• Title/Summary/Keyword: Image Preprocessing

Search Result 707, Processing Time 0.033 seconds

Real-time semantic segmentation of gastric intestinal metaplasia using a deep learning approach

  • Vitchaya Siripoppohn;Rapat Pittayanon;Kasenee Tiankanon;Natee Faknak;Anapat Sanpavat;Naruemon Klaikaew;Peerapon Vateekul;Rungsun Rerknimitr
    • Clinical Endoscopy
    • /
    • v.55 no.3
    • /
    • pp.390-400
    • /
    • 2022
  • Background/Aims: Previous artificial intelligence (AI) models attempting to segment gastric intestinal metaplasia (GIM) areas have failed to be deployed in real-time endoscopy due to their slow inference speeds. Here, we propose a new GIM segmentation AI model with inference speeds faster than 25 frames per second that maintains a high level of accuracy. Methods: Investigators from Chulalongkorn University obtained 802 histological-proven GIM images for AI model training. Four strategies were proposed to improve the model accuracy. First, transfer learning was employed to the public colon datasets. Second, an image preprocessing technique contrast-limited adaptive histogram equalization was employed to produce clearer GIM areas. Third, data augmentation was applied for a more robust model. Lastly, the bilateral segmentation network model was applied to segment GIM areas in real time. The results were analyzed using different validity values. Results: From the internal test, our AI model achieved an inference speed of 31.53 frames per second. GIM detection showed sensitivity, specificity, positive predictive, negative predictive, accuracy, and mean intersection over union in GIM segmentation values of 93%, 80%, 82%, 92%, 87%, and 57%, respectively. Conclusions: The bilateral segmentation network combined with transfer learning, contrast-limited adaptive histogram equalization, and data augmentation can provide high sensitivity and good accuracy for GIM detection and segmentation.

Development of an Automated ESG Document Review System using Ensemble-Based OCR and RAG Technologies

  • Eun-Sil Choi
    • Journal of the Korea Society of Computer and Information
    • /
    • v.29 no.9
    • /
    • pp.25-37
    • /
    • 2024
  • This study proposes a novel automation system that integrates Optical Character Recognition (OCR) and Retrieval-Augmented Generation (RAG) technologies to enhance the efficiency of the ESG (Environmental, Social, and Governance) document review process. The proposed system improves text recognition accuracy by applying an ensemble model-based image preprocessing algorithm and hybrid information extraction models in the OCR process. Additionally, the RAG pipeline optimizes information retrieval and answer generation reliability through the implementation of layout analysis algorithms, re-ranking algorithms, and ensemble retrievers. The system's performance was evaluated using certificate images from online portals and corporate internal regulations obtained from various sources, such as the company's websites. The results demonstrated an accuracy of 93.8% for certification reviews and 92.2% for company regulations reviews, indicating that the proposed system effectively supports human evaluators in the ESG assessment process.

Finite Element Method Modeling for Individual Malocclusions: Development and Application of the Basic Algorithm (유한요소법을 이용한 환자별 교정시스템 구축의 기초 알고리즘 개발과 적용)

  • Shin, Jung-Woog;Nahm, Dong-Seok;Kim, Tae-Woo;Lee, Sung Jae
    • The korean journal of orthodontics
    • /
    • v.27 no.5 s.64
    • /
    • pp.815-824
    • /
    • 1997
  • The purpose of this study is to develop the basic algorithm for the finite element method modeling of individual malocclusions. Usually, a great deal of time is spent in preprocessing. To reduce the time required, we developed a standardized procedure for measuring the position of each tooth and a program to automatically preprocess. The following procedures were carried to complete this study. 1. Twenty-eight teeth morphologies were constructed three-dimensionally for the finite element analysis and saved as separate files. 2. Standard brackets were attached so that the FA points coincide with the center of the brackets. 3. The study model of a patient was made. 4. Using the study model, the crown inclination, angulation, and the vertical distance from the tip of a tooth was measured by using specially designed tools. 5. The arch form was determined from a picture of the model with an image processing technique. 6. The measured data were input as a rotational matrix. 7. The program provides an output file containing the necessary information about the three-dimensional position of teeth, which is applicable to several finite element programs commonly used. The program for a basic algorithm was made with Turbo-C and the subsequent outfile was applied to ANSYS. This standardized model measuring procedure and the program reduce the time required, especially for preprocessing and can be applied to other malocclusions easily.

