• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.5
• /
• pp.23-29
• /
• 2020

The National Institute of Agricultural Sciences of the Rural Developement Administration (NAS, RDA) is conducting various studies on various crops, such as monitoring the cultivation environment and analyzing harvested seeds for high-throughput phenotyping. In this paper, we propose a deep learning-based rice seed segmentation method to analyze the seeds of various crops owned by the NAS. Using Mask-RCNN deep learning model, we perform the rice seed segmentation from manually taken images under specific environment (constant lighting, white background) for analyzing the seed characteristics. For this purpose, we perform the parameter tuning process of the Mask-RCNN model. By the proposed method, the results of the test on seed object detection showed that the accuracy was 82% for rice stem image and 97% for rice grain image, respectively. As a future study, we are planning to researches of more reliable seeds extraction from cluttered seed images by a deep learning-based approach and selection of high-throughput phenotype through precise data analysis such as length, width, and thickness from the detected seed objects.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.6
• /
• pp.1162-1169
• /
• 2007

In this paper, we proposed a container identifier recognition method for containers used in harbors. After converting a real container image to a gray image, edges are detected from the gray image applying Prewitt mask and candidate identifier area is extracted using morphological features of individual identifier for identifying containers. Because noises are included in the extracted candidate identifier area, noises are eliminated and each identifier is separated using 4-directional edge tracking algorithm and Grassfire algorithm. Each identifier in the noise-free candidate identifier area is recognized using FCM-based row RBF network for discriminating containers. We used 300 real container images for experiment to evaluate the performance of the proposed method, and we could verify the proposed method is better than a conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1262-1270
• /
• 2020

Recently, the smart video surveillance research, which has been receiving increasing attention, has mainly focused on the intruder detection and tracking, and abandoned object detection. On the other hand, research on real-time detection of stolen objects is relatively insufficient compared to its importance. Considering various smart surveillance video application environments, this paper presents two different types of stolen object detection algorithms. We first propose an algorithm that detects theft of statically and dynamically registered surveillance objects using a dual background subtraction model. In addition, we propose another algorithm that detects theft of general surveillance objects by applying the dual background subtraction model and Mask R-CNN-based object segmentation technology. The former algorithm can provide economical theft detection service for pre-registered surveillance objects in low computational power environments, and the latter algorithm can be applied to the theft detection of a wider range of general surveillance objects in environments capable of providing sufficient computational power.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.619-628
• /
• 2022

Although face recognition and face generation have been growing in popularity, the privacy issues of using facial images in the wild have been a concurrent topic. In this paper, we propose a face editing network that can reduce privacy issues by generating face images with various properties from a small number of real face images and facial mask information. Unlike the existing methods of learning face attributes using a lot of real face images, the proposed method generates new facial images using a facial segmentation mask and texture images from five parts as styles. The images are then trained with our network to learn the styles and locations of each reference image. Once the proposed framework is trained, we can generate various face images using only a small number of real face images and segmentation information. In our extensive experiments, we show that the proposed method can not only generate new faces, but also localize facial attribute editing, despite using very few real face images.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.41-45
• /
• 2010

Image processing techniques are fundamental in human vision-based image information processing. There have been widely studied areas such as image transformation, image enhancement, image restoration, and image compression. One of research subgoals in those areas is enhancing image information for the correct information retrieval. As a fundamental task for the image recognition and interpretation, image enhancement includes noise filtering techniques. Conventional filtering algorithms may have high noise removal rate but usually have difficulty in conserving boundary information. As a result, they often use additional image processing algorithms in compensation for the tradeoff of more CPU time and higher possibility of information loss. In this paper, we propose a Fuzzy Mask Filtering algorithm that has high noise removal rate but lesser problems in above-mentioned side-effects. Our algorithm firstly decides a threshold based on fuzzy logic with information from masks. Then it decides the output pixel value by that threshold. In a designed experiment that has random impulse noise and salt pepper noise, the proposed algorithm was more effective in noise removal without information loss.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.4
• /
• pp.36-47
• /
• 1992

