• Agricultural and Biosystems Engineering
• /
• 제1권2호
• /
• pp.100-105
• /
• 2000

Quality sorting of cut flowers is very essential to increase the value of products. There are many factors that determine the quality of cut flowers such as length, thickness, and straightness of stem, and color and maturity of bud. Among these factors, the straightness of stem and the maturity of bud are generally considered to be more difficult to evaluate. A prototype grading and sorting machine for cut flowers was developed and tested for a rose variety. The machine consisted of a chain-drive feed mechanism, a pneumatic discharge system, and a grading system utilizing color image processing and neural network. Artificial neural network algorithm was utilized to grade cut roses based on the straightness of stem and maturity of bud. Test results showed 89% agreement with human expert for the straightness of stem and 90% agreement for the maturity of bud. Average processing time for evaluating straightness of the stem and maturity of the bud were 1.01 and 0.44 second, respectively. Application of neural network eliminated difficulties in determining criteria of each grade category while maintaining similar level of classification error.

• Journal of Biosystems Engineering
• /
• 제20권4호
• /
• pp.376-382
• /
• 1995

This study was intended to develop more reliable fruit sorting algorithm regardless of the feeding positions of fruits by using the neural network in which various information could be included as input data. Specific objectives of this study were to select proper input units in the neural network by investigating the features of input image, to analyze the sorting accuracy of the algorithm depending on the feeding positions of Fuji apple and to evaluate the performance of the algorithm for practical usage. the average value in color grading accuracy was 90%. Based on the computing time required for color grading, the maximum sorting capacity was estimated to approximately 10, 800 apples per hours. Finally, it is concluded that the neuro-net based color sorting algorithm developed in this study has feasibility for practical usage.

• Journal of Biosystems Engineering
• /
• 제32권3호
• /
• pp.160-165
• /
• 2007

This study was conducted to evaluate beef using a color machine vision system. The machine vision system has an advantage to measure larger area than a colorimeter and also could measure other quality factors like distribution of fats. However, the machine vision measurement is affected by system components. To measure the beef color with the machine vision system, the effect of color balancing control was tested and calibration model was developed. Neural network for color calibration which learned reference color patches showed a high correlation with colorimeter in L*a*b* coordinates and had an adaptability at various measurement environments. The trained network showed a very high correlation with the colorimeter when measuring beef color.

• 한국연초학회지
• /
• 제16권1호
• /
• pp.26-33
• /
• 1994

A tobacco ripeness grading meter was designed and constructed using the color sensor, its performance was evaluated. A degree of ripeness grading of a leaf is very closely related to the measured tobacco leaf color. Measuring the small amount of the reflectance precisely depends on the apparatus including color sensor, light source, detector sensitivity, and geometric characteristics of appratus. To analyze and minimize the variational effects, experiments to select the proper condition were performed. Because of the combined effect mentioned above, the system has some variation on its response. Basis on the results of the experiments, prototype was developed and interfaced to a computer system. The main components of prototype included a tungsten lamp as a light source, Amorphous full color sensor with three filters, regulated D.C. power supply, OP - AMP(741 TC) for amplification, AR - B3001 board for interfacing to a computer with analog to digital conversion, and a compatible IBM PC XT computer. The experimental results of the developed ripeness tobacco leaf measurement system are summarized as following: [1] The output readings of ripeness grade meter for tobacco leaf, which is based on harvesting time, showed the apparent difference in variety of different quality. It was considered suitable that three filters(red, green, blue) in Amorphous full color sensor could be used in four different ripeness degree measurement of tobacco leaf. [2] The output readings of ripeness grade meter for tobacco leaf, which is based on government procurement, showed apparent difference in variety of different quality. Tobacco leaf varieties to stalk position are divided into tips, leaf, cutters, and primings, It is considered suitable that only red filter in the sensor could be used to classify the grade of tobacco leaf within the same kind tobacco stalk. However, the ripeness grade meter was not adequate to classify all the tobacco grades in the four different tobacco leaves.

• 한국멀티미디어학회논문지
• /
• 제25권10호
• /
• pp.1386-1394
• /
• 2022

As consumption of high-quality fruits increases and sales and packaging units become smaller, the demand for automatic fruit grading systems is increasing. Compared to other crops, the quality of fruit is determined by visual characteristics such as shape, color, and scratches, rather than just physical size and weight. Accordingly, this study presents a CNN model that can effectively extract and classify the visual features of fruits and a perceptron that classifies fruits using physical features, and proposes a stacking ensemble model that can effectively combine the classification results of these two neural networks. The experiments with AI Hub public data show that the stacking ensemble model is effective for grading fruits. However, the ensemble model does not always improve the performance of classifying all the fruit grading. So, it is necessary to adapt the model according to the kind of fruit.

