• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.3
• /
• pp.25-33
• /
• 2007

In this paper, I propose a method which can enhance the visual quality of IRST images based on a loaded location in ship and an AOS. The IRST adjusts an AOS to detect targets with various altitudes because of its narrow vertical field of view and offers various functions to enhance images with its low contrast. In the proposed method, images are divided into two regions of sea and sky on the basis of the horizon after establishing relation between an AOS and a horizon location within an image. As a result, image enhancement of the proposed method is performed adaptively according to the divided region while that of conventional method is performed for entire image without the region division. Simulation results show that the proposed method represents higher visibility compared with conventional one.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.367-369
• /
• 2022

In this paper, the predicted results were confirmed by label mapping for each class while implementing multi-class image classification to confirm accurate results for images in which the trained model failed classification. A CNN model was constructed and trained using Kaggle's Intel Image Classification dataset, and the mapped label values of multiple classes of images and the values classified by the model were compared by label mapping the images of the test dataset.

• Journal of Biomedical Engineering Research
• /
• v.22 no.3
• /
• pp.231-239
• /
• 2001

This paper proposes a region segmenting method for the Pap-smear image. The proposed method uses a pixel classifier based on neural network, which consists of four stages : preprocessing, feature extraction, region segmentation and postprocessing. In the preprocessing stage, brightness value is normalized by histogram stretching. In the feature extraction stage, total 36 features are extracted from $3{\times}3$ or $5{\times}5$ window. In the region segmentation stage, each pixel which is associated with 36 features, is classified into 3 groups : nucleus, cytoplasm and background. The backpropagation network is used for classification. In the postprocessing stage, the pixel, which have been rejected by the above classifier, are re-classified by the relaxation algorithm. It has been shown experimentally that the proposed method finds the nucleus region accurately and it can find the cytoplasm region too.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.742-751
• /
• 2005

This paper proposes a novel text image watermarking algorithm based on word classification. The words are classified into K classes using simple features. Several adjacent words are grouped into a segment. and the segments are also classified using the word class information. The same amount of information is inserted into each of the segment classes. The signal is encoded by modifying some inter-word spaces statistics of segment classes. Subjective comparisons with conventional word-shift algorithms are presented under several criteria.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.10
• /
• pp.1561-1570
• /
• 1989

In this paper, we propose an image coding scheme which combines the Laplacian pyramid structure and a hierarchical finite state classified vector quantizer in the DCT domain, namely FSDCT-CTQ. First, an optimal bit allocation problem for fixed rates DCT-CVQ on the Laplacian pyramid structure is described. In an asymptotic case, with an optimal bit allocation, a coding gain over scalar quantization of each Laplacian plane is derived. Second, it is experimentallhy shown that the Laplacian pyramid structure provides a considerable codng gain in the sense of total MMSE (minimum mean squared error). Finally, we propose an FS-DCT-CVQ which exploits the hierarchicla correlation between the Laplacian planes. Simulation results on real images show that the proposed coding scheme can reconstruct an image with 30.33 dB at 0.192 bpp, 32.45 dB at 0.385 bpp, respectively.

• Fibers and Polymers
• /
• v.1 no.1
• /
• pp.45-54
• /
• 2000

Impact behaviors of the large deformable composites of Kevlar fiber reinforced composites of different preform structures have been investigated. An analytic tool was developed to characterize the impact behavior of the Kevlar composites. The image analysis technique, and deply technique were employed to develop energy balance equation under impact loading. An energy method was employed to establish the impact energy absorption mechanism of Kevlar multiaxial warp knitted composites. The total impact energy was classified into four categories including delamination energy, membrane energy, bending energy and rebounding energy under low velocity impact. Membrane and bending energy were calculated from the image analysis of the deformed shape of impacted specimen and delamination energy was calculated using the deplying technique. Also, the impact behavior of Kevlar composites under high velocity impact of full penetration of the composite specimen was studied. The energy absorption mechanisms under high velocity impact were modelled and the absorbed energy was classified into global deformation energy, shear-out energy, deformation energy and fiber breakage energy. The total energy obtained from the model corresponded reasonably well with the experimental results.

• Journal of Korea Multimedia Society
• /
• v.21 no.3
• /
• pp.333-341
• /
• 2018

In this paper, we propose an algorithm to automatically detect gait's joints. The proposed method classifies gait's types into front gait and flank gait so as to automatically detect gait's joints. And then according to classified types, the proposed applies joint extracting algorithm to input images. Firstly, we split input images into foreground image using difference images of Hue and gray-scale image of input and background one and extract gait's object. The proposed method classifies gaits into front gait and flank gait using ratio of Face's width to torso's width. Then classified gait's type, joints are detected 10 at front gait and detected 7~8 at flank gait. The proposed method is applied to the camera's input and the result shows that the proposed method automatically extracts joints.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.5 no.2
• /
• pp.24-33
• /
• 1987

This study aims at obtaining more effective image processing techniques and more accurately classified image in the sphere which uses remotely sensed data. For this practice, the result of land use classification compounding summer scene with winter scene and the classified result of summer scene were compared, analyzed. From the upper analysed results, we found that Bitemporal Classification technique and $tan^{-1}$transformation were effective. Particularly, dividing crop class into two classes of farmland and field was more possible by appling Bitemporal Classification technique.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.32 no.11
• /
• pp.1771-1781
• /
• 2008

The purpose of this study was to classify the casual image by clothing design elements. This research was done by survey method with 30 kinds of casual 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. Casual image was classified by 6 factors. Those were classic-casual, modern-casual, romantic-casual, vintage-casual, sexy-casual and active-casual images. 2. Classic-casual image was well-expressed by A silhouette, fit, chromatic and chromatic color coordinations and hard texture. Modern-casual image was well-expressed by H silhouette, fit and achromatic and achromatic color coordinations. Romantic-casual image was well-expressed by A silhouette, fit and soft texture. Vintage-casual image was well-expressed by H silhouette, combination apparel-fit, chromatic and chromatic color coordinations and fade-out texture. Sexy-casual image was well-expressed by fitted silhouette, tight apparel-fit and combination texture. 3. Casual image was positioned into mostly dynamic and modern on image scale.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.8
• /
• pp.1222-1233
• /
• 2006

The purpose of this study was to classify the modern image by clothing design elements. This research was done by survey method with 25 kinds of modern image photos selected in fashion magazines. The data was analyzed by Reliability Analysis, Factor Analysis, MANOVA, One-Way ANOVA, Duncan's test and MDS. The results of this study are as follows: 1. modern image was classified by 5 factors. Those were sexy-modern, elegant-modern, natural-modern, mannish-modern and minimal-modern images. 2. Sexy-modern image was well-expressed by chromatic and chromatic color coordinations. Elegant-modern image was well-expressed by fitted silhouette, fit and achromatic and chromatic color coordinations. Natural-modern image was well-expressed by A silhouette, loose apparel-fit, chromatic and chromatic coordinations and soft texture. Mannish-modern image was well-expressed by H silhouette, loose apparel-fit, chromatic and chromatic color coordinations and hard texture. Minimal-modern image was well-expressed by H silhouette, tight or loose apparel-fit and soft texture. 3. modern image was positioned into mostly hard or masculine on image scale.