• 한국지능시스템학회논문지
• /
• 제25권5호
• /
• pp.437-443
• /
• 2015

이 논문에서는 가시광선 얼굴영상과 그로부터 예측한 열 적외선 텍스처의 데이터 융합에 의한 얼굴인식 방법에 관하여 연구하였다. 제안하는 얼굴인식 기법은 가시광선 얼굴영상과 열 적외선 텍스처를 PCA에 의하여 낮은 차원의 특징공간에서 특징벡터로 변환한 다음, 다층 신경회로망을 사용하여 가시광선 영상 특징으로부터 얼굴의 열적외선 특징을 예측하여 열 적외선 텍스처를 생성하였다. 학습과정에서는 주어진 개체로부터 획득한 한 쌍의 가시광선 및 열 적외선 영상에 대해서 PCA를 이용하여 낮은 차원의 특징공간으로 변환한 다음, 가시광선 영상특징으로부터 열 분포 특징으로 매핑시키는 비선형 함수에 해당하는 신경회로망의 내부 파라미터를 결정한다. 학습된 신경회로망은 입력 가시광선 얼굴 특징으로부터 열 에너지 분포 특성의 PCA계수를 예측하고, 이로부터 열 적외선 텍스처를 생성한다. 대표적인 두 가지 얼굴인식 알고리즘 Eigenfaces와 Fisherfaces을 사용하여 NIST/Equinox 데이터베이스에 대하여 얼굴인식에 관한 실험을 수행하였다. 예측한 열 적외선 텍스처와 가시광선 얼굴영상의 데이터 융합결과는 가시광선 얼굴영상만을 사용한 경우에 비해서 얼굴인식의 성능이 개선되었음을 수신자 조작특성 (ROC) 및 첫 번째 매칭성능에 의하여 검증하였다.

• Journal of Information Processing Systems
• /
• 제15권6호
• /
• pp.1296-1305
• /
• 2019

To solve the problem of poor noise suppression capability and frequent loss of edge contour and detailed information in current fusion methods, an infrared and visible light image fusion method based on variational multiscale decomposition is proposed. Firstly, the fused images are separately processed through variational multiscale decomposition to obtain texture components and structural components. The method of guided filter is used to carry out the fusion of the texture components of the fused image. In the structural component fusion, a method is proposed to measure the fused weights with phase consistency, sharpness, and brightness comprehensive information. Finally, the texture components of the two images are fused. The structure components are added to obtain the final fused image. The experimental results show that the proposed method displays very good noise robustness, and it also helps realize better fusion quality.

• 한국의류학회지
• /
• 제32권3호
• /
• pp.494-504
• /
• 2008

The purpose of this study was to classify the romantic image by clothing design elements. This research was done by survey method with 20 kinds of romantic image photos selected in fashion magazines. The data was analyzed by Reliability Analysis, Factor Analysis, ANOVA, Duncan's test and MDS. The results of this study are as follows: 1. Romantic image was classified by 4 factors. Those were sexy-romantic, retro-romantic, natural-romantic and cute-romantic images. 2. Sexy-romantic image was well-expressed by fitted silhouette, achromatic and achromatic color coordinations and see-through texture. Retro-romantic image was well-expressed by X silhouette, achromatic and achromatic color coordinations and see-through or combination texture. Natural-romantic image was well-expressed by A silhouette and chromatic and achromatic color coordinations. Cute-romantic image was well-expressed by A silhouette and soft or combination(silky and soft) texture. 3. Romantic image was positioned into mostly traditional or artificial on image scale.

• 한국측량학회지
• /
• 제30권6_2호
• /
• pp.665-672
• /
• 2012

Amid rapidly increasing imagery inputs and their volume in a remote sensing imagery database, Content-Based Image Retrieval (CBIR) is an effective tool to search for an image feature or image content of interest a user wants to retrieve. It seeks to capture salient features from a 'query' image, and then to locate other instances of image region having similar features elsewhere in the image database. For a CBIR approach that uses texture as a primary feature primitive, designing a texture descriptor to better represent image contents is a key to improve CBIR results. For this purpose, an extended feature vector combining the Gabor filter and co-occurrence histogram method is suggested and evaluated for quantitywise and qualitywise retrieval performance criterion. For the better CBIR performance, assessing similarity between high dimensional feature vectors is also a challenging issue. Therefore a number of distance metrics (i.e. L1 and L2 norm) is tried to measure closeness between two feature vectors, and its impact on retrieval result is analyzed. In this paper, experimental results are presented with several CBIR samples. The current results show that 1) the overall retrieval quantity and quality is improved by combining two types of feature vectors, 2) some feature is better retrieved by a specific feature vector, and 3) retrieval result quality (i.e. ranking of retrieved image tiles) is sensitive to an adopted similarity metric when the extended feature vector is employed.

• 반도체디스플레이기술학회지
• /
• 제13권4호
• /
• pp.91-96
• /
• 2014

Mobile image retrieval is one of the most exciting and fastest growing research fields in the area of multimedia technology. As the amount of digital contents continues to grow users are experiencing increasing difficulty in finding specific images in their image libraries. This paper proposes a new efficient and effective mobile image retrieval method that applies a weighted combination of color and texture utilizing spatial-color and second order statistics. The system for mobile image searches runs in real-time on an iPhone and can easily be used to find a specific image. To evaluate the performance of the new method, we assessed the iPhone simulations performance in terms of average precision and recall using several image databases and compare the results with those obtained using existing methods. Experimental trials revealed that the proposed descriptor exhibited a significant improvement of over 13% in retrieval effectiveness, compared to the best of the other descriptors.