  • PDF

Study of Prediction Model Improvement for Apple Soluble Solids Content Using a Ground-based Hyperspectral Scanner (지상용 초분광 스캐너를 활용한 사과의 당도예측 모델의 성능향상을 위한 연구)

  • Song, Ahram;Jeon, Woohyun;Kim, Yongil
    • Korean Journal of Remote Sensing
    • /
    • v.33 no.5_1
    • /
    • pp.559-570
    • /
    • 2017
  • A partial least squares regression (PLSR) model was developed to map the internal soluble solids content (SSC) of apples using a ground-based hyperspectral scanner that could simultaneously acquire outdoor data and capture images of large quantities of apples. We evaluated the applicability of various preprocessing techniques to construct an optimal prediction model and calculated the optimal band through a variable importance in projection (VIP)score. From the 515 bands of hyperspectral images extracted at wavelengths of 360-1019 nm, 70 reflectance spectra of apples were extracted, and the SSC ($^{\circ}Brix$) was measured using a digital photometer. The optimal prediction model wasselected considering the root-mean-square error of cross-validation (RMSECV), root-mean-square error of prediction (RMSEP) and coefficient of determination of prediction $r_p^2$. As a result, multiplicative scatter correction (MSC)-based preprocessing methods were better than others. For example, when a combination of MSC and standard normal variate (SNV) was used, RMSECV and RMSEP were the lowest at 0.8551 and 0.8561 and $r_c^2$ and $r_p^2$ were the highest at 0.8533 and 0.6546; wavelength ranges of 360-380, 546-690, 760, 915, 931-939, 942, 953, 971, 978, 981, 988, and 992-1019 nm were most influential for SSC determination. The PLSR model with the spectral value of the corresponding region confirmed that the RMSEP decreased to 0.6841 and $r_p^2$ increased to 0.7795 as compared to the values of the entire wavelength band. In this study, we confirmed the feasibility of using a hyperspectral scanner image obtained from outdoors for the SSC measurement of apples. These results indicate that the application of field data and sensors could possibly expand in the future.

Fast Detection of Finger-vein Region for Finger-vein Recognition (지정맥 인식을 위한 고속 지정맥 영역 추출 방법)

  • Kim, Sung-Min;Park, Kang-Roung;Park, Dong-Kwon;Won, Chee-Sun
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.46 no.1
    • /
    • pp.23-31
    • /
    • 2009
  • Recently, biometric techniques such as face recognition, finger-print recognition and iris recognition have been widely applied for various applications including door access control, finance security and electric passport. This paper presents the method of using finger-vein pattern for the personal identification. In general, when the finger-vein image is acquired from the camera, various conditions such as the penetrating amount of the infrared light and the camera noise make the segmentation of the vein from the background difficult. This in turn affects the system performance of personal identification. To solve this problem, we propose the novel and fast method for extracting the finger-vein region. The proposed method has two advantages compared to the previous methods. One is that we adopt a locally adaptive thresholding method for the binarization of acquired finger-vein image. Another advantage is that the simple morphological opening and closing are used to remove the segmentation noise to finally obtain the finger-vein region from the skeletonization. Experimental results showed that our proposed method could quickly and exactly extract the finger-vein region without using various kinds of time-consuming filters for preprocessing.

