in the feedforward network (FFN) to capture token variations of the image and narrow the frequency gap. Via integrating our proposed transformer blocks with the unfolding framework, our ITU-Net achieves state-of-the-art (SOTA) performance on both synthetic and real hyperspectral datasets.

Hot rolled steel surface defect detection and classification using an automatic ensemble approach

This study introduces an ensemble-based Deep Neural Network (DNN) model for detecting defects on steel surfaces. The method suggested in this study classifies steel surface conditions into six possible fault categories, namely, crazing, inclusion, rolled in, pitted surface, scratches, and patches. The images undergo preprocessing and extraction of features in spatial and frequency domains using image segmentation techniques such as grey level difference method (GLDM), fast Fourier Transform (FFT), grey level co-occurrence matrix (GLCM), texture analysis and discrete wavelet transform (DWT). The ensembling of image features into a fused feature pool is carried out after the preprocessing of input images that are provided as input to a light-weight neural network model for training and testing. The performance of the model is comprehensively evaluated via an ablation study both before and after ensembling. In addition, the model capability is effectively analyzed using receiver operating characteristics (ROC) curve, confusion matrix from which classification accuracy of the model could be obtained and other parameters including precision and f1-score. It was observed that the proposed deep learning network presents phenomenally high accuracy of 99.72% for detection and classification of steel surface faults. This result was found to be superior when compared with the performance of the same neural network over each feature type individually. This study also compares the classification results of the model built based on the ensembled feature set with the results of various other classification approaches available in literature. The ensemble-based model could potentially be integrated into existing inspection systems for real-time, efficient and robust condition monitoring of steel surfaces.