Time filter

Source Type

Wang H.-P.,Shandong University | Wang H.-P.,Shandong Economic Management Institute | Feng X.-Y.,Shandong University | Li L.,Shandong University
Shenzhen Daxue Xuebao (Ligong Ban)/Journal of Shenzhen University Science and Engineering | Year: 2012

The recognition of white foreign fibers in lint has always been a difficulty in cotton detection. Because the gray values of white foreign fibers are approximate to lint, it is very difficult to recognize white foreign fibers just by gray value. Through the texture feature analysis of lint and white foreign fibers, it was found that the entropy of gray level co-occurrence matrix (GLCM) could be used to judge whether there were white foreign fibers in lint. According to the gray value characteristics of lint and white foreign fibers, this paper compressed the gray level piecewise and nonuniformly. Thus, the threshold segmentation method based on texture features was put forward, and white foreign fibers were recognized from lint by means of the entropy threshold segmentation method. Results showed that compressing the gray level piecewise and non-uniformly could effectively reduce the computing time and guarantee the accuracy of recognition at the same time, and this algorithm can effectively improve the speed and precision of white foreign fibers recognition. Source

Wang H.,Shandong University | Wang H.,Shandong Economic Management Institute | Feng X.,Shandong University | Li L.,Shandong University
Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering | Year: 2012

The white foreign fibers detection is a difficult problem of the lint online detection. Through the analysis of the 2D gray histogram of white foreign fibers and lint, the two-dimensional Otsu algorithm was improved. This improved algorithm considered the probabilities of the counter-diagonal area in 2D gray histogram when the probabilities of objective and background was calculated, and reduced the range of threshold. The results indicated that the improved algorithm of 2D effectively enhanced the accuracy and real-time property of segmentation comparing with the one-dimensional Otsu algorithm and the fast two-dimensional Otsu algorithm. The improved algorithm has been successfully used in practical production. Source

Wang H.,Shandong University | Wang H.,Shandong Economic Management Institute | Feng X.,Shandong University | Li L.,Shandong University
Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering | Year: 2013

The initial moisture content (dry basis) of seed cotton picked by machine is very high, occasionally exceeding 18%. However, research has shown that the moisture content between 6.5% and 8.5% is optimal for processing seed cotton. To obtain a higher drying efficiency and better drying quality of seed cotton before cleaning and ginning, it is necessary to control drying conditions within a narrow range. However, many cotton gins currently set and control the temperature of seed-cotton drying equipment based on personal judgments, which is inaccurate and risky. Based on a large number of experiments on hot air drying characteristics, this paper developed a hot-air drying model of seed cotton and solved the above problem. We used quadratic regression in a 3×3 factorial experimental design to model the effects on the final moisture content of three factors (hot air temperature, seed cotton feed rates and initial moisture content) and three levels of each factor. Results show that all three factors significantly influence the drying rate of seed cotton. In addition, the first 15 s of the drying process exhibits a faster drying rate, after which the drying rate rapidly decreases. Curve fitting with a monomial diffusion model, Page's drying model, and a quadratic polynomial model, we found that the monomial diffusion model fit the data more closely (R2=0.9549) than the other models. Analyzing the drying process more closely, we determined that our hot-air drying model of seed cotton could provide a theoretical basis for adjusting the control parameters in real time on the drying equipment. Of the three control parameters tested, the final moisture content of seed cotton is most sensitive to (a) the initial moisture content, (b) cotton feed rate, and (c) hot-air temperature, in decreasing order of sensitivity. The hot-air drying model developed in this paper has been applied in real-time control of seed cotton drying in actual production, confirming its utility in process effectiveness and consistency, energy efficiency, and net economic benefit to the ginner. Source

Hu S.,Shandong Economic Management Institute
Proceedings of the 2012 International Conference on Industrial Control and Electronics Engineering, ICICEE 2012 | Year: 2012

The spring up of large numbers of partial-duplicate images on the internet brings a new challenge to the image retrieval systems. Rather than taking the image as a whole, researchers bundle the local visual words by MSER detector into groups and add simple relative ordering geometric constraint to the bundles. Experiments show that bundled features become much more discriminative than single feature. However, in order to achieve more discriminative power, the bundle should be carefully extracted with elaborate contour, which can separate different objects and exclude irrelative visual words. In this paper, we propose a novel partial-duplicate image retrieval scheme based on regions extract by saliency analysis. In addition, to increase the discriminative power and robustness for coping with various transformations such as flip and rotation, the visual words detected in the region are further restrained by an affine invariant constraint. The affine invariant constraint employs the area ratio invariance property of affine transformation to build the affine invariant matrix for bundled visual words. Experimental results on the internet partial-duplicate image database verify the effectiveness of our approach. © 2012 IEEE. Source

Wang H.,Shandong University | Wang H.,Shandong Economic Management Institute | Feng X.,Shandong University | Wang N.,Shandong Economic Management Institute | Shi J.,Shandong Economic Management Institute
Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering | Year: 2013

In order to improve the recognition accuracy of white foreign fibers in cotton, a detection algorithm of white foreign fibers based on improved chaos particle swarm optimization was proposed in this paper. In this algorithm, the image was divided into different classes according to the grey value of image pixels. The variances between adjacent classes were thought of as a particle. All of these particles constituted a particle swarm. The maximum variances between classes were thought of as a fitness function. Therefore, the chaotic particle swarm optimization (PSO) algorithm was applied to image segmentation. The standard particle swarm optimization was easy to fall into a local optimum. Given this problem, this algorithm took the sliding window technology to determine if it falls into a local optimum. This algorithm contrasted the average population fitness in the sliding window with the current population fitness in the sliding window. If the current population fitness was similar to the average population fitness, the algorithm was thought not to fall into the local optimum, continued to evolve, and the sliding window starting position was moved to the current location, the size was set to 1, or it was thought to fall into a local optimum. If the algorithm fell into a local optimum, it used a chaotic mechanism to initialize the population to jump out of the local optimum. The starting position and size of the sliding window dynamic changed according to the judgment result. This method effectively solved the problems of the standard particle swarm optimization (PSO) algorithm that it fell well into a local optimum. In order to test the algorithm, this paper also set up a detection device, including an acA1300-30 gc type color plane array CCD camera, M0814 type lens, HLV-24-1220 type LED light source, and PCI-8ADPF type data acquisition card, then it selected five kinds of common white foreign fibers such as the pieces of plastic bags, white hair, feathers, threads, and synthetic fibers. Each kind had 100 samples. These samples were mixed in the cotton and were photographed. The test identified 500 pictures which contained white foreign fibers. The results showed that the rate of detecting pieces of plastic bags, white hair, feathers, threads, and synthetic fibers could reach 98%, 97%, 100%, 100%, and 98%, and the average rate was 98.6%. By comparison with the standard two-dimensional Otsu algorithm segmentation test found in the fine segmentation of different fibers and fiber and cotton overlap, the algorithm had a higher degree of precision segmentation than the standard two-dimensional Otsu algorithm. Source

Discover hidden collaborations