• Journal of Semiconductor Engineering
• /
• 제2권1호
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.

• 한국정보과학회논문지:시스템및이론
• /
• 제35권7호
• /
• pp.340-353
• /
• 2008

화풍을 효과적이고 객관적으로 기술하는 한 방법으로 팔레트 추출에 대한 수학적 모델을 제시한다. 이 모델에서는 팔레트를 허용 오차 범위 내에서 회화 작품의 영상을 표현할 수 있는 주요 색상의 집합으로 정의하고 색상 그룹핑과 주요 색상 추출의 두 단계를 거처 팔레트 색상을 추출한다. 색상 그룹핑은 주어진 회화에 대해 적응적으로 색의 분해능을 조절하여 각 회화 작품을 이루는 기초 색상을 추출하며 다음 주요 색상 추출 단계에서 이것과 이것이 차지하는 영역에 대한 정보를 바탕으로 K-Means 클러스터링 알고리즘을 적용하여 팔레트를 얻는다. 실험을 통해 유명 화가의 작품을 대상으로 RGB와 CIE LAB 색상 모델을 사용하여 추출한 팔레트를 3차원 색 공간에 표시하였다. 팔레트 색상의 거리를 사용한 화가 분류 실험과 실사 영상의 색채 변환 실험 통해 이 방법이 화풍 분석과 그래픽 분야에 적용될 수 있음을 확인하였다.

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.143-151
• /
• 2021

The enormous prevalence of transferring official confidential digital documents via the Internet shows the urgent need to deliver confidential messages to the recipient without letting any unauthorized person to know contents of the secret messages or detect there existence . Several Steganography techniques such as the least significant Bit (LSB), Secure Cover Selection (SCS), Discrete Cosine Transform (DCT) and Palette Based (PB) were applied to prevent any intruder from analyzing and getting the secret transferred message. The utilized steganography methods should defiance the challenges of Steganalysis techniques in term of analysis and detection. This paper presents a novel and robust framework for color image steganography that combines Linear Congruential Generator (LCG), simulated annealing (SA), Cesar cryptography and LSB substitution method in one system in order to reduce the objection of Steganalysis and deliver data securely to their destination. SA with the support of LCG finds out the optimal minimum sniffing path inside a cover color image (RGB) then the confidential message will be encrypt and embedded within the RGB image path as a host medium by using Cesar and LSB procedures. Embedding and extraction processes of secret message require a common knowledge between sender and receiver; that knowledge are represented by SA initialization parameters, LCG seed, Cesar key agreement and secret message length. Steganalysis intruder will not understand or detect the secret message inside the host image without the correct knowledge about the manipulation process. The constructed system satisfies the main requirements of image steganography in term of robustness against confidential message extraction, high quality visual appearance, little mean square error (MSE) and high peak signal noise ratio (PSNR).

• 한국전자통신학회논문지
• /
• 제15권1호
• /
• pp.1-8
• /
• 2020

사람의 손길이 닿지 않는 곳에 위험 상황이 발생하였다면 무인 비행체를 활용하여 그 상황의 규모와 위치를 파악하여 더 큰 피해를 줄일 수 있다. 이러한 점에서 착안하여 본 논문에서는 무인 비헹체가 원활한 호버링을 수행할 수 있도록 Beta Flight를 사용하여 Roll, Pitch, Yaw의 최솟값과 최댓값을 설정한 후 센서의 작동을 감지하여 기체의 기울기의 변화에 따라 센서의 PID 값을 설정하여 수평이 유지될 수 있도록 오차를 최소화하여 안전한 호버링을 할 수 있도록 하였다. 또한, 카메라는 Open CV를 활용하여 라즈베리파이 프로그램을 설치한 후 HSV 색상표를 활용하여 화원과 가장 가까운 색인 붉은색을 제외한 나머지 부분을 흑백 처리하는 필터링을 씌워 공중에서 감지한 영상을 실시간으로 수신할 수 있도록 하였다. 최종적으로 0.5~5m 높이에서 호버링이 가능하였으며 5m 높이에서 반지름이 5cm 인 붉은색 원을 인식할 수 있음을 확인하였다.

• 한국의상디자인학회지
• /
• 제18권2호
• /
• pp.115-125
• /
• 2016

This study analyzes the characteristics of the motifs and colors in flower and bird paintings which contain and present Korea's unique aesthetics based on its richest data among all other types of Korean folk paintings. With a theoretical exploration of folk paintings and an analysis of the motifs and colors, textile design with an aim to present highly valued korean modern fashion design was developed. Two hundred and seventy flower and bird paintings were selected from relevant materials, resulting in an extraction of 5,068 colors. A palette of representative colors was made based on densely distributed hues and tones. The research can be summarized as follows: Flower and bird paintings contain flowers, birds, trees and animals and the motifs in the paintings stand for spirituality, philosophies from different times and other symbols of our nation. Each of the motifs in these paintings is a prayer for good luck, especially conjugal harmony and fecundity to bring about happiness and richness. Colors in flower and bird paintings are characteristic of the order: YR(25.5%)>R(19.2%)>Y(10.6%)>PB(9.2%)>G(7.9%), with low-chromatic YR and highly bright R taking up a larger percent. The order of tones is: d(13.5%)>dk (10.5%)>s(10.4%)>dkg(10.0%)>sf(9.1%)and the tone is dark in general. YR, taking up the largest percent, was dull, light, and soft. As for the achromatic colors, the order is: W(5.2%)>Gy(1.9%)>Bk(0.7%). Based on the above analyzed color data, those colors which were high in their hue and tone were extracted to present representative colors. In this way, representative colors like yellow, yellowish red, red, green, and purplish blue were extracted. This was the basis to present motifs and colors originating from subjects of folk paintings in various patterns using Illustrator CS6, to create modern fashion design.