• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3917-3941
• /
• 2019

The recent interest in artificial intelligence and machine learning has partly contributed to an interest in the use of such approaches for hyperspectral remote sensing (HRS) imagery classification, as evidenced by the increasing number of deep framework with deep convolutional neural networks (CNN) structures proposed in the literature. In these approaches, the assumption of obtaining high quality deep features by using CNN is not always easy and efficient because of the complex data distribution and the limited sample size. In this paper, conventional handcrafted learning-based multi features based on expert knowledge are introduced as the input of a special designed CNN to improve the pixel description and classification performance of HRS imagery. The introduction of these handcrafted features can reduce the complexity of the original HRS data and reduce the sample requirements by eliminating redundant information and improving the starting point of deep feature training. It also provides some concise and effective features that are not readily available from direct training with CNN. Evaluations using three public HRS datasets demonstrate the utility of our proposed method in HRS classification.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.2
• /
• pp.93-100
• /
• 2021

Purpose: (1) To evaluate the trabecular pattern at the femoral attachment of the posterior cruciate ligament (PCL) in patients with a PCL injury; (2) to analyze bone microarchitecture by applying gray level co-occurrence matrix (GLCM)-based texture analysis; and (3) to determine if there is a significant relationship between bone microarchitecture and posterior instability. Materials and Methods: The study included 96 patients with PCL tears. Trabecular patterns were evaluated on T2-weighted MRI qualitatively, and were evaluated by GLCM texture analysis quantitatively. The grades of posterior drawer test (PDT) and the degrees of posterior displacement on stress radiographs were recorded. The 96 patients were classified into two groups: acute and chronic injury. And 27 patients with no PCL injury were enrolled for control. Pearson's correlation coefficient and one-way ANOVA with Bonferroni test were conducted for statistical analyses. This protocol was approved by the Institutional Review Board. Results: A thick and anisotropic trabecular bone pattern was apparent in normal or acute injury (n = 57/61;93.4%), but was not prominent in chronic injury and posterior instability (n = 31/35;88.6%). Grades of PDT and degrees of posterior displacement on stress radiograph were not correlated with texture parameters. However, the texture analysis parameters of chronic injury were significantly different from those of acute injury and control groups (P < 0.05). Conclusion: The trabecular pattern and texture analysis parameters are useful in predicting posterior instability in patients with PCL injury. Evaluation of the bone microarchitecture resulting from altered biomechanics could advance the understanding of PCL function and improve the detection of PCL injury.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1462-1468
• /
• 2022

Among the data used for the diagnosis of calf disease, feces play an important role in disease diagnosis. In the image of calf feces, the health status can be known by the shape, color, and texture. For the fecal image that can identify the health status, data of 207 normal calves and 158 calves with diarrhea were pre-processed according to fecal status and used. In this paper, images of fecal variables are detected among the collected calf data and images are trained by applying GLCM-CNN, which combines the properties of CNN and GLCM, on a dataset containing disease symptoms using convolutional network technology. There was a significant difference between CNN's 89.9% accuracy and GLCM-CNN, which showed 91.7% accuracy, and GLCM-CNN showed a high accuracy of 1.8%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.956-962
• /
• 2022

Diffuse thyroid disease has ambiguous diagnostic criteria and many errors occur according to the subjective diagnosis of skilled practitioners. If image processing technology is applied to ultrasound images, quantitative data is extracted, and applied to a computer auxiliary diagnostic system, more accurate and political diagnosis is possible. In this paper, 19 parameters were extracted by applying the Gray level co-occurrence matrix (GLCM) algorithm to ultrasound images classified as normal, mild, and moderate in patients with thyroid disease. Using these parameters, an artificial neural network (ANN) was applied to analyze diffuse thyroid ultrasound images. The final classification rate using ANN was 96.9%. Using the results of the study, it is expected that errors caused by visual reading in the diagnosis of thyroid diseases can be reduced and used as a secondary means of diagnosing diffuse thyroid diseases.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• Korean Journal of Materials Research
• /
• v.8 no.7
• /
• pp.648-652
• /
• 1998

TIG remelting was performed to harden the surface of automobile earn shaft. Multipass remelting was conducted in longitudinal direction under argon gas atmosphere. The microstructure of as-east earn shaft was gray iron which consisted of flake graphite and pearlitic matrix. The remelted area had microstructue of both fine pearlite and ledeburite structure that consisted of globular austenite and $Fe_3C$. Hardness for as-cast earn shaft had HRc 25~28, however it increased at remelted area to HRc 53~55. Black line was found at heat affected zone next to the fusion line, that is remelt area of previous pass, during multipass remelting. Black line was identified as graphite, which was transformed from $Fe_3C$. in the ledeburite structure. It is observed that all graphites were nucleated at $Fe_3C$. and matrix interface. High density energy laser remelting process was also applied to verify whether black line could be eliminated. However, black line was still existed as observed in TIG remelting process. Regraphitization was simulated on the ledeburitic structure specimen using Gleeble 1500 with conditions of 1100 and 100$0^{\circ}C$ for 0.5, I, 3, 5 and 1Osee. From the fact that graphite was formed even at the simulation condition of 100$0^{\circ}C$ for 0.5sec, it is seen that regraphitization is an inevitable phenomenon generated whatever processes used during multipass overlap remelting.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.378-391
• /
• 2010