In this paper, a set of TM(template matching) mask using the AM(associative mapping) technique was generated and the edge detection algorithm for a SAR image was proposed. And also, the performance of the proposed edge detection algorithm was tested with the conventional edge detection techniques. The proposed edge detection algorithm created an edge image which was more accurate and clear than the conventional edge detection techniques and the performance of the proposed detection technique was not deteriorated for low intensity area in the image because the uncertainly thresholded value genetated by the conventional detection methods was requested. Also, the number of masks and the detection time were reduced by adjusting resolution of edge detection and the consideration for the threshold value extracting the edge was very intuitive.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.561-564
• /
• 2001

잡음에 의해 훼손된 영상 신호를 복원할 때 쓰이는 Wiener filter는 국부영역의 잡음 분산과 신호 분산을 가지고 적응적으로 필터의 파라미터를 조절한다. 그러나 기존의 Wiener filter는 고정된 필터 마스크를 사용함으로써, 평탄 영역의 잡음을 크게 제거하면, 에지 부분의 잡음이 살고, 에지 부분의 잡음을 제거하면, 평탄영역의 잡음이 사는 특성이 있다. 본 논문은 Kirsh mask로 에지와 그 방향성을 판별한 후, 에지 부분의 잡음을 제거하면서 평탄 영역의 잡음도 동시에 제거하기 위해 가변적인 필터 마스크를 사용했으며, 잡음에 의해 훼손된 방향성 정보를 살러 주기위해 필터 마tm크와 훼손된 영상 이미지에 방향성 정보를 추가했다. 제안된 방법으로 실험한 결과 주관적 비교에서 에피 부분이 잡음을 제거하고 방향성을 살렸으며, PSNR을 이용한 객관적 비교에서도 기존알고리즘보다 개선된 성능을 보였다.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.913-916
• /
• 1998

In this paper, to provide the robustness of character recognition, we propose a recognition method using the dilated boundary curve feature which has the invariance characteristics for the shift, scale, and rotation changes of character pattern. And its some characteristics and effectieness are evaluated through the experiments for both the english alphabets and the numeral digits. The feature vector is represented by the fourier descriptor for a boundary curve of the dilated character pattern which is generated by the circular mask dilation method, and is used for a nearest neighbort classifier(NNC) or a nearest neighbor mean classifier(NNMC). These the processing time and the recognition rate, and take also the robustness of recognition for both some internal noise and partial corruption of an image pattern.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.32A no.10
• /
• pp.51-63
• /
• 1995

In this paper, a new real-time optical image switching system based on the phase-typed BPEJTC is suggested. The phase filter mask which has the arbitrary position mapping function between input and output planes is constructed by using the modified JTPS of the BPEJTC. Then, the input image is convolved with this phase filter mask in the spatial frequency domain and through further Fourier transform the input image is switched to the new positions in the output correlation plane where the correlation peaks are occurred. And, based on the computer simulation results, the practical optical switched to the new positions in the output correlation plane where the correlation peaks are occurred. And, based on the computer simulation results, the practical optical switching system is opto-digitally constructed and through some experiments on image switching the possiblity of real-time implementation of the multiple optical image switching system by using the BPEJTC is suggeste.

• The KIPS Transactions:PartB
• /
• v.8B no.2
• /
• pp.189-194
• /
• 2001

본 논문에서는 개인 식별을 위하여 복수 해상도 구조를 제시하였고 이 방법으로 구순문 인식을 구현하였다. 구순문 인식은 지문, 음성 패턴, 홍채 패턴과 얼굴 인식과 같은 신체적 특징에 비하여 상대적으로 연구가 많이 이루어지지 않은 신체적 특징이다. 구순문은 CCD 카메라를 이용할 경우 홍채나 얼굴 패턴 같은 다른 특징 요소와 연결하여 인식 시스템을 구축할 수 있는 장점을 가지고 있다. 구순문 인식을 위해 pattern kernels를 이용한 새로운 방법을 제시하였다. Pattern kernels는 여러 개의 local lip print mask들로 구성된 함수이며, lip print의 정보를 디지털 데이터로 전환시켜 준다. 복수 해상도를 가지는 인식 시스템은 단일 해상도의 시스템보다 더욱 신뢰적이며 인식률도 높다.