Software Application in Machine Vision Investigation of Agricultural Seeds Quality

Ola, Daniel; Mănescu, Mihai; Cristea, Luciana; Budde, Jörn; Hoffmann, Thomas

doi:10.4028/www.scientific.net/AMM.436.463

Paper Titles

Numerical Sliding Mode Control for a DC-DC Buck Converter
p.427

Universal Communication Node for Building Automation Systems
p.435

Adaptive Control System for Drill Machine
p.445

An Agent Infrastructure For the Human Driver Assistant
p.451

Software Application in Machine Vision Investigation of Agricultural Seeds Quality
p.463

Developing an Interface for a Research Program
p.474

Quality Modeling Framework for Service Composition. An Indoor Air Quality Monitoring System Case Study
p.480

Semantic Middleware Architecture
p.488

A Holistic Vision of Medical Services and Information Support System Based on E-Healthcare Framework
p.497

HomeApplied Mechanics and MaterialsEngineering Decisions and Scientific Research in...Software Application in Machine Vision...

Software Application in Machine Vision Investigation of Agricultural Seeds Quality

Abstract:

The paper tries to analyze the possibilities of classification of hemp fiber plant seeds in order to provide an image recognition sorting system that can estimate the quality of the fiber hemp seeds destined for human consumption. Systems that can optically grade cereal grains are already available in the agricultural industry. The automatic classification systems for seeds take in consideration the size, shape, color and texture in order to assess the quality of nutritional seeds.This work investigates the classification possibilities of image systems using photo images acquired by an RGB camera. The article presents the experimental stand and devices used for the image analysis of the fiber hemp seeds probes. The method for the selection of the representative pixels of the quality seeds is described and finally the results for the classification of the ratio of ripe seeds versus unripe seeds are presented in graphs. Conclusions are formulated and discussed.

Info:

Periodical:

Applied Mechanics and Materials (Volume 436)

Main Theme:

Engineering Decisions and Scientific Research in Aerospace, Robotics, Biomechanics, Mechanical Engineering and Manufacturing

Edited by:

Adrian Olaru

Pages:

463-473

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.436.463

Citation:

D. Ola et al., "Software Application in Machine Vision Investigation of Agricultural Seeds Quality", Applied Mechanics and Materials, Vol. 436, pp. 463-473, 2013

Online since:

October 2013

Authors:

Daniel Ola, Mihai Mănescu, Luciana Cristea, Jörn Budde, Thomas Hoffmann

Keywords:

Color Histogram, Pixel Intensity Level, Plant Seeds, White Balance

Export:

RIS, BibTeX

Price:

$41.00

Permissions:

Request Permissions

Add to Cart

References

[1] GRANITTO, Pablo M.; VERDES, Pablo F.; CECCATTO, H. Alejandro. Large-scale investigation of weed seed identification by machine vision. Computers and Electronics in Agriculture, 2005, 47. Jg., Nr. 1, S. 15-24.

DOI: https://doi.org/10.1016/j.compag.2004.10.003

[2] GRANITTO, Pablo M., et al. Weed seeds identification by machine vision. Computers and Electronics in Agriculture, 2002, 33. Jg., Nr. 2, S. 91-103. http: /dx. doi. org/10. 1016/S0168-1699(02)00004-2.

DOI: https://doi.org/10.1016/s0168-1699(02)00004-2

[3] WU, Ji-hua; LIU, Yan-de; OUYANG, Ai-guo. Research on Real Time Identification of Seed Variety by Machine Vision Technology [J]. Journal of Transcluction Technology, 2005, 4. Jg., S. 015.

[4] DELL'AQUILA, A. Towards new computer imaging techniques applied to seed quality testing and sorting. Seed Science and Technology, 2007, 35. Jg., Nr. 3, S. 519-538.

DOI: https://doi.org/10.15258/sst.2007.35.3.01

[5] SHAHIN, M. A.; SYMONS, S. J. A machine vision system for grading lentils. Canadian Biosystems Engineering, 2001, 43. Jg., S. 7. 7-7. 14.

[6] URENA, R.; RODRIGUEZ, F.; BERENGUEL, M. A machine vision system for seeds quality evaluation using fuzzy logic. Computers and Electronics in Agriculture, 2001, 32. Jg., Nr. 1, S. 1-20.

DOI: https://doi.org/10.1016/s0168-1699(01)00150-8

[7] MAJUMDAR, S.; JAYAS, D. S. Classification of bulk samples of cereal grains using machine vision. Journal of Agricultural Engineering Research, 1999, 73. Jg., Nr. 1, S. 35-47.

