• 한국군사과학기술학회지
• /
• 제23권2호
• /
• pp.139-146
• /
• 2020

The camouflage pattern was difficult to distinguish from the surrounding background, so it was difficult to classify the object and the background image when the color image is used as the training data of deep-learning. In this paper, we proposed a red-green color blindness image transformation method using the principle that people of red-green blindness distinguish green color better than ordinary people. Experimental results show that the camouflage soldier's recognition performance improved by proposed a deep learning model of the ensemble technique using the imitated red-green-blind image data and the original color image data.

• Molecules and Cells
• /
• 제39권10호
• /
• pp.750-755
• /
• 2016

Although innate color preference of motile organisms may provide clues to behavioral biases, it has remained a longstanding question. In this study, we investigated innate color preference of zebrafish larvae. A cross maze with different color sleeves around each arm was used for the color preference test (R; red, G; green, B; blue, Y; yellow). The findings showed that 5 dpf zebrafish larvae preferred blue over other colors (B > R > G > Y). To study innate color recognition further, tyrosinase mutants were generated using CRISPR/Cas9 system. As a model for oculocutaneous albinism (OCA) and color vision impairment, tyrosinase mutants demonstrated diminished color sensation, indicated mainly by hypopigmentation of the retinal pigment epithelium (RPE). Due to its relative simplicity and ease, color preference screening using zebrafish larvae is suitable for high-throughput screening applications. This system may potentially be applied to the analysis of drug effects on larval behavior or the detection of sensory deficits in neurological disorder models, such as autism-related disorders, using mutant larvae generated by the CRISPR/Cas9 technique.