Jinxing Wang

Purity Identification of Maize Seed Based on Color Characteristics

In order to identify miscellaneous seed from maize seed accurately and rapidly, maize seed purity identification method based on color extracted from the images of both the maize crown and the maize side was proposed for improving maize seed purity. Firstly, segmentation and single extraction were carried on the original image; secondly, the color models RGB and HSV were used to extract multidimensional eigenvectors from the maize crown and the maize side; finally, multidimensional eigenvectors were projected into one-dimensional space through applying Fisher discriminant theory and K-means algorithm was carried on the new color space. The experimental results show that K-means algorithm based on one-dimensional space received through Fisher discriminant theory can effectively identify maize seed purity, and the recognition rate was over 93.75%.

The effects of grain texture and phenotypic traits on the thin-layer drying rate in maize (Zea mays L.) inbred lines

Abstract To explore the relation of maize grain texture and phenotypic traits with grain thin-layer drying rate, we observed the ultra-structure of maize grain, and tested three traits about the maize grain texture and four phenotypic traits. The vitreous part percentage was different (P

Feature Selection for Cotton Foreign Fiber Objects Based on PSO Algorithm

Due to large amount of calculation and slow speed of the feature selection for cotton fiber, a fast feature selection algorithm based on PSO was developed. It is searched by particle swarm optimization algorithm. Though search features by using PSO, it is reduced the number of classifier training and reduced the computational complexity. Experimental results indicate that, in the case of no loss of the classification performances, the method accelerates feature selection.

A Fast Processing Method of Foreign Fiber Images Based on HSV Color Space

Traditionally, it was hard for image segmentation to suit the cotton image segmentation of foreign fibers. To solve this problem, this paper proposed an image segmentation method of foreign fibers based on HSV color space. The value of foreign fibers images’ S channel was enhanced in this method to improve the contrast of foreign fiber and its background which help the subsequent image segmentation. The result of experiment shows that the method could highlight the images of foreign fibers, speed up subsequent image segmentation and realize fast image segmentation.

An Efficient Iterative Thresholding Algorithms for Color Images of Cotton Foreign Fibers

The goal of color image segmentation is to divide the image into homogeneous regions. Thresholding is a commonly used technique for image segmentation. Thresholding assumes that image present a number of components, each of a nearly homogeneous value, and that one can separate the components by a proper choice of intensity threshold. In this paper, we present an efficient iterative algorithm for finding optimal thresholds. In the first step, color images were captured, and the edge of color images were detected by edge detection method. In the second step, color images were converted into a gradient map, and then the regular of experience values were analyzed, at last the best threshold of the gradient map was chosen by selecting the best experience value iteratively. The experiment results indicate that the best threshold selection of the gradient map can precisely segment the high-resolution color images of cotton foreign fibers.

A Smart Multi-parameter Sensor with Online Monitoring for the Aquaculture in China

PH, DO,ORP, EC and water-level are important parameters of the aquaculture monitoring. But the high cost of foreign sensors and high-energy consumption of Chinese sensors make it impossible for wide use in China. This paper uses MCU STM8L152 to realize the ultralow power design. With simple hardware structure design, the cost of the multi-parameter sensor can be reduced .The experiment data of the multi-parameter sensor contrasting with the results obtained by Hach multi-parmeter meter, indicates that the sensor is reliable to monitor the water quality with low cost, high efficiency and good precision.

Research on the Knowledge Based Parameterized CAD System of Wheat and Rice Combine Chassis

In this paper, through using Pro/Toolkit to do secondary development of Pro/E, it completes the parametric modeling of every key parts of rice and wheat combined harvester chassis by using the object-oriented technology, and combines with Microsoft Access database to store the relevant knowledge. Meanwhile, it collects lots of related knowledge about rice and wheat combine harvester chassis from various channels and establishes a knowledge base of key components of the chassis after sorting them which can achieve the purposes of rapid designing chassis.

The Improved DBSCAN Algorithm Study on Maize Purity Identification

In order to identify maize purity rapidly and efficiently, the image processing technology and clustering algorithm were studied and explored in depth focused on the maize seed and characteristics of the seed images. An improved DBSCAN on the basis of farthest first traversal algorithm (FFT) adapting to maize seeds purity identification was proposed in the paper. The color features parameters of the RGB, HIS and Lab color models of maize crown core area were extracted, while H, S and B as to be the effective characteristic vector after data analysis. The abnormal points of different density characteristic vector points were separated by FFT. Then clustering results were combined after local density cluster by DBSCAN. According to the result of test, the method plays a great role in improving the accuracy of maize purity identification.

Research of Dynamic Identification Technology on Cotton Foreign Fibers

Due to the low efficiency, large errors and other practical issues of manual sorting selection method, a new cotton foreign fiber analysis instrument was developed. After fully-smashing by the ginned cotton machine, the uninterrupted uniform cotton layer was formed, and then the image of the flow cotton layer was collected by line scanning camera. Firstly the gray-scale processing is carried on to the original cotton foreign fibers image. Moreover, some other treatment such as adaptive threshold method, filter technique and enhancement processing, are used to complete the image segmentation in order to obtain clear binary image; then hollowed inner point method and neighborhood search method are used to extract the contours in order to obtain the characteristic parameters of foreign fibers. Finally the category identification and weight statistics of foreign fibers is completed based on rough sets theory. It’s proved by experiments that the detection speed of this new instrument can achieve 40m/h and the recognition precision of this analyzer can achieve 90%.

STUDY AND REALIZATION OF IMAGE SEGMENTATION ON THE COTTON FOREIGN FIBERS

A method of foreign fibers image segmentation based on Mean shift, dilation and filtering algorithm is presented. For the representative gray images of hair, chicken feather and mixed foreign fibers, the Mean shift algorithm is used to carry on image segmentation; then dilation and filtering process is carried on to the divided image element. In this way the precise image segmentation of foreign fibers is realized. It’s proved by experiments that the image segmentation method proposed by this article can suppress the noise well, and the segmentation results are satisfied for all kinds of foreign fibers image.