In this paper, it is tested that an individual is able to be identified with finger face images and the results are presented. Special operators, FFG(Facet Function Gradient) masks by which the gradient of a facet function fit on a gray levels of image patches can be computed are used and a new procedure named F-algorithm is introduced to match the finger face images. The finger face image is divided into the equal subregions and each subregions are divided into equal patches with this algorithm. The FFG masks are used for convolution operation over each patch to produce scalar values. These values from a feature matrix, and the identity of fingers is determined by a norm of the elements of the feature matrices. The distribution of the norms shows conspicuous differences between the pairs of hand images of the same persons and the pairs of the different persons. This is a result to prove the ability of discrimination with the finger face image. An identification rate of 95.0% is obtained as a result of the test in which 500 hand images taken from 100 persons are processed through F-algorithm. It is affirmed that the finger face reveals to be such a good biometrics as other hand parts owing to the ability of discrimination and the identification rate.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.8
• /
• pp.579-588
• /
• 2013

This paper proposes an effective watermarking approach for copyright protection of fire video images. The proposed watermarking approach efficiently utilizes the inherent characteristics of fire data with respect to color and texture by using a gray level co-occurrence matrix (GLCM) and fuzzy c-means (FCM) clustering. GLCM is used to generate a texture feature dataset by computing energy and homogeneity properties for each candidate fire image block. FCM is used to segment color of the fire image and to select fire texture blocks for embedding watermarks. Each selected block is then decomposed into a one-level wavelet structure with four subbands [LL, LH, HL, HH] using a discrete wavelet transform (DWT), and LH subband coefficients with a gain factor are selected for embedding watermark, where the visibility of the image does not affect. Experimental results show that the proposed watermarking approach achieves about 48 dB of high peak-signal-to-noise ratio (PSNR) and 1.6 to 2.0 of low M-singular value decomposition (M-SVD) values. In addition, the proposed approach outperforms conventional image watermarking approach in terms of normalized correlation (NC) values against several image processing attacks including noise addition, filtering, cropping, and JPEG compression.

• Korean Journal of Heritage: History & Science
• /
• v.44 no.3
• /
• pp.78-91
• /
• 2011

The Usuki Stone Buddha Statues in Japan are carved on mainly dark gray welded lapilli tuff accompanied by lenticular fiamme. This rock is composed of matrix which contains feldspar and opaque minerals with some phenocrysts of quartz and feldspar. The matrix is slight to highly welded. The statues have been weathered and weakened by salt and freezing of water. To enhance the mechanical properties of the rock, consolidants and water repellents were applied. The absorption ratio of the rock was highly decreased after the treatment of the water repellents, the consolidant OH 100, as well. Ultrasonic velocity revealed similarly higher values in the treated rock by KSE 300 and OH 100, compared to non-treated rock. KSE 300, especially, highly increased the Equotip surface hardness. All studied consolidants and water repellents were found to change the original color of the stone. SNL, specifically, resulted the significant change in color. In addition, KSE 300 were observed to improve resistance to weathering such as microcrack and fracture through freezing-thawing test after treatment.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.989-1006
• /
• 2020

Building change monitoring based on building detection is one of the most important fields in terms of monitoring artificial structures using high-resolution multi-temporal images such as CAS500-1 and 2, which are scheduled to be launched. However, not only the various shapes and sizes of buildings located on the surface of the Earth, but also the shadows or trees around them make it difficult to detect the buildings accurately. Also, a large number of misdetection are caused by relief displacement according to the azimuth and elevation angles of the platform. In this study, object-based building detection was performed using the azimuth angle of the Sun and the corresponding main direction of shadows to improve the results of building change detection. After that, the platform's azimuth and elevation angles were used to detect changed buildings. The object-based segmentation was performed on a high-resolution imagery, and then shadow objects were classified through the shadow intensity, and feature information such as rectangular fit, Gray-Level Co-occurrence Matrix (GLCM) homogeneity and area of each object were calculated for building candidate detection. Then, the final buildings were detected using the direction and distance relationship between the center of building candidate object and its shadow according to the azimuth angle of the Sun. A total of three methods were proposed for the building change detection between building objects detected in each image: simple overlay between objects, comparison of the object sizes according to the elevation angle of the platform, and consideration of direction between objects according to the azimuth angle of the platform. In this study, residential area was selected as study area using high-resolution imagery acquired from KOMPSAT-3 and Unmanned Aerial Vehicle (UAV). Experimental results have shown that F1-scores of building detection results detected using feature information were 0.488 and 0.696 respectively in KOMPSAT-3 image and UAV image, whereas F1-scores of building detection results considering shadows were 0.876 and 0.867, respectively, indicating that the accuracy of building detection method considering shadows is higher. Also among the three proposed building change detection methods, the F1-score of the consideration of direction between objects according to the azimuth angles was the highest at 0.891.