Earticle

자동차 운전면허 시험에서 객관적인 평가가 중요하다. 특히 도로 주행시험은 실제 도로에 서 운전능력, 규칙준수, 상황판단능력 등을 종합적으로 시험하는 것이다. 이를 위하여 본 논 문에서는 GPS와 센서 데이터 및 기기조작 정보를 활용하여 운전면허 시험의 자동채점시스 템을 제안한다. 자동채점 시스템은 차량탑재장치, 채점용단말, 데이터 제어장치, 데이터 저장 및 처리를 위한 서버로 구성되어 있다. 차량탑재장치는 차량에 설치된 센서 데이터를 수집한 다. 채점 단말은 차량탑재장치로부터 받은 데이터를 활용하여 기준에 따라 자동채점 한다. 또한 이동 중에 GPS 오차로 인하여 차량이 도로를 벗어나 표현되므로 지도매칭 기법과 경로 이탈 및 복귀 알고리즘을 적용하였다. 이 시스템은 기존 시험 채점 방식과 달리 자동 채점이 가능하며, 시험 결과에서 정확한 차량위치 표시와 GPS 음영지역을 벗어났을 때 10초 이내로 경로 복귀를 하였다. 이 시스템은 도로 주행 교육에도 활용될 수 있을 것으로 기대된다.

It is important to estimate objectively in the driving test. Especially, the driving test is examined by totally driving ability, rule observation and situational judgement. For this, a grading automation system for driving test was presented by using GPS, sensor data and equipment operation informations. This system is composed of vehicle mounted module, automatic grading terminal, data controller, data storage and processing server. The vehicle mounted module gathters sensor data in the car. The terminal performs automatic grading using the received sensor data according the driving test criterion. To overcome the misposition of vehicle in the map due to GPS error, we proposed the automatic grading system by map matching method, path deviation and return algorithm. In the experimental results, it was possible to grade automatically, display the right position of the car, and return to the right path under 10 seconds when the vehicle was out of the shadow region of the GPS. This system can be also applied to the driving education.

E-learning is taking more roles in the current methods of education. The automatic grading and assessment play a major role in both e-learning and traditional education as a method to reduce educational expenses and relief instructors from some of the lengthy tasks such as grading. In this paper, automatic grading for software code assignments or homework is described. A tool is developed to automatically grade students’ code assignments. Concepts or code from Students’ answers are first parsed. Key abstractions and keywords are extracted from students’ assignments and compared with typical or expected answers. Weights are given to code keywords by the instructor based on their value and importance in the overall answer. Relating this grading with code plagiarism, similarities are also measured between students’ assignments and an Euclidean distance method is developed and calculated between each assignment with all other assignments. Results showed that automatic grading for code assignments can be automated due to the nature of expected answers where grader can set and expect a fixed number of possible keywords in each answer. Such formality may not exist for several other types of essay questions.

The existing fruit sorter has the method of tilting tray and extracting fruits by the action of solenoid or springs. In peaches, the most sort processing is supported by man because the sorter make fatal damage to peaches. In order to sustain commodity and quality of peach non-destructive, non-contact and real time based sorter was needed. This study was performed to develop peach sorter using near-infrared spectroscopy in real time and nondestructively. The prototype was developed to decrease internal and external damage of peach caused by the sorter, which had a way of extracting tray with it. To decrease positioning error of measuring sugar contents in peaches, fiber optic with two direction diverged was developed and attached to the prototype. The program for sorting and operating the prototype was developed using visual basic 6.0 language to measure several quality index such as chlorophyll, some defect, sugar contents. The all sorting result was saved to return farmers for being index of good quality production. Using the prototype, program and MLR(multiple linear regression) model, it was possible to estimate sugar content of peaches with the determination coefficient of 0.71 and SEC of 0.42bx using 16 wavelengths. The developed MLR model had determination coefficient of 0.69, and SEP of 0.49bx, it was better result than single point measurement of 1999's. The peach sweetness grading system based on NIR reflectance method, which consists of photodiode-array sensor, quartz-halogen lamp and fiber optic diverged two bundles for transmitting the light and detecting the reflected light, was developed and evaluated. It was possible to predict the soluble solid contents of peaches in real time and nondestructively using the system which had the accuracy of 91 percentage and the capacity of 7,200 peaches per an hour for grading 2 classes by sugar contents. Draining is one of important factors for production peaches having good qualities. The reason why one farm's product belows others could be estimated for bad draining, over-much nitrogen fertilizer, soil characteristics, etc. After this, the report saved by the peach grading system will have to be good materials to farmers for production high quality peaches. They could share the result or compare with others and diagnose their cultural practice.

