• Title/Summary/Keyword: pixel combination

Search Result 90, Processing Time 0.029 seconds

Deep learning framework for bovine iris segmentation

  • Heemoon Yoon;Mira Park;Hayoung Lee;Jisoon An;Taehyun Lee;Sang-Hee Lee
    • Journal of Animal Science and Technology
    • /
    • v.66 no.1
    • /
    • pp.167-177
    • /
    • 2024
  • Iris segmentation is an initial step for identifying the biometrics of animals when establishing a traceability system for livestock. In this study, we propose a deep learning framework for pixel-wise segmentation of bovine iris with a minimized use of annotation labels utilizing the BovineAAEyes80 public dataset. The proposed image segmentation framework encompasses data collection, data preparation, data augmentation selection, training of 15 deep neural network (DNN) models with varying encoder backbones and segmentation decoder DNNs, and evaluation of the models using multiple metrics and graphical segmentation results. This framework aims to provide comprehensive and in-depth information on each model's training and testing outcomes to optimize bovine iris segmentation performance. In the experiment, U-Net with a VGG16 backbone was identified as the optimal combination of encoder and decoder models for the dataset, achieving an accuracy and dice coefficient score of 99.50% and 98.35%, respectively. Notably, the selected model accurately segmented even corrupted images without proper annotation data. This study contributes to the advancement of iris segmentation and the establishment of a reliable DNN training framework.

A Study on Stroke Extraction for Handwritten Korean Character Recognition (필기체 한글 문자 인식을 위한 획 추출에 관한 연구)

  • Choi, Young-Kyoo;Rhee, Sang-Burm
    • The KIPS Transactions:PartB
    • /
    • v.9B no.3
    • /
    • pp.375-382
    • /
    • 2002
  • Handwritten character recognition is classified into on-line handwritten character recognition and off-line handwritten character recognition. On-line handwritten character recognition has made a remarkable outcome compared to off-line hacdwritten character recognition. This method can acquire the dynamic written information such as the writing order and the position of a stroke by means of pen-based electronic input device such as a tablet board. On the contrary, Any dynamic information can not be acquired in off-line handwritten character recognition since there are extreme overlapping between consonants and vowels, and heavily noisy images between strokes, which change the recognition performance with the result of the preprocessing. This paper proposes a method that effectively extracts the stroke including dynamic information of characters for off-line Korean handwritten character recognition. First of all, this method makes improvement and binarization of input handwritten character image as preprocessing procedure using watershed algorithm. The next procedure is extraction of skeleton by using the transformed Lu and Wang's thinning: algorithm, and segment pixel array is extracted by abstracting the feature point of the characters. Then, the vectorization is executed with a maximum permission error method. In the case that a few strokes are bound in a segment, a segment pixel array is divided with two or more segment vectors. In order to reconstruct the extracted segment vector with a complete stroke, the directional component of the vector is mortified by using right-hand writing coordinate system. With combination of segment vectors which are adjacent and can be combined, the reconstruction of complete stroke is made out which is suitable for character recognition. As experimentation, it is verified that the proposed method is suitable for handwritten Korean character recognition.

Integrated Color Matching in Stereoscopic Image by Combining Local and Global Color Compensation (지역과 전역적인 색보정을 결합한 스테레오 영상에서의 색 일치)

  • Shu, Ran;Ha, Ho-Gun;Kim, Dae-Chul;Ha, Yeong-Ho
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.50 no.12
    • /
    • pp.168-175
    • /
    • 2013
  • Color consistency in stereoscopic contents is important for 3D display systems. Even with a stereo camera of the same model and with the same hardware settings, complex color discrepancies occur when acquiring high quality stereo images. In this paper, we propose an integrated color matching method that use cumulative histogram in global matching and estimated 3D-distance for the stage of local matching. The distance between the current pixel and the target local region is computed using depth information and the spatial distance in the 2D image plane. The 3D-distance is then used to determine the similarity between the current pixel and the target local region. The overall algorithm is described as follow; First, the cumulative histogram matching is introduced for reducing global color discrepancies. Then, the proposed local color matching is established for reducing local discrepancies. Finally, a weight-based combination of global and local matching is computed. Experimental results show the proposed algorithm has improved global and local error correction performance for stereoscopic contents with respect to other approaches.

Polarimetry of solar system small bodies using the Seoul National University 61cm telescope and TRIPOL

