Earticle

It is important to understand the exact habitat distribution of endangered species because of their decreasing numbers. In this study, we build a system with a deep learning module that collects the image data of endangered animals, processes the data, and saves the data automatically. The system provides a more efficient way than human effort for classifying images and addresses two problems faced in previous studies. First, specious answers were suggested in those studies because the probability distributions of answer candidates were calculated even if the actual answer did not exist within the group. Second, when there were more than two entities in an image, only a single entity was focused on. We applied an object detection algorithm (YOLO) to resolve these problems. Our system has an average precision of 86.79%, a mean recall rate of 93.23%, and a processing speed of 13 frames per second.

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

Image restoration plays a vital role in computer vision by enhancing degraded images. Deep learning techniques, including convolutional neural networks and generative adversarial networks, have significantly advanced this field. The key tasks include deblurring, inpainting, denoising, and super-resolution. This study reviews current restoration methods and compares their strengths and limitations across various applications. It identifies areas for improvement and recommends suitable techniques for specific tasks. The applications span healthcare, underwater imaging, and the preservation of old photographs. Enhanced restoration enables better interpretation, storage, and usability of visual data across diverse domains.

The aim of this study is to investigate the automatic recognition and analysis of Jeju marine-life images using artificial intelligence (AI) technology. The dataset of marine-life images was prepared using tools such as Python, TensorFlow, and Google Colab (Google Colaboratory). We also developed models by training deep learning AI in image recognition to automatically recognize the species found in these images and extract their associated information, such as taxonomy, characteristics, and distribution. This study is innovative in that it uses deep learning technology combined with imagerecognition technology for marine biodiversity research. In addition, these results will lead to the development of the marine-life industry in Jeju by supporting marine environment monitoring and marine resource conservation. Furthermore, this study is anticipated to contribute to academic advancement, specifically in the study of marine species diversity.

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

An image fusion method is proposed on the basis of depth model segmentation to overcome the shortcomings of noise interference and artifacts caused by infrared and visible image fusion. Firstly, the deep Boltzmann machine is used to perform the priori learning of infrared and visible target and background contour, and the depth segmentation model of the contour is constructed. The Split Bregman iterative algorithm is employed to gain the optimal energy segmentation of infrared and visible image contours. Then, the nonsubsampled contourlet transform (NSCT) transform is taken to decompose the source image, and the corresponding rules are used to integrate the coefficients in the light of the segmented background contour. Finally, the NSCT inverse transform is used to reconstruct the fused image. The simulation results of MATLAB indicates that the proposed algorithm can obtain the fusion result of both target and background contours effectively, with a high contrast and noise suppression in subjective evaluation as well as great merits in objective quantitative indicators.

Artificial intelligence, especially deep learning technology, is penetrating the majority of research areas, including the field of bioinformatics. However, deep learning has some limitations, such as the complexity of parameter tuning, architecture design, and so forth. In this study, we analyze these issues and challenges in regards to its applications in bioinformatics, particularly genomic analysis and medical image analytics, and give the corresponding approaches and solutions. Although these solutions are mostly rule of thumb, they can effectively handle the issues connected to training learning machines. As such, we explore the tendency of deep learning technology by examining several directions, such as automation, scalability, individuality, mobility, integration, and intelligence warehousing.

Radio propagation modeling and path loss prediction have been the subject of many machine learning-based estimation attempts. Our current work uses deep learning for the task in question, trying to exploit the potential of applying convolutional neural networks in order to perform predictions based on images. A comparison between data-driven and image-driven estimations has been carried out in order to assess the proposed method. The results show that an appropriately chosen image can, per se, be treated as an alternative to a vector of tabular data and produce reliable predictions. The effect of the image’s size has also been examined.

Accurate classification of cloud images is a challenging task. Almost all the existing methods rely on hand-crafted feature extraction. Their limitation is low discriminative power. In the recent years, deep learning with convolution neural networks (CNNs), which can auto extract features, has achieved promising results in many computer vision and image understanding fields. However, deep learning approaches usually need large datasets. This paper proposes a deep learning approach for classification of cloud image patches on small datasets. First, we design a suitable deep learning model for small datasets using a CNN, and then we apply data augmentation and dropout regularization techniques to increase the generalization of the model. The experiments for the proposed approach were performed on SWIMCAT small dataset with k-fold cross-validation. The experimental results demonstrated perfect classification accuracy for most classes on every fold, and confirmed both the high accuracy and the robustness of the proposed model.

