• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.67-76
• /
• 2019

In this paper, we propose an efficient object classification method based on semantic segmentation for multi-labeled image data. In addition to various pixel unit information and processing techniques such as color information, contour, contrast, and saturation included in image data, a detailed region in which each object is located is extracted as a meaningful unit and the experiment is conducted to reflect the result in the inference. We use a neural network that has been proven to perform well in image classification to understand which object is located where image data containing various class objects are located. Based on these researches, we aim to provide artificial intelligence services that can classify real-time detailed areas of complex images containing various objects in the future.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.432-435
• /
• 2007

본 논문은 신원확인 수단으로 부각되어 관심이 높은 홍채인식에 대한 연구이다 홍채인식 시스템의 경우 홍채영역에 따라 각 영상들의 특징 값이 차지하는 비중이 서로 다르게 분포되어 있고 눈썹이나 조명에 의한 잡음으로 인하여 인식성능에 영향을 미친다. 이 경우 기존에 등록되어 인증된 사용자의 홍채영상일지라도 제대로 인식하지 못하거나 인증에 실패할 수 있으며, 실세계에서의 홍채영역 사용이 원활하지 못하게 된다. 그러므로 단일 생체인식 시스템에서 홍채인식을 할 경우, 중요한 특징을 그대로 유지하고 인식성능을 향상시키기 위해서 획득된 홍채 영상의 정규화와 전처리 과정을 거친 다음 홍채영역을 분할한 후 각 영역에서의 보정치 적용을 통한 특징추출 방법을 제안한다. 또한 웨이블릿 변환과 주성분 분석을 이용하여 인식 성능이 개선된 특징추출 방법임을 보인다.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.1
• /
• pp.91-97
• /
• 2009

This paper proposes novel FE-CBIRS that finds best position of a cut to be retrieved based on color feature distribution in digital contents of IPTV. Conventional CBIRS have used a method that utilizes both color and shape information together to classify images, as well as a method that utilizes both feature information of the entire region and feature information of a partial region that is extracted by segmentation for searching. Also, in the algorithm, average, standard deviation and skewness values are used in case of color features for each hue, saturation and intensity values respectively. Furthermore, in case of using partial regions, only a few major colors are used and in case of shape features, the invariant moment is mainly used on the extracted partial regions. Due to these reasons, some problems have been issued in CBIRS in processing time and accuracy so far. Therefore, in order to tackle these problems, this paper proposes the FE-CBIRS that makes searching speed faster by classifying and indexing the extracted color information by each class and by using several cuts that are restricted in range as comparative images.

• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.689-698
• /
• 2006

Pattern recognition is the study of how machines can observe the environment, learn to distinguish patterns of interest from their background, and make sound and reasonable decisions about the categories of the patterns. Color image consists of various color patterns. And most pattern recognition methods use the information of color which has been trained and extract the feature of the color. This thesis extracts adaptively specific color feature from images with several limited colors. Because the number of the color patterns is limited, the distribution of the color in the image is similar. But, when there are some noises and distortions in the image, its distribution can be various. Therefore we cannot extract specific color regions in the standard image that is well expressed in special color patterns to extract, and special color regions of the image to test. We suggest new method to reduce the error of recognition by extracting the specific color feature adaptively for images with the low distortion, and six test images with some degree of noises and distortion. We consequently found that proposed method shouws more accurate results than those of statistical pattern recognition.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.359-368
• /
• 2002

In this paper, we propose effective boundary line extraction algorithm for moving objects by matching error image and moving vectors, and fast tracking algorithm for moving object by partial boundary lines. We extracted boundary line for moving object by generating seeds with probability distribution function based on Watershed algorithm, and by extracting boundary line for moving objects through extending seeds, and then by using moving vectors. We processed tracking algorithm for moving object by using a part of boundary lines as features. We set up a part of every-direction boundary line for moving object as the initial feature vectors for moving objects. Then, we tracked moving object within current frames by using feature vector for the previous frames. As the result of the simulation for tracking moving object on the real images, we found that tracking processing of the proposed algorithm was simple due to tracking boundary line only for moving object as a feature, in contrast to the traditional tracking algorithm for active contour line that have varying processing cost with the length of boundary line. The operations was reduced about 39% as contrasted with the full search BMA. Tracking error was less than 4 pixel when the feature vector was $(15\times{5)}$ through the information of every-direction boundary line. The proposed algorithm just needed 200 times of search operation.