INVESTIGATION OF BAIKDU-SAN VOLCANO WITH SPACE-BORNE SAR SYSTEM

  • Kim, Duk-Jin;Feng, Lanying;Moon, Wooil-M.
    • Proceedings of the KSRS Conference
    • /
    • 1999.11a
    • /
    • pp.148-153
    • /
    • 1999
  • Baikdu-san was a very active volcano during the Cenozoic era and is believed to be formed in late Cenozoic era. Recently it was also reported that there was a major eruption in or around 1002 A.D. and there are evidences which indicate that it is still an active volcano and a potential volcanic hazard. Remote sensing techniques have been widely used to monitor various natural hazards, including volcanic hazards. However, during an active volcanic eruption, volcanic ash can basically cover the sky and often blocks the solar radiation preventing any use of optical sensors. Synthetic aperture radar(SAR) is an ideal tool to monitor the volcanic activities and lava flows, because the wavelength of the microwave signal is considerably longer that the average volcanic ash particle size. In this study we have utilized several sets of SAR data to evaluate the utility of the space-borne SAR system. The data sets include JERS-1(L-band) SAR, and RADARSAT(C-band) data which included both standard mode and the ScanSAR mode data sets. We also utilized several sets of auxiliary data such as local geological maps and JERS-1 OPS data. The routine preprocessing and image processing steps were applied to these data sets before any attempts of classifying and mapping surface geological features. Although we computed sigma nought ($\sigma$$^{0}$) values far the standard mode RADARSAT data, the utility of sigma nought image was minimal in this study. Application of various types of classification algorithms to identify and map several stages of volcanic flows was not very successful. Although this research is still in progress, the following preliminary conclusions could be made: (1) sigma nought (RADARSAT standard mode data) and DN (JERS-1 SAR and RADARSAT ScanSAR data) have limited usefulness for distinguishing early basalt lava flows from late trachyte flows or later trachyte flows from the old basement granitic rocks around Baikdu-san volcano, (2) surface geological structure features such as several faults and volcanic lava flow channels can easily be identified and mapped, and (3) routine application of unsupervised classification methods cannot be used for mapping any types of surface lava flow patterns.

  • PDF

Wavelet-Based Edge Detection Using Local Histogram Analysis in Images (영상에서 웨이블렛 기반 로컬 히스토그램 분석을 이용한 에지검출)

  • Park, Min-Joon;Kwon, Min-Jun;Kim, Gi-Hun;Shim, Han-Seul;Kim, Dong-Wook;Lim, Dong-Hoon
    • The Korean Journal of Applied Statistics
    • /
    • v.24 no.2
    • /
    • pp.359-371
    • /
    • 2011
  • Edge detection in images is an important step in image segmentation and object recognition as preprocessing for image processing. This paper presents a new edge detection using local histogram analysis based on wavelet transform. In this work, the wavelet transform uses three components (horizontal, vertical and diagonal) to find the magnitude of the gradient vector, instead of the conventional approach in which tw components are used. We compare the magnitude of the gradient vector with the threshold that is obtained from a local histogram analysis to conclude that an edge is present or not. Some experimental results for our edge detector with a Sobel, Canny, Scale Multiplication, and Mallat edge detectors on sample images are given and the performances of these edge detectors are compared in terms of quantitative and qualitative measures. Our detector performs better than the other wavelet-based detectors such as Scale Multiplication and Mallat detectors. Our edge detector also preserves a good performance even if the Sobel and Canny detector are sharply low when the images are highly corrupted.