Considering factors such as illumination, camera quality variations, and background-specific variations, identifying a face using a smartphone-based facial image capture application is challenging. Face Image Quality Assessment refers to the process of taking a face image as input and producing some form of "quality" estimate as an output. Typically, quality assessment techniques use deep learning methods to categorize images. The models used in deep learning are shown as black boxes. This raises the question of the trustworthiness of the models. Several explainability techniques have gained importance in building this trust. Explainability techniques provide visual evidence of the active regions within an image on which the deep learning model makes a prediction. Here, we developed a technique for reliable prediction of facial images before medical analysis and security operations. A combination of gradient-weighted class activation mapping and local interpretable model-agnostic explanations were used to explain the model. This approach has been implemented in the preselection of facial images for skin feature extraction, which is important in critical medical science applications. We demonstrate that the use of combined explanations provides better visual explanations for the model, where both the saliency map and perturbation-based explainability techniques verify predictions.

본 연구에서는 지방량을 측정하는 Fat-amount 검사에서 FBP(Filtered back projection), IR(Iterative Reconstruction)과 함께 DLIR 기법을 이용하여 영상을 재구성한 후 HU(Hounsfield unit), VFA(Visceral Fat Area), SFA(Subcutaneous Fat Area), V/S(Visceral-Subcutaneous Fat Ratio), SD(Standard Deviation)을 비교하여 DLIR의 유용성을 평가했다. 지방의 정량적 측정에서는 FBP, ASIR-V와 DLIR이 통계적으로 유의한 차이 없는 결과를 도출할 수 있었고, 오히려 SD은 DLIR에서 낮아져 Fat의 정량적 측정은 동일하면서, 영상의 질을 높일 수 있는 임상적 으로 충분히 가치 있는 기법이라고 보여진다. 타 검사에 비해 큰 단점으로 지목되고 있는 방사선량을 줄이는 데에 있어 충분한 가지가 있다고 사료된다.

In this study, in ‘CT Fat-amount’ to measure the amount of fat, the image was reconstructed using the DLIR technique along with FBP (Filtered back projection) and IR (Iterative Reconstruction), and then HU (Hounsfield unit), VFA (Visceral Fat Area), and SFA The usefulness of DLIR was evaluated by comparing (Subcutaneous Fat Area), V/S (Visceral-Subcutaneous Fat Ratio), and SD (Standard Deviation). In the quantitative measurement of fat, FBP, ASIR-V, and DLIR were able to produce results with no statistically significant difference. Rather, the SD was lower in DLIR, so the quantitative measurement of fat was the same, but the quality of the image could be improved clinically. It appears to be a worthwhile technique. It is believed that there are sufficient ways to reduce the radiation dose, which is considered a major disadvantage compared to other tests.

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

Background: Magnetic resonance (MR) image guided radiation therapy system, enables real time MR guided radiotherapy (RT) without additional radiation exposure to patients during treatment. However, MR image lacks electron density information required for dose calculation. Image fusion algorithm with deformable registration between MR and computed tomography (CT) was developed to solve this issue. However, delivered dose may be different due to volumetric changes during image registration process. In this respect, synthetic CT generated from the MR image would provide more accurate information required for the real time RT. Materials and Methods: We analyzed 1,209 MR images from 16 patients who underwent MR guided RT. Structures were divided into five tissue types, air, lung, fat, soft tissue and bone, according to the Hounsfield unit of deformed CT. Using the deep learning model (U-NET model), synthetic CT images were generated from the MR images acquired during RT. This synthetic CT images were compared to deformed CT generated using the deformable registration. Pixelto- pixel match was conducted to compare the synthetic and deformed CT images. Results and Discussion: In two test image sets, average pixel match rate per section was more than 70% (67.9 to 80.3% and 60.1 to 79%; synthetic CT pixel/deformed planning CT pixel) and the average pixel match rate in the entire patient image set was 69.8%. Conclusion: The synthetic CT generated from the MR images were comparable to deformed CT, suggesting possible use for real time RT. Deep learning model may further improve match rate of synthetic CT with larger MR imaging data.

We developed a deep learning-based algorithm with plant fruit images to predict the quantitative traits, fruit size, and weight. Highbush blueberry was selected as a model plant because of its commercial importance. Mask R-CNN was adopted for a deep learning guidance model to predict fruits' width, length, and weight. The deep learning algorithm had a high performance on object detection and image segmentation with more than 90% accuracy and detection rate.