• Journal of the Korea Institute of Building Construction
• /
• v.17 no.6
• /
• pp.545-557
• /
• 2017

The study is about the efficient alternative to concrete surface in the field of visual inspection technology for deteriorated infrastructure. By combining industrial drones and deep learning based image analysis techniques with traditional visual inspection and research, we tried to reduce manpowers, time requirements and costs, and to overcome the height and dome structures. On board device mounted on drones is consisting of a high resolution camera for detecting cracks of more than 0.3 mm, a lidar sensor and a embeded image processor module. It was mounted on an industrial drones, took sample images of damage from the site specimen through automatic flight navigation. In addition, the damege parts of the site specimen was used to measure not only the width and length of cracks but white rust also, and tried up compare them with the final image analysis detected results. Using the image analysis techniques, the damages of 54ea sample images were analyzed by the segmentation - feature extraction - decision making process, and extracted the analysis parameters using supervised mode of the deep learning platform. The image analysis of newly added non-supervised 60ea image samples was performed based on the extracted parameters. The result presented in 90.5 % of the damage detection rate.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1176-1194
• /
• 2018

The object classification using the images' contents is a big challenge in computer vision. The superpixels' information can be used to detect and classify objects in an image based on locations. In this paper, we proposed a methodology to detect and classify the image's pixels' locations using enhanced bag of words (BOW). It calculates the initial positions of each segment of an image using superpixels and then ranks it according to the region score. Further, this information is used to extract local and global features using a hybrid approach of Scale Invariant Feature Transform (SIFT) and GIST, respectively. To enhance the classification accuracy, the feature fusion technique is applied to combine local and global features vectors through weight parameter. The support vector machine classifier is a supervised algorithm is used for classification in order to analyze the proposed methodology. The Pascal Visual Object Classes Challenge 2007 (VOC2007) dataset is used in the experiment to test the results. The proposed approach gave the results in high-quality class for independent objects' locations with a mean average best overlap (MABO) of 0.833 at 1,500 locations resulting in a better detection rate. The results are compared with previous approaches and it is proved that it gave the better classification results for the non-rigid classes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.1C
• /
• pp.73-81
• /
• 2005

We propose an automatic modulation recognition scheme which extracts pre-defined key features from the received signal and then applies equal gain combining method to determine the used modulation. Moreover, we compare and analyze the performance of the proposed algorithm with that of decision-theoretic algorithm. Our scheme extracts five pre-defined key features from each data segment, a data unit for the key feature extraction, which are then averaged over all the segments to recognize the modulation according to the decision procedure. We check the performance of the proposed algorithm through computer simulations for analog modulations such as AM, FM, SSB and for digital modulations such as FSK2, FSK4, PSK2, and PSK4, by measuring recognition success rate varying SNR and data collection time. The result shows that the performance of the proposed scheme is comparable to that of the decision-theoretic algorithm with less complexity.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.10
• /
• pp.783-789
• /
• 2020

This paper proposes a new method for vision-based navigation using semantically segmented aerial images. Vision-based navigation can reinforce the vulnerability of the GPS/INS integrated navigation system. However, due to the visual and temporal difference between the aerial image and the database image, the existing image matching algorithms have difficulties being applied to aerial navigation problems. For this reason, this paper proposes a suitable matching method for the flight composed of navigational feature extraction through semantic segmentation followed by template matching. The proposed method shows excellent performance in simulation and even flight situations.