  • Jin, Sunho;Ishiguro, Masateru;Kwon, Yuna Grace;Geem, Jooyeon;Bach, Yoonsoo P.;Seo, Jinguk;Sasago, Hiroshi;Sato, Shuji
    • The Bulletin of The Korean Astronomical Society
    • /
    • v.44 no.1
    • /
    • pp.64.2-64.2
    • /
    • 2019
  • It is known that lights scattered by comets and asteroids are partially polarized. From polarimetric observations of those objects, we can investigate physical properties, such as albedos, sizes of cometary dust particles and regolith of asteroids. Since the polarization degrees of those objects highly depend on their phase angles (Sun-object-observer's angles), long-term monitoring observations are required. Moreover, comets show unforeseeable activations (i.e., outbursts) which need follow-up observations to understand the mechanism. In order to realize such monitoring and transient observations, we installed the Triple-Range Imager and POLarimeter (TRIPOL) on the 61cm telescope of Seoul National University (Hereafter, SNU) Gwanak campus. With this combination, we can obtain g', r', i' bands photopolarimetric images simultaneously with $8.0^{\prime}{\times}8.0^{\prime}$ field of view and pixel resolution of 0.94" pixel-1. Here, we make a presentation regarding the photometric and polarimetric performances of TRIPOL on the SNU 61cm telescope. In addition, we introduce initial polarimetric results of asteroid and comets with the instruments. First, we determine the limiting magnitudes (defined as magnitudes for S/N=5) of $15.17{\pm}0.06$ (g'-band), $15.68{\pm}0.01$ (r'-band), $16.24{\pm}0.03$ (I'-band), respectively, with total 240-seconds exposure (four 60-seconds exposure images, each was taken at different rotation angle for the half-wave plate). Second, we found that the instrumental polarization is negligibly small, ($-0.32{\pm}0.04%$ in the g', $-0.36{\pm}0.05%$ in the r' and $-0.21{\pm}0.04%$ in the i'-bands), while the polarization efficiencies are large enough to maximize the performance (i.e., $97.52{\pm}0.03%$ in the g', $98.83{\pm}0.02%$ in the r' and $99.15{\pm}0.02%$ in the i'-bands). With the instruments, we made observations of three Jupiter-family comets, 21P/Giacobini-Zinner, 38P/Stephan-Oterma, and 46P/Wirtanen and plan to observe one near-Earth asteroid, (433) Eros, on a trial basis. Especially for comets, we discriminate signals from dust and gas to eliminate gas contamination, which are known to change observed degree of linear polarization, using multi-band images. We confirm that the phase angle dependency of these comets are consistent with previous observations, probably because polarimetric property of Jupiter-family comets are broadly homogeneous unlike asteroids. We will also describe future observation plans using TRIPOL and SNU 61cm telescope.

  • PDF

A Study on Illumination Normalization Method based on Bilateral Filter for Illumination Invariant Face Recognition (조명 환경에 강인한 얼굴인식 성능향상을 위한 Bilateral 필터 기반 조명 정규화 방법에 관한 연구)

  • Lee, Sang-Seop;Lee, Su-Young;Kim, Joong-Kyu
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.47 no.4
    • /
    • pp.49-55
    • /
    • 2010
  • Cast shadow caused by an illumination condition can produce troublesome effects for face recognition system using reflectance image. Consequently, we need to separate cast shadow area from feature area for improvement of recognition accuracy. A Bilateral filter smooths image while preserving edges, by means of a nonlinear combination of nearby pixel values. Processing such characteristics, this method is suited to our purpose in illumination estimation process based on Retinex. Therefore, in this paper, we propose a new illumination normalization method based on the Bilateral filter in face images. The proposed method produces a reflectance image that is preserved relatively exact cast shadow area, because coefficient of filter is designed to multiply proximity and discontinuity of pixels in input image. Performance of our method is measured by a recognition accuracy of principle component analysis(PCA) and evaluated to compare with other conventional illumination normalization methods.

Investigation of Radiation Effects on the Signal and Noise Characteristics in Digital Radiography (디지털 래디오그라피의 신호 및 잡음 특성에 대한 방사선 영향에 관한 연구)

  • Kim, Ho-Kyung;Cho, Min-Kook;Graeve, Thorsten
    • Journal of Biomedical Engineering Research
    • /
    • v.28 no.6
    • /
    • pp.756-767
    • /
    • 2007
  • For the combination of phosphor screens having various thicknesses and a photodiode array manufactured by complementary metal-oxide-semiconductor (CMOS) process, we report the observation of image-quality degradation under the irradiation of 45-kVp spectrum x rays. The image quality was assessed in terms of dark pixel signal, dynamic range, modulation-transfer function (MTF), noise-power spectrum (NPS), and detective quantum efficiency (DQE). For the accumulation of the absorbed dose, the radiation-induced increase both in dark signal and noise resulted in the gradual reduction in dynamic range. While the MTF was only slightly affected by the total ionizing dose, the noise power in the case of $Min-R^{TM}$ screen, which is the thinnest one among the considered screens in this study, became larger as the total dose was increased. This is caused by incomplete correction of the dark current fixed-pattern noise. In addition, the increase tendency in NPS was independent of the spatial frequency. For the cascaded model analysis, the additional noise source is from direct absorption of x-ray photons. The change in NPS with respect to the total dose degrades the DQE. However, with carefully updated and applied correction, we can overcome the detrimental effects of increased dark current on NPS and DQE. This study gives an initial motivation that the periodic monitoring of the image-quality degradation is an important issue for the long-term and healthy use of digital x-ray imaging detectors.