• 한국의류학회지
• /
• 제17권3호
• /
• pp.428-435
• /
• 1993

The purpose of this study was to investigate the difference of the visual evaluation about clothing texture, the state of wearing and the method of presentation. The data from observation were analyzed by factor analysis, t-test, ANOVA, Scheffe test and MCA. The results of this study were as follows ; 1. 17 pairs of discriptors used for the visual evaluation of clothing stimuli were found to include four factor dimensions(total variance 65.6%) ; Attention, Appearance, Texture, Maturity. 2. For the image of clothing texture, there were significant differences in the attention and texture. 3. For the image of the state of wearing, there were significant differences in the attention and appearance. 4. For the image of the method of presentation, there were significant differences in the clothing texture and the state of wearing. 5. According to clothing texture, the state of wearing and the method of presentation, the interaction effect was significant in the attention and appearance.

• 한국정보처리학회논문지
• /
• 제7권11호
• /
• pp.3592-3602
• /
• 2000

영상 처리는 크게 영상에 내재된 특성값을 얻어내는 영상분석과, 동일한 성질의 영상을 분류하는 영상분류의 두단계로 이루어진다. 본 논문에서는 텍스쳐에 내재된 일반적인 속성인 거침과 부드러움의 특성 추출을 통해서 영상에 포함된 다양한 텍스쳐를 자동적으로 인식하고 분류하는 방법을 제안한다. 특성추출은 텍스쳐 영상이 지닌 그레이 레벨의 공간적인 의존성을 이용한 통계적 분석에 기반한 것으로 모멘트와 동차성의 조합을 통해서 일반적인 텍스쳐의 속성을 검출하기 때문에 텍스쳐의 구조형태에 크게 영향을 받지 않는 이점을 가지고 있다. 거친 텍스쳐일수록 강하게 반응하는 모멘트와 부드러운 텍스쳐일수록 강하게 반응하는 동차성의 차를 이용하기 때문에 보다 뚜렷한 텍스쳐 분할이 가능하다. 제안한 시스템의 성능 평가를 위해서 다양한 텍스쳐 영상에 제안한 방법을 적용하고, 성공적인 결과를 보인다.

• 한국의류학회지
• /
• 제44권2호
• /
• pp.354-368
• /
• 2020

Accurate and versatile image data-sets are essential for fashion AI research and AI-based fashion businesses based on a systematic attribute classification system. This study constructs a color and texture attribute hierarchical classification system by collecting fashion item images and analyzing the metadata of fashion items described by consumers. Essential dimensions to explain color and texture attributes were extracted; in addition, attribute values for each dimension were constructed based on metadata and previous studies. This hierarchical classification system satisfies consistency, exclusiveness, inclusiveness, and flexibility. The image tagging to confirm the usefulness of the proposed classification system indicated that the contents of attributes of the same image differ depending on the annotator that require a clear standard for distinguishing differences between the properties. This classification system will improve the reliability of the training data for machine learning, by providing standardized criteria for tasks such as tagging and annotating of fashion items.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권1호
• /
• pp.288-301
• /
• 2017

In this paper, we propose an optimized algorithm for texture classification by computing a completed modeling of the local binary pattern (CLBP) instead of the traditional LBP of a scalable block size in an image. First, we show that the CLBP descriptor is a better representative than LBP by extracting more information from an image. Second, the CLBP features of scalable block size of an image has an adaptive capability in representing both gross and detailed features of an image and thus it is suitable for image texture classification. This paper successfully implements a machine learning scheme by applying the CLBP features of a scalable size to the Support Vector Machine (SVM) classifier. The proposed scheme has been evaluated on Outex and CUReT databases, and the evaluation result shows that the proposed approach achieves an improved recognition rate compared to the previous research results.

• 디지털산업정보학회논문지
• /
• 제11권4호
• /
• pp.89-97
• /
• 2015

In this paper, a method of color image segmentation based on DBSCAN(Density Based Spatial Clustering of Applications with Noise) using compactness of superpixels and texture information is presented. The DBSCAN algorithm can generate clusters in large data sets by looking at the local density of data samples, using only two input parameters which called minimum number of data and distance of neighborhood data. Superpixel algorithms group pixels into perceptually meaningful atomic regions, which can be used to replace the rigid structure of the pixel grid. Each superpixel is consist of pixels with similar features such as luminance, color, textures etc. Superpixels are more efficient than pixels in case of large scale image processing. In this paper, superpixels are generated by SLIC(simple linear iterative clustering) as known popular. Superpixel characteristics are described by compactness, uniformity, boundary precision and recall. The compactness is important features to depict superpixel characteristics. Each superpixel is represented by Lab color spaces, compactness and texture information. DBSCAN clustering method applied to these feature spaces to segment a color image. To evaluate the performance of the proposed method, computer simulation is carried out to several outdoor images. The experimental results show that the proposed algorithm can provide good segmentation results on various images.