A New Software for Quantitative Measurement of Strabismus based on Digital Image (디지털 영상 기반 정량적인 사시각 측정을 위한 새로운 소프트웨어)

  • Kim, Tae-Yun;Seo, Sang-Sin;Kim, Young-Jae;Yang, Hee-Kyung;Hwang, Jeong-Min;Kim, Kwang-Gi
    • Journal of Korea Multimedia Society
    • /
    • v.15 no.5
    • /
    • pp.595-605
    • /
    • 2012
  • Various methods for measuring strabismus have been developed and used in clinical diagnosis. However, most of them are based on the visual inspection by clinicians. For this reason, there is a high possibility of subjective evaluation in clinical decisions and they are only useful for cooperative patients. Therefore, the development of a more objective and reproducible method for measuring strabismus is needed. In this paper, we introduce a new software to complement the limitations of previous diagnostic methods. Firstly, we simply obtained facial images of patients and performed several preprocessing steps based on the spherical RGB color model with them. Then, the measurement of strabismus was performed automatically by using our 3D eye model and mathematical algorithm. To evaluate the validity of our software, we performed statistical correlation analysis of the results of the proposed method and the Krimsky test by two clinicians for ten patients. The coefficients of correlation for two clinicians were very high, 0.955 and 0.969, respectively. The coefficient of correlation between two clinicians also showed 0.968. We found a statistically significant correlation between two methods from our results. The newly developed software showed a possibility that it can be used as an alternative or effective assistant tool of previous diagnostic methods for strabismus.

Vehicle Area Segmentation from Road Scenes Using Grid-Based Feature Values (격자 단위 특징값을 이용한 도로 영상의 차량 영역 분할)

  • Kim Ku-Jin;Baek Nakhoon
    • Journal of Korea Multimedia Society
    • /
    • v.8 no.10
    • /
    • pp.1369-1382
    • /
    • 2005
  • Vehicle segmentation, which extracts vehicle areas from road scenes, is one of the fundamental opera tions in lots of application areas including Intelligent Transportation Systems, and so on. We present a vehicle segmentation approach for still images captured from outdoor CCD cameras mounted on the supporting poles. We first divided the input image into a set of two-dimensional grids and then calculate the feature values of the edges for each grid. Through analyzing the feature values statistically, we can find the optimal rectangular grid area of the vehicle. Our preprocessing process calculates the statistics values for the feature values from background images captured under various circumstances. For a car image, we compare its feature values to the statistics values of the background images to finally decide whether the grid belongs to the vehicle area or not. We use dynamic programming technique to find the optimal rectangular gird area from these candidate grids. Based on the statistics analysis and global search techniques, our method is more systematic compared to the previous methods which usually rely on a kind of heuristics. Additionally, the statistics analysis achieves high reliability against noises and errors due to brightness changes, camera tremors, etc. Our prototype implementation performs the vehicle segmentation in average 0.150 second for each of $1280\times960$ car images. It shows $97.03\%$ of strictly successful cases from 270 images with various kinds of noises.

  • PDF

Vehicle Recognition with Recognition of Vehicle Identification Mark and License Plate (차량 식별마크와 번호판 인식을 통한 차량인식)

  • Lee Eung-Joo;Kim Sung-Jin;Kwon Ki-Ryong
    • Journal of Korea Multimedia Society
    • /
    • v.8 no.11
    • /
    • pp.1449-1461
    • /
    • 2005
  • In this paper, we propose a vehicle recognition system based on the classification of vehicle identification mark and recognition of vehicle license plate. In the proposed algorithm, From the input vehicle image, we first simulate preprocessing procedures such as noise reduction, thinning etc., and detect vehicle identification mark and license plate region using the frequency distribution of intensity variation. And then, we classify extracted vehicle candidate region into identification mark, character and number of vehicle by using structural feature informations of vehicle. Lastly, we recognize vehicle informations with recognition of identification mark, character and number of vehicle using hybrid and vertical/horizontal pattern vector method. In the proposed algorithm, we used three properties of vehicle informations such as Independency property, discriminance property and frequency distribution of intensity variation property. In the vehicle images, identification mark is generally independent of the types of vehicle and vehicle identification mark. And also, the license plate region between character and background as well as horizontal/vertical intensity variations are more noticeable than other regions. To show the efficiency of the propofed algorithm, we tested it on 350 vehicle images and found that the propofed method shows good Performance regardless of irregular environment conditions as well as noise, size, and location of vehicles.

  • PDF