• FLOWER RESEARCH JOURNAL
• /
• v.19 no.1
• /
• pp.55-63
• /
• 2011

This study was carried out to develop new cultivars of Hibiscus species from crosses between introduced interspecific hybrids and cultivars in Hibiscus species. Fruit setting of interspecific crosses of Hibiscus strains was less than 10% and the number of seeds in the fruit was also in low level. Three individuals of specific flower and leaf characteristics were selected from crosses between introduced interspecific hybrid, 'Fujimusme'(♀), and H. syriacus 'Namwon'(♂) in 2004. A new strain, Hibiscus ${\times}$ 'W-26', was selected from the crossing of interspecific hybrid, 'Fujimusme'(♀), and H. syriacus 'Namwon'(♂), which had white flower and narrow separated petal. Hibiscus ${\times}$ 'WRB-2' was selected from the crossing of interspecific hybrid, 'Fujimusme'(♀), and H. syriacus 'Namwon'(♂), which had white flower and blue eye spot. Hibiscus ${\times}$ 'R-141' was selected from crosses between introduced interspecific hybrid, 'Shichisai'(♀) and H. syriacus 'Namwon'(♂), which had large flowers over 13 cm diameter and revealed tall tree type. Hibiscus ${\times}$ 'R-142' was selected from the crossing of interspecific hybrid, 'Shichisai'(♀), and H. syriacus 'Namwon'(♂), which had large flowers over 13 cm diameter and revealed tall tree type. The characteristics were succeded after grafting. Flower of 'R-142' had reddish violet color with red eye spot, whereas its parent had blue and purple flowers.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.453-462
• /
• 2021

A lot of license plate data is required for car number recognition. License plate data needs to be balanced from past license plates to the latest license plates. However, it is difficult to obtain data from the actual past license plate to the latest ones. In order to solve this problem, a license plate recognition study through deep learning is being conducted by creating a synthetic license plates. Since the synthetic data have differences from real data, and various data augmentation techniques are used to solve these problems. Existing data augmentation simply used methods such as brightness, rotation, affine transformation, blur, and noise. In this paper, we apply a style transformation method that transforms synthetic data into real-world data styles with data augmentation methods. In addition, real license plate data are noisy when it is captured from a distance and under the dark environment. If we simply recognize characters with input data, chances of misrecognition are high. To improve character recognition, in this paper, we applied the DeblurGANv2 method as a quality improvement method for character recognition, increasing the accuracy of license plate recognition. The method of deep learning for license plate detection and license plate number recognition used YOLO-V5. To determine the performance of the synthetic license plate data, we construct a test set by collecting our own secured license plates. License plate detection without style conversion recorded 0.614 mAP. As a result of applying the style transformation, we confirm that the license plate detection performance was improved by recording 0.679mAP. In addition, the successul detection rate without image enhancement was 0.872, and the detection rate was 0.915 after image enhancement, confirming that the performance improved.