• 한국가구학회지
• /
• 제19권5호
• /
• pp.307-318
• /
• 2008

Scientific methods for grading urushi lacquer includes general properties (viscosity, pH etc), and quantitative analysis of moisture, urushiol, gum, laccase content etc, and properties of coating layer such as set to touch drying time, gloss, color difference, delamination strength, tensile strength of film. The grading results evaluated by scientific method showed n order with chinese urushi lacquer (E) > domestic urushi lacquer (A) > japanese urushi lacquer (C) > chinese urushi lacquer (D) > domestic urushi lacquer (B). It is different from hose of traditional methods. Therefore, a more accurate grading of urushi lacquer should be ade by combining traditional method with scientific method.

• Journal of Biosystems Engineering
• /
• 제31권6호
• /
• pp.514-523
• /
• 2006

Production of green pepper has been increased due to customer's preference and a projected ten-year boom in the industry in Korea. This study was carried out to develop an automatic grading and sorting system for green pepper using machine vision. The system consisted of a feeding mechanism, segregation section, an image inspection chamber, image processing section, system control section, grading section, and discharging section. Green peppers were separated and transported using a bowl feeder with a vibrator and a belt conveyor, respectively. Images were taken using color CCD cameras and a color frame grabber. An on-line grading algorithm was developed using Visual C/C++. The green peppers could be graded into four classes by activating air nozzles located at the discharging section. Length and curvature of each green pepper were measured while removing a stem of it. The first derivative of thickness profile was used to remove a stem area of segmented image of the pepper. While pepper is moving at 0.45 m/s, the accuracy of grading sorting for large, medium and small pepper are 86.0%, 81.3% and 90.6% respectively. Sorting performance was 121 kg/hour, and about five times better than manual sorting. The developed system was also economically feasible to grade and sort green peppers showing the cost about 40% lower than that of manual operations.

• 대한후두음성언어의학회지
• /
• 제16권1호
• /
• pp.19-22
• /
• 2005

Background and Objectives : While considerable progress has been made in enhancing the quality of laryngoscopy and image processing, the evaluation of laryngeal erythema is still based on the clinician's judgement. The purpose of this study is to quantitatively measure the degree of erythema and to examine the relationship with clinical grading. Materials and Methods : Color images of larynx from 100 subjects were captured from video-documented examinations of laryngoscopy. The amount of erythema within the digitized larynx image was quantified using software developed and was compared with a grading system (0 to 3 scale) based on visual inspection by 4 experienced clinicians. The results were compared by deriving Kappa, Kendall and Spearman statistic. Results : There was high intra-observer(R=0.402-0.755) and inter-observer correlation (R=0.789). Among parameters, the red composite value had most remarkable agreement with clinical grading(R=0.827). Conclusion : The result suggest that the computer based analysis of laryngeal erythema can provide quantiative data on degree of erythema and the basis for further development of an expert system.

• 한국연초학회지
• /
• 제17권1호
• /
• pp.5-14
• /
• 1995

Efficient algorithms for the automatic classification of flue-cured tovacco ripeness and grading have been developed The ripeness of the tobacco was classified into 4 levels vased on the color. The lab-built simple RGB color measuring system was utilized for detecting the light reflectance of the tobacco leaves. The measured data were used far training the artificial neural network The performance of the trained network was also tested far the untrained samples. The spectrophotometer was used to detect the light reflectance and absorption of the graded tobacco leaves in the frequency ranges of the visible light The measured data and the statistical analysis was performed to investigate the light characteristics of the graded samples. The measured data were obtained from samples of 5 different grades directly without considering the leaf positions. Those data were used far training the artificial neural network The performance of the trained network was also tested far the untrained samples. The neural network based sensor information processing showed successful results for grading of tobacco leaves.

• Journal of Biosystems Engineering
• /
• 제39권3호
• /
• pp.174-183
• /
• 2014

Purpose: A robust, efficient auto-grading computer vision system for meat carcasses is in high demand by researchers all over the world. In this paper, we discuss our study, in which we developed a system to speed up line processing and provide reliable results for pork grading, comparing the results of our algorithms with visual human subjectivity measurements. Methods: We differentiated fat and lean using an entropic correlation algorithm. We also developed a self-designed robust segmentation algorithm that successfully segmented several porkcut samples; this algorithm can help to eliminate the current issues associated with autothresholding. Results: In this study, we carefully considered the key step of autoextracting lean tissue. We introduced a self-proposed scheme and implemented it in over 200 pork-cut samples. The accuracy and computation time were acceptable, showing excellent potential for use in online commercial systems. Conclusions: This paper summarizes the main results reported in recent application studies, which include modifying and smoothing the lean area of pork-cut sections of commercial fresh pork by human experts for an auto-grading process. The developed algorithms were implemented in a prototype mobile processing unit, which can be implemented at the pork processing site.