• Title/Summary/Keyword: 양품

Search Result 53, Processing Time 0.021 seconds

3D Film Image Inspection Based on the Width of Optimized Height of Histogram (히스토그램의 최적 높이의 폭에 기반한 3차원 필름 영상 검사)

  • Jae-Eun Lee;Jong-Nam Kim
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.23 no.2
    • /
    • pp.107-114
    • /
    • 2022
  • In order to classify 3D film images as right or wrong, it is necessary to detect the pattern in a 3D film image. However, if the contrast of the pixels in the 3D film image is low, it is not easy to classify as the right and wrong 3D film images because the pattern in the image might not be clear. In this paper, we propose a method of classifying 3D film images as right or wrong by comparing the width at a specific frequency of each histogram after obtaining the histogram. Since, it is classified using the width of the histogram, the analysis process is not complicated. From the experiment, the histograms of right and wrong 3D film images were distinctly different, and the proposed algorithm reflects these features, and showed that all 3D film images were accurately classified at a specific frequency of the histogram. The performance of the proposed algorithm was verified to be the best through the comparison test with the other methods such as image subtraction, otsu thresholding, canny edge detection, morphological geodesic active contour, and support vector machines, and it was shown that excellent classification accuracy could be obtained without detecting the patterns in 3D film images.

Development of Deep Learning Structure to Improve Quality of Polygonal Containers (다각형 용기의 품질 향상을 위한 딥러닝 구조 개발)

  • Yoon, Suk-Moon;Lee, Seung-Ho
    • Journal of IKEEE
    • /
    • v.25 no.3
    • /
    • pp.493-500
    • /
    • 2021
  • In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.

Physiological and Ecological Studies on the Low Temperature Damages of Rice (Oryza sativia L.) (수도의 저온장해에 관한 생리 생태학적 연구)

  • 오윤진
    • KOREAN JOURNAL OF CROP SCIENCE
    • /
    • v.26 no.1
    • /
    • pp.1-31
    • /
    • 1981
  • Experiments were conducted to investigate rice varietal response to low water and air temperatures at different growth stages from 1975 to 1980 in a phytotron in Suweon and in a cold water nursery in Chooncheon. Germination ability, seedling growth, sterility of laspikelets, panicle exertion, discoloration of leaves, and delay of heading of recently developed indica/japonica cross(I/J), japonica, and indica varieties at low air temperature or cold water were compared to those at normal temperature or natural conditions. The results are summarized as follows: 1. Practically acceptable germination rate of 70% was obtained in 10 days after initiation of germination test at 15\circ_C for japonica varieties, but 15 days for IxJ varieties. Varietal differences in germination ability at suboptimal temperature was greatest at 16\circ_C for 6 days. 2. Cold injury of rice seedlings was most severe at the 3.0-and 3.5-leaf stage and it was reduced as growth stage advanced. A significant positive correlation was observed between cold injury at 3-leaf stage and 6-leaf stage. 3. At day/night temperatures of 15/10\circ_C seedlings of both japonica and I/J varieties were dead in 42 days. At 20/15\circ_C japonica varieties produced tillers actively, but tillering of I/J varieties was retarded a little. At 25/15\circ_C, both japonica and I/J varieties produced tillers most actively. Increase in plant height was proportional to the increase in all varieties. 4. In I/J varieties the number of differentiated panicle rachis branches and spikelets was reduced at a day-night temperature of 20-15\circ_C compared to 25-20 or 30-25\circ_C, but not in japonica varieties although panicle exertion was retarded at 20-15\circ_C. The number of spikelets was not correlated with the number of primary rachis branches, but positively correlated with that of secondary rachis branches. 5. Heading of rice varieties treated with 15\circ_C air temperature at meiotic stage was delayed compared to that at tillering stage by 1-3 days and heading was delayed as duration of low temperature treatment increased. 6. At cold water treatment of 17\circ_C from tillering to heading stage, heading of japonica, I/J, and cold tolerant indica varieties was delayed 2-6, 3-9, and 4-5 days, respectively, Growth stage sensitive to delay of heading delay at water treatment were tillering stage, meiotic stage, and booting tage in that order, delay of heading was greater in indica corssed japonica(Suweon 264), japonica(Suweon 235), and cold tolerant indica(Lengkwang) varieties in that order. Delay of heading due to cold water treatment was positively correlated with culm length reduction and spikelet sterility. 7. Elongation of culms and exertion of panicles of rice varieties treated with low air temperature 17\circ_C. Culm length reduction rate of tall varieties was lower than that of short statured varieties at low temperature. Panicle exertion was most severaly retarded with low temperature treatment at heading stage. Generally, retardation of panicle exertion of 1/1 varieties was more severe than that of japonica varieties at low temperature. There was a positive correlation between panicle exertion and culm length at low temperature. 8. The number of panicles was increased with cold water treatment at tillering stage, but reduced at meiotic stage. As time of cold water treatment was conducted at earlier growth stage, culm length was shorter and panicle exertion poorer. 9. Sterility of all rice varieties was negligible at 17\circ_C for three days but 30.3-85.2% of strility was observed for nine-day treatment at 17\circ_C. Among the tested varieties, sterility of Suweon 264 and Milyang 42 was highest and that of Suweon 290 and Suweon 287 was lowest. The most sensitive growth stage to low temperature induced sterility was from 15 to 5 days before heading. There was positive correlation between sterility of rice plants treated with low temperature at meiotic and heading stage. 10. Percentage of spikelet sterility was greatest at cold water treatment at meiotic stage (auricle distance -15~-10cm) and it was higher in 1/1 (Suweon 264, Joseng tongil), japonica (Nongbaek, Towada), and cold tolerance indica(Lengkwang) varieties in the order. Level of cold water and position of young-ear affected on the sterility of varieties at meiotic stage; percentage of spikelet sterility of variety, Lengkwang, of which young-ear was located above the cold water level was high, but that of short statured variety, Suweon 264, of which young-ear was located in the cold water was lower. 11. Percentage of ripened grains was not reducted at 15\circ_C air temperature for three days at full heading stage in all varieties. However, at six-day low temperature treatment Suweon 287, Suweon 264 showed percentage of ripended grains lower than 60%, but at nine-day low temperature treatment all varieties showed percentage of ripened grains lower than 60%. Low temperature treatment of 17\circ_C from 10 days after heading for 20 days did not affect on the ripening of all varieties. 12. Uptake of nitrogen, phosphorous, potassium, calcium, and magnesium in whole plants was higher at average air temperature of 25\circ_C, but concentration of the elements was lower compared to those at 19\circ_C. However, both total uptake and concentration of manganese were higher at 19\circ_C compared to 25\circ_C. 13. Higher application of nitrogen, phosphorus, silicate, and compost increased yield of rice due to increased number of panicles and spike let fertility in cold water irrigated paddy.

  • PDF