Planthopper is a major problem pest of agricultural crops and rice, feeding mainly on the leaves and stems of crops and causing devastating damage to farmers in South Korea. Planthoppers reduce nutrients in the body of crops and cause crop diseases by destroying tissue or transmitting viruses, so accurate detection and diagnosis is essential to minimize the damage. With the development of artificial intelligence in recent years, deep learning has been widely used to diagnose the pests. Most of the pest diagnosis research and programs use approaches based on object detection and image classification. However, traditional planthopper detection models may misidentify other pests as planthoppers, which can reduce user confidence in the diagnostic model. To address this misrecognition problem, this study investigates a deep learning-based planthopper Image detection and discrimination model for detecting and classifying the planthopper images. The proposed model combines the Faster RCNN object detection model and the Resnet50 classification model to automatically detect planthoppers among other pests in aerial entomology net images. The performance measurements showed that the benchmark model using the Faster RCNN algorithm achieved a high Recall of 91.23%, but a relatively low Precision of 24.34%. On the other hand, the model proposed in this study has a high recall of 96.22% and a high precision of 96.73%, proving that it can detect planthoppers well.

In this study, we propose a deep learning-based forest road recognition technology and integrate it into an autonomous steering and speed control system for a forestry forwarder. We trained a YOLOv8 segmentation model on 640×480 pixel images collected from straight, curved, and occluded sections of forestry roads, achieving a precision of 0.997, a recall of 0.994, an F1 score of 0.995, and an average precision of 0.994. We developed a centerline extraction algorithm that calculates the lateral offset between the vehicle center and the detected road centerline using the segmented mask. This offset is then input into an electronic steering lever control system, which replaces the existing mechanical steering lever to enable rapid response. In field experiments conducted on actual forest roads, the maximum average path tracking error was 0.534 m over three trials, confirming that the vision-based approach can reliably guide the forwarder under various lighting conditions, shadows, and roadside structures. This method is expected to overcome the limitations of GNSS/INS-based autonomous driving systems, as it operates solely with cameras and single-board hardware. The research results suggest that deep learning-based image processing provides a solid foundation for fully autonomous forestry operations and has the potential to improve the productivity and safety of timber transport operations.

본 연구에서는 배터리 파쇄 공정 산물에 대해 영상 인식 기반 분석 기법을 적용하여, 복합 폐기물의 재활용 효율 향상을 도모하고자 하였다. YOLOv8을 기반으로 재질 인식을 위한 학습 모델을 구축하였으며, Canny edge 기반 윤곽선 검출 및 기준선 보정 기법을 통해 입자의 면적을 정량화하였다. 약 7,000개의 이미지를 학습 데이터로 활용하였으며, 데이터 증강 및 보정 알고리즘을 이용하여 mAP 0.971의높은 객체 인식 정확도를 달성하였다. 입자 면적 정보를 기반으로 단위 면적당 질량(g/mm2)을 통해 입자별 질량을 추정하였으며, 이를 통해 영상 기반 회수율 및 순도를 계산하였다. 예측값은 실험을 통해 얻은 실측값과 비교되었으며, 회수율은 모든 재질에서 95% 이상, 순도는 약 90% 수준의 정합률을 보여 영상 기반 분석의 신뢰성을 입증하였다. 영상인식 기반의 재질 인식 및 입자 특성 분석을 통한 선별 회수율 및 순도 계산에 대한 신뢰도를 확보하였다. 연구는 영상 기반 분석이 기존 장비 대비 신속하고 효율적임을 보여주며, 향후 실시간 품질모니터링 및 공정 최적화 시스템으로의 확장 가능성을 제시한다.

In this study, an image recognition-based analysis method was applied to by-products generated from the battery crushing process, aiming to improve the recycling efficiency of complex waste streams. A deep learning model for material classification was developed based on YOLOv8, and particle areas were quantified using Canny edge-based contour detection along with baseline calibration techniques. Approximately 7,000 images were utilized for training, and data augmentation and correction algorithms enabled the model to achieve a high object detection accuracy with an mAP of 0.971. Based on the quantified particle area and the calibrated mass per unit area (g/mm2), the mass of each particle was estimated. These values were used to calculate recovery and grade, and the predicted results were compared with experimentally measured data. Recovery exceeded 95% across all material types, and the correspondence rate for grade reached approximately 90%, confirming the reliability of the image-based analysis. The study demonstrates that material classification and particle property analysis based on image processing enable accurate evaluation of separation recovery and product grade. In addition, the method shows potential for rapid and efficient assessment compared to conventional equipment and can be further expanded into real-time quality monitoring and process optimization systems.