Guidance Line Extraction for Autonomous Weeding robot based-on Rice Morphology Characteristic in Wet Paddy (논 잡초 방제용 자율주행 로봇을 위한 벼의 형태학적 특징 기반의 주행기준선 추출)

  • Choi, Keun Ha;Han, Sang Kwon;Han, Sang Hoon;Park, Kwang-Ho;Kim, Kyung-Soo;Kim, Soohyun
    • The Journal of Korea Robotics Society
    • /
    • v.9 no.3
    • /
    • pp.147-153
    • /
    • 2014
  • In this paper, we proposed a new algorithm of the guidance line extraction for autonomous weeding robot based on infrared vision sensor in wet paddy. It is the critical process for guidance line extraction which finds the central point or area of rice row. In order to improve accuracy of the guidance line, we are trying to use the morphological characteristics of rice that the direction of rice leaves have convergence to central area of rice row. Using Hough transform, we were represented the curved leaves as a combination of segmented straight lines on binary image that has been skeletonized and segmented object. A slope of the guidance line was gotten as calculate the average slope of all segmented lines. An initial point of the guidance line was determined that is the maximum pixel value of the accumulated white columns of a binary image which is rotated the slope of guidance line in the opposite direction. We also have verified an accuracy of the proposed algorithm by experiments in the real wet paddy.

Monitoring Rock Physical Property Changes due to Excavations Using Horizontal Crosshole Georadar Tomography (수평 시추공간 지오레이다 토모그래피를 이용한 터널 굴착에 의한 암반 물성 변화의 고찰)

  • Jung, Yun-Moon;Lee, Myung-Sung;Song, Myung-Jun;Woo, Ik
    • Tunnel and Underground Space
    • /
    • v.6 no.4
    • /
    • pp.342-347
    • /
    • 1996
  • The changes of electromagnetic wave velocity in rock were monitored to investigate rock behaviors due to the drill & blasting excavations through georadar tomography during the construction of the underground rock laboratory (5 m wide, 6 m high, and 140 m long) at Mabuk-Ri, Goosung-Myun, Yongin-Si, Kyunggi-Do. Two horizontal boreholes spaced 1.4 m apart were drilled parallel to the test tunnel before excavating it, high-resolution crosshole georadar tomography with about 500 MHz electromagnetic waves was performed at pre-excavation phase (May, 1996) and post-excavation phase (August, 1996). The data were acquired with the combination of 34 sources and 44 receivers with space of 0.3 m. Only 11 continuous receivers were selectively utilized with one fixed source. Sampling interval was 0.4 ns and each trace has 512 samples. The first arrival of each trace was picked manually with a picking software. The total number of rays used in inversion amounted to 34x11 and the size of pixel was determined to be 0.3 m. As an inversion technique, SIRT(Simultaneous Iterative Reconstruction Technique) was applied in this study. The velocity of electromagnetic waves at post-excavation phase decreased as large as 15% in comparison with that at pre-excavation phase, which may be attributed to the creation of micro-cracks in rock due to excavations and saturation with groundwater. Small amount of borehole deviation made a critical effect in radar tomography. Totally different tomograms were created after borehole deviation corrections.

  • PDF

Design and Implementation of Efficient Plate Number Region Detecting System in Vehicle Number Plate Image (자동차 번호판 영상에서 효율적인 번호판 영역 검출 시스템의 설계 및 개발)

  • Lee Hyun-Chang
    • Journal of the Korea Society of Computer and Information
    • /
    • v.10 no.5 s.37
    • /
    • pp.87-94
    • /
    • 2005
  • This paper describes the method of detecting the region of vehicle number plate in colored car image with number plate. Vehicle number plate region generally shows formula colors in accordance with type of car. According to this, we use the method to combine a color ingredient H of HSI color model and a color ingredient Q of YIQ color model. However, the defect which a total operation time takes much exists if it uses such method. Therefore, in this paper, the concurrent accomplishes a candidate area extraction operation as draw a color H and Q ingredient among steps of extracting a region of vehicle number Plate. After the above step, as a next step in combination with color H and Q we can accomplish an region extraction fast by comparing to candidate regions extracted from each steps not to do a comparison operation to all of image pixel information. We also show implementation results Processed at each steps and compare with extraction time according to image resolutions.

  • PDF

Epipolar Resampling from Kompsat-2 and Kompsat-3 (아리랑 위성 2호와 3호를 이용한 이종 영상 간 에피폴라 영상 생성)

  • Song, Jeong-Heon;Oh, Jae-Hong
    • Journal of the Korean Association of Geographic Information Studies
    • /
    • v.17 no.4
    • /
    • pp.156-166
    • /
    • 2014
  • As of 2014, KARI (Korea Aerospace Research Institute) operates two high-resolution satellites such as Kompsat-2 and Kompsat-3. Kompsat-3 has capability of in-track stereo images acquisition but it is quite limited because the stereo mode lowers the spatial coverage in a trajectory. In this paper we analyze the epipolar geometry from the heterogeneous Kompsat-2 and Kompsat-3 image combination to epipolar resample them for 3D spatial data acquisition. The analysis was carried out using the piecewise approach with RPCs (Rational Polynomial Coefficients) and the result showed the parabolic epipolar curve pattern. We also concluded that the third order polynomial transformation is required for epipolar image resampling. The resampled image pair showed 1 pixel level of y-parallax and can be used for 3D display and digitizing.