اتصال به اینترنت شما ضعیف یا قطع است.

Price corn seeds + Wholesale buying and selling

Corn ear test is very important in sustainable corn breeding. Test indexes, mainly using SIFT-based panoramic photography, include height, radii, rows, and the number of corn kernels which can help in learning to breed new and fine corn varieties. These corn characteristics are typically collected by traditional manual weighing, which is difficult to meet the testing requirements of high-performance corn husks. Corn, a staple food crop, is a valuable source of many foods and products. In 2019, the global maize crop is expected to reach 1.106 billion tons, and China’s maize planting has reached 0.65 billion hectares. The immediate task is to make better use of the limited sown areas for better quality and higher maize yields. The use of genetic breeding technology to improve corn kernel tests (height, radius, rows and number of kernels and seedlings) is an important means of advanced corn breeding. It is also the basis for evaluating the performance of suitable maize crops under different conditions and for growing the best varieties. Traditional manual surveying now relies on hiring many workers to count and weigh corn, which is time-consuming and subjective. Due to the low efficiency and high cost of traditional manual measurements, researchers are turning to using machine vision technology to identify and analyze corn, but there are very few methods for nondestructively measuring corn husk. Maize testing technology based on machine vision and optical imaging has become an attractive platform for high yield maize production and is gaining increasing interest. The aim of this study was to implement corn husk detection using optical image analysis by constructing an optical image acquisition system. The height and length measurements were calculated based on the rotation angle of the device and the ear length of each image sequence, and the ear and line measurements were obtained using a SIFT-based optical image. Corn ear tests based on the lateral image can be classified according to the number of husk features, that is, the phenotypic method of computing single and multiple images. The results showed that the accuracy of each value was above 90.00%. Zhou et al. (2015) obtained 3D phenotypic parameters of calluses using 2D imaging and combined callus color characteristics with callus biological laws to develop a model. The average measurement speed of the test system was 32.30 kernels/min.

The zero-error rate of the cobs and kernels series was above 93.00%. By obtaining the artificially counted number of nodes and the number of root nodes in a single row in a randomly selected central cylinder region, the total number of root nodes after peeling was calculated. Although the method required considerable human intervention, it was easy to perform, and for 23 grains of corn, an error of -7.67% to +8.60% was obtained. From a corn husk imaging perspective, although the single image estimation method performs well, it can easily lead to inaccurate measurement results and poor stability due to incomplete information about the entire ear surface. For the method of estimating multiple phenotypes, it can improve the accuracy, but the complexity of the method is high due to the redundant information about the corn husk surface. Panoramic photography is basically a complex image of an object. Beautiful images are usually captured with a rotary lens camera, but the equipment is expensive and cumbersome to use. For corn husk experiments using optical imaging, Wang et al. (2013) rotated a corn husk by using an angle time interval to capture a sequence of images.

The SIFT algorithm was then used to extract the characteristic points of the image. The points were then aligned on adjacent images, and relative motion between the two images could be described using homography. Depending on the direction of motion, when consistency detection was performed and outliers were removed, two images were registered in the same matching process. A dynamic programming technique was used to identify the suture line, and irrelevant regions in the two images adjacent to the suture line were trimmed to obtain a composite image. This process lasted about 30 seconds for each corn. The experimental results showed that, under the condition of a power level of α = 0.05, there was no significant difference between the method and the manual calibration, but a subtle variation of the values ​​still existed in some parts of the panorama, n 'the system had enormous flaws. Based on a vertically oriented industrial grid, Du et al. (2018) collected a single dataset of a corn husk consisting of side-view images at different locations, extracted the smallest distortion area in the middle of the corn husk, and stitched a transparent model of the ear surface. The imaging system efficiency was 12 cores/min, and the phenotype efficiency was 4 cores/min. The results show that the accuracy of length and number of lines can reach 99.00% and 98.89%, respectively.

However, the number of sequential images was too large, and the stitched horizontal images had a clear displacement, which may affect the subsequent experimental work. The capturing device of panoramic imageTo image a single ear of corn from the periphery and shoot around the ear in a constant sequence, this study selected a stepper motor and a single-chip microcomputer as the main control components for sequence capture. pictures of corn. Sequence image processing using lab color space Natural color photographs are easily affected by artificial light, glare, and shadows and are therefore very sensitive to glare. However, the images in the Lab color space are not affected by such interference, and the main color of the image sequences in the corn patch is yellow. The earpiece is easily distinguishable from the background using the Lab color spot. Therefore, a nuclear classification based on the Lab dye position was chosen. Since the RGB color space cannot be converted directly to the Lab color space, the RGB color space must first be converted to the XYZ color space, which provided the necessary conditions for the subsequent partitioning of the corn patch.

How useful is this article to you?

Average Score 5 / Number of votes: 1

Comments (0 Comments)

💰 Tenfold your income 💎