• Korean Journal of Remote Sensing
• /
• v.16 no.3
• /
• pp.199-209
• /
• 2000

This study improves the feature tracking method (FTM) in estimating the ocean current vectors from the sequential AVHRR satellite imageries by adding the objective algorithm in defining the edges and boundaries of the oceanic eddies and fronts. It was implemented by using the Sobel operator. The Sobel operator has been proved to be in effective filter in detecting the edges of any object on the image. In estimating the current vectors on the edges defined by the Sobel operator, center coordinates of the Pattern and Search tiles need to be determined by the investigator. The objective feature tracking method combined with maximum cross correlation method (MCC) is turned out to be very efficient and fast, since it uses only parts of the image containing the objects instead of searching the entire image. In the validation with the in situ ADCP measurements of currents in the East Sea, the estimated current speed values are around 35% lower than and current directions are deviated by $34^{\circ}$ from ADCP current vectors. The results are regarded as improved ones compared to the previous investigators'.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• 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.28 no.7C
• /
• pp.719-725
• /
• 2003

The content-based image retrieval system extracts features of color, shape and texture from raw images, and builds the database with those features in the indexing process. The search in the whole retrieval system is defined as a process which finds images that have large similarity to query image using the feature database. This paper proposes a new two-stage search method in the content-based image retrieval system. The method is that the features are condensed and stored by the property of Cauchy-Schwartz inequality in order to reduce the similarity computation time which takes a mostly response time from entering a query to getting retrieval results. By the extensive computer simulations, we have observed that the proposed two-stage search method successfully reduces the similarity computation time while maintaining the same retrieval relevance as the conventional exhaustive search method. We also have observed that the method is more effective as the number of images and dimensions of the feature space increase.

• Current Optics and Photonics
• /
• v.7 no.3
• /
• pp.237-247
• /
• 2023

In middle- and long-distance imaging systems, due to the atmospheric turbulence caused by temperature, wind speed, humidity, and so on, light waves propagating in the air are distorted, resulting in image-quality degradation such as geometric deformation and fuzziness. In remote sensing, astronomical observation, and traffic monitoring, image information loss due to degradation causes huge losses, so effective restoration of degraded images is very important. To restore images degraded by atmospheric turbulence, an image-restoration method based on improved compound multibranch feature fusion (CMFNetPro) was proposed. Based on the CMFNet network, an efficient channel-attention mechanism was used to replace the channel-attention mechanism to improve image quality and network efficiency. In the experiment, two-dimensional random distortion vector fields were used to construct two turbulent datasets with different degrees of distortion, based on the Google Landmarks Dataset v2 dataset. The experimental results showed that compared to the CMFNet, DeblurGAN-v2, and MIMO-UNet models, the proposed CMFNetPro network achieves better performance in both quality and training cost of turbulent-image restoration. In the mixed training, CMFNetPro was 1.2391 dB (weak turbulence), 0.8602 dB (strong turbulence) respectively higher in terms of peak signal-to-noise ratio and 0.0015 (weak turbulence), 0.0136 (strong turbulence) respectively higher in terms of structure similarity compared to CMFNet. CMFNetPro was 14.4 hours faster compared to the CMFNet. This provides a feasible scheme for turbulent-image restoration based on deep learning.

• Information and Communications Magazine
• /
• v.7 no.3
• /
• pp.27-34
• /
• 1990

The $(L,\psi)$ feature description on the binary boundary air craft image is introduced of classifying 3-D object (aircraft) identification. Three types for associative matrix memories are employed and tested for their classification performance. The fast association involved in these memories can be implemented using a parallel optical matrix-vector operation. Two associative memories are based on pseudoinverse solutions and the third one is interoduced as a paralell version of a nearest-neighbor classifier. Detailed simulation results for each associative processor are provided.

• Journal of Korea Society of Industrial Information Systems
• /
• v.2 no.1
• /
• pp.73-87
• /
• 1997

Multilayer neural network using a modified beackpropagation learning algorithm was introduced to achieve automatic identification of different types of aircraft in a variety of 3-D orientations. A 3-D shape of an aircraft can be described by a library of 2-D images corresponding to the projected views of an aircraft. From each 2-D binary aircraft image we extracted 2-D invariant (L, Φ) feature vector to be used for training neural network aircraft classifier. Simulations concerning the neural network classification rate was compared using nearest-neighbor classfier (NNC) which has been widely served as a performance benchmark. And we also introduced reliability measure of the designed neural network classifier.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.146-149
• /
• 2003

개인의 신분을 확인하는 생체인식기술은 정보기술이 고도화된 사회 속에서 정보보안의 관점에서 더욱 중요한 문제로 인식되기 시작했다. 이러한 생체인식 영역 중에서 비교적 거부감을 덜 주면서 어느 정도의 인식율을 제공하는 얼굴인식 분야의 연구는 지난 수년간 활발하게 진행되었다. 보통 전통적으로 얼굴인식에는 우선 PCA가 적용되어 데이터를 축소하고 LDA가 얼굴 인식을 위한 특징벡터를 추출하는 역할을 수행한다 본 논문에서는 이러한 이원적인 과정을 동시 대각화를 통해 하나의 과정으로 통합하고 기존의 유클리디언 디스턴스 대신에 SVM(Support Vector Machine) 패턴 분류기를 사용하여 얼굴인식을 수행하는 알고리즘을 제안한다.

• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1250-1260
• /
• 2020

This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.1
• /
• pp.59-68
• /
• 1999

Recently, research and developmental direction of communication system is concurrent adopting voice data and face image in speaking to provide more higher recognition rate then in the case of only voice data. Therefore, we present a method of lipreading in speech image sequence by using the 3-D facial shape model. The method use a feature information of the face image such as the opening-level of lip, the movement of jaw, and the projection height of lip. At first, we adjust the 3-D face model to speeching face image sequence. Then, to get a feature information we compute variance quantity from adjusted 3-D shape model of image sequence and use the variance quality of the adjusted 3-D model as recognition parameters. We use the intensity inclination values which obtaining from the variance in 3-D feature points as the separation of recognition units from the sequential image. After then, we use discrete HMM algorithm at recognition process, depending on multiple observation sequence which considers the variance of 3-D feature point fully. As a result of recognition experiment with the 8 Korean vowels and 2 Korean consonants, we have about 80% of recognition rate for the plosives and vowels. We propose that usability with visual distinguishing factor that using feature vector because as a result of recognition experiment for recognition parameter with the 10 korean vowels, obtaining high recognition rate.