DOI: https://doi.org/10.1006/jaer.1998.0388

[8] LUO, X.; JAYAS, D. S.; SYMONS, S. J. Identification of damaged kernels in wheat using a color machine vision system. Journal of cereal science, 1999, 30. Jg., Nr. 1, S. 49-59.

DOI: https://doi.org/10.1006/jcrs.1998.0240

[9] . ] MATTHÄUS, B.; BRÜHL, L. Virgin hemp seed oil: An interesting niche product. Eur. J. Lipid Sci. Technol., 2008, 110 Jg., S. 655–661.

DOI: https://doi.org/10.1002/ejlt.200700311

[10] . ]Information on http: /www. agriculture. gov. sk. ca/Default. aspx?DN=e60e706d-c852-4206-9959-e4b134782175.

Paper TitlePages

Color Image Region Growth Segmentation Integration of Normalized Cut

Authors: Xiao Ying Wu, Li Juan Ma, Zhao Feng Li, Shi Tao Yan

Abstract: This paper solves that image segmentation result is not consistent with human visual perception or too broken. First of all, based on the continuity of image features, appropriate human vision, calculated the similarity of color image pixel as Eq.2 in HSV space to grow region, then made the regional merge, using normalized-cut segmentation method as Eq.4 and Eq.5 to eliminate over-segmentation phenomenon. In this paper, experimental results shows that the segmentation can be achieved very good results as Fig.1, and parts of the method can be applied in other segmentation to solve over segmentation. This method on color images as the research object is different from other methods on gray images, the selection of seeds and achieves these automatic that differ from general algorithms, presents a new implementation to solve over-segmentation.

139

An Image Scrambling Method Based on Chaotic Sequence and Space-Bit-Plane Operation

Authors: Rui Liu, Xiao Ping Tian

Abstract: Image scrambling is an important technique in digital image encryption and digital image watermarking. This paper proposes a new image scrambling method, which based on chaotic sequence and space-bit-plane operation (SBPO). First, every eight pixels from different areas of image were selected according to chaotic sequence, and grouped together to form a collection. Second, the SBPO was performed in every collection and built eight pixels of the image with new values. The scrambling image was generated when all pixels were processed. This method can scramble image not only based on the pixel’s position but also the value and their corresponding probability. The experimental results show that this scrambling method possesses perfect confusion properties and it can resist various attacks.

231

A New Chaotic Image Scrambling Scheme Based on Spatial Bit-Level Map

Authors: Rui Liu

Abstract: Image scrambling is an important technique in digital image encryption and digital image watermarking. This paper proposes a new image scrambling algorithm based on chaotic sequence and spatial bit-level map. First, I used Logistic chaotic sequences to rearrange digital image pixels into one-dimensional (1-D) sequence, then the value of each pixel in the sequence was decomposed into k-bits which constituted a two-dimensional (2-D) bit matrix. Second, the spatial bit-level map was performed in the 2-D bit matrix to generate pixels with new values. Finally, the scrambling image was generated according to these pixels. This algorithm can scramble image based on the pixel’s position and the value and their corresponding probability. The experimental results show that this scrambling algorithm possesses perfect confusion properties and it can resist various attacks. Also it can apply to non-square image.

2589

The Real Time System of Hair Detection in Mushroom Based on Computer Vision

Authors: Tong Qiang Li, Cai Feng Zheng, Jian Peng Gan

Abstract: By analysing the Mushroom image, the paper puts forward a kind of line-structure extraction algorithm combination of local gray value and continuity of line direction .After the operations in many aspects of basis image processing, such as gray-scale, denoising , segmentation, contour detection and morphological, this article has developed a set of hair detection system based on computer vision for the Mushroom. The experimental results show this system could well meet the actual needs, and has a broad market prospect.

1199

A Simple Algorithm for Video Object Tracking

Authors: Zhao Xia Fu, Li Ming Wang

Abstract: As one of the crucial issues of computer vision, video object tracking is widely used in many applications, such as visual surveillance, human-computer interaction, visual transportation, visual navigation of robots, military guidance, etc. The existing object tracking algorithms in engineering applications have the huge amount of computation, which can not meet the needs of real-time system applications, and the tracking accuracy is not high. So a simple and practical video object tracking algorithm is proposed in this paper. The Otsu algorithm is used for image binarization to filter the background, and the object edge is further processed based on mathematical morphology, and thus the tracking object is more clearly. The centroid weighted method determines the location of the center of the object only by one step calculation, which makes the location more accurate. The experimental results show that the algorithm of the paper is effective for detecting and tracking of a moving object in a static scene and it has a low complexity.

1552