Assessing exterior egg quality indicators using machine vision

ABSTRACT

1. The objective of this study was to develop a machine vision method for analysing exterior parameters of chicken eggs to automate the stage of primary sorting.

2. The developed algorithm based on predetermined thresholds calculated egg quality indicators, including geometric dimensions, shape index and the mottling grade. The algorithm was implemented with an experimental setup that combined the image-based and the candling methods. A total of 400 egg samples were analysed.

3. Comparison of results of the algorithm with those obtained using the traditional manual method showed that mean value of radii values difference was 0.095 ± 0.058 mm for the sharp and 0.080 ± 0.047 mm for the blunt end of the egg, with standard deviations of 0.58 mm and 0.49 mm, respectively.

4. The correlation coefficient between the shape index values determined by the two methods was 0.93; the standard deviation of absolute differences between corresponding values was 1.05%.

5. The results of mottling grade estimation were compared using F-measure and confusion matrix.

6. The results allow the possibility to perform the assessment of egg exterior quality factors in an automatic mode, independent of the expertise of a grader.     

A computer vision system for oocyte counting using images captured by smartphone

This work proposes a computer vision procedure for counting Twospot astyanax (Astyanax bimaculatus) oocytes in Petri dishes using images captured by smartphone. First, the proposed procedure uses simple linear iterative clustering (SLIC) to divide the images into groups of pixels (superpixels). Then, based on their color and space characteristics, the images are classified into light background, dark background, dirt, or oocyte by a machine learning algorithm. Five different types of machine learning algorithms were tested: support vector machines (SVM), decision trees using the algorithm J48 and random forest, k-nearest neighbors (k-NN), and Naive Bayes. To train the algorithms, 8.578 superpixels were classified by an expert into oocyte (n = 354), dirtiness (n = 651), dark background (n = 3.622), and light background (n = 3.951). Of the five learning algorithms, SVM obtained the best result with 97% correct oocyte recognition. Given the wide availability of smartphones, we therefore conclude that the presented procedure can be a valuable tool in future experiments and studies on fertilization and hatching success in Twospot astyanax.     

基于机器视觉的玉米秸秆行实时定位机器人设计

为了实现机器人玉米秸秆行的精确定位,对耕作玉米机器人的结构进行了改进,并提出了一种基于泰勒级数展开式的RSSI定位方法,提高了机器人玉米秸秆行的定位精度。定位系统使用高清晰度的摄像机采集图像,并采用PID闭环反馈的方式控制机器人的位移,利用PC主控端图像处理,实现了实时定位功能。为了验证机器人玉米秸秆行定位的可靠性,采用田间试验的方法对机器人的性能进行了测试。结果表明:RSSI定位方法的定位精度较高,且图像处理系统可以准确地标定玉米秸秆行,实现机器人在玉米田中的精确定位,避免了机器人在作业过程中对农作物造成损害。     

基于机器视觉的饲料生产智能包装系统设计与应用研究

为提高饲料生产订单的包装效率、智能化程度、降低包装成本,文章基于机器视觉,从硬件选择与软件设计两个层面设计饲料生产智能包装系统。采用AutoMod软件对饲料生产智能包装系统进行仿真试验,检验整个包装系统效果。结果表明,该智能包装系统包装效率高、关键设备利用率高、系统可靠性、可行性良好。     

计算机视觉技术在智慧羊场中的研究进展

智慧羊场具有科学化、标准化管理的优点,是羊场转型发展的趋势。计算机视觉技术是人工智能的核心,可以实现非接触性、自动化、实时监测羊的个体信息。本文总结并分析了计算机视觉在羊场的个体识别方法、行为识别方法、体尺与体重估测、疾病监测的研究现状,并指出计算机视觉在智慧羊场的进一步发展趋势。 [关键词] 计算机视觉|智慧羊场|个体识别|行为识别|体尺与体重估测|疾病监测     

Design for Precision Measurement System Based on Machine Vision

It is difficult to measure the geometric quantity of small parts in finishing, assembling and measuring, because it's easy to break the workpieces' surface and alter their position by means of traditional contact measuring methods.There are some non contact measurers, such as,light feeler pin and interference microscope etc., because of it's high price and strict working conditions,so it's difficult to promote them in widely use. Precision measurement system based on machine vision has the advantages of non contact measuring as well as high performance and low price. Some problems, such as light source, algorithm of edge fitting, auto focusing,are discussed.     

Design of Vision System Based on Service Robot

A vision system based on the service robot is involved. In the system, picture signal is acquired by the picture sensor OV7635. Frame memory AL422B is used as data buffer memory, while CPLD controlled the time order DSP performed. In the software system of image processing, to accomplish color image segmentation and recognition, the threshold vector judgment and improved seed-fill algorithm is introduced, and the image geometric moment is calculated during the segmenting. In order to achieve a vision servo system which composed of image-based feedback and adaptive compensation, the deduced matrix-based Jacobian from the image moment is taken as image feature. Adopted the TFT LCD is adopted to straightly disolav the result of vision recognition and vision tracing.     

一种快速判别梨果梗的方法

果梗完好与否是梨品质检测的指标之一,因而对果梗情况进行准确判别具有重要意义。为此,通过计算机视觉系统摄取梨的图像,利用图像处理技术提出了一种能快速判别梨果梗有无的算法。该算法的识别正确率达90%,识别速度大约在20～30ms,实现了对梨果梗进行高速检测的目标。