Visual features of a mushroom(Lentinus Edodes L) are critical in sorting and grading as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. Though actions involved in human grading looks simple, a decision making undereath the simple action comes form the results of the complex neural processing of the visual image. And processing details involved in the visual recognition of the human brain has not been fully investigated yet. Recently, however, an artificial neural network has drawn a great attention because of its functional capability as a partial substitute of the human brain. Since most agricultural products are not uniquely defined in its physical properties and do not have a well defined job structure, a research of the neuro-net based human like information processing toward the agricultural product and processing are widely open and promising. In this pape , neuro-net based grading and sorting system was developed for a mushroom . A computer vision system was utilized for extracting and quantifying the qualitative visual features of sampled mushrooms. The extracted visual features and their corresponding grades were used as input/output pairs for training the neural network and the trained results of the network were presented . The computer vision system used is composed of the IBM PC compatible 386DX, ITEX PFG frame grabber, B/W CCD camera , VGA color graphic monitor , and image output RGB monitor.

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.

들깨(Perilla frutescens var. japonica)는 꿀풀과(Lamiaceae)에 속하는 1년생초로써 키는 60-90cm 정도이며, 줄기는 네모지고 곧게 서며 긴 털이 있다. 잎은 마주나고 달걀 모양원형으로 뾰족하며 밑부분은 둥글다. 잎은 길이 7-12cm, 나비 5-8cm로 톱니가 있고 앞면은 녹색이지만 뒷면에는 자줏빛이 돈다. 들깨는 식용계란, 돼지고기, 양식어류 등의 생산을 위한 기능성 보조식품의 사료와 한방에서는 만성위염, 기침, 위산과다 등의 약용으로도 쓰이고 있다. 또한 들깻잎은 특유의 향취로 인해 육류나 생선회, 영양탕 등의 음식점에서 상추와 함께 대량소비가 되고 있다. (중략)

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.

선별은 청과물을 포장하기 이전에 크기, 중량, 색깔등 정해진 규격에 따라 고르는 과정을 말하고, 크게 인력선별과 기계선별, 개별선별과 공동선별로 구분한다. 국내의 경우 아직까지도 수확된 청과물은 농가단위로 개별선별하고 있으며, 중량식 선별기를 이용하여 등급선별 한 후 15kg, 10kg 상자에 포장하는 것이 가장 일반적이다. 근래에 청과물의 부가가치를 높이기 위해서 중량에 색깔을 선별할 수 있는 기능을 추가한 기계시스템이 개발되어 산업화된 바 있다(최 등, 1997). 또한 근적외선 분광분석법을 이용하여 과일의 당도를 비파괴적으로 측정 선별할 수 있는 시스템이 개발 실용화 단계에 있다(이 등, 1998). (중략)

대학의 컴퓨터 관련 학과에서 데이터베이스에 대한 SQL(DML)을 학생들에게 숙지시키기 위한 시험(정기 시험, 퀴즈)은 필수이며, 이에 대한 채점을 수작업을 하고 있어 교수들에게 채점의 부담으로 작용하고 있다. 본 논문은 이런 부담을 덜기 위한 SQL 채점 자동화 시스템을 개발함으로써 학생들에게 채점의 부담 없이 시험을 통해 충분한 시험을 실시하도록 하는 시스템을 개발하였다. 대학에서 SQL은 SELECT, UPDATE, INSERT, DELETE 4개의 데이터 조작어로 구분되며, 기본적인 구문의 시험이 대부분이다, 이에 대한 채점 구문분석을 위한 파싱트리(parsing tree)을 만들어 자동 채점 시스템을 구현하였다.

육안에 의한 피혁의 등급 판정 과정은 장시간 시 피로에 의한 일관성 결여로 인해 판정 결과에 대한 신뢰성을 주지 못한다. 따라서 피혁의 품질을 결정하기 위한 객관적인 지표와 이를 기준으로 등급 판정 과정의 자동화가 필요하다. 본 논문에서 적용된 피혁 자동 선별 시스템은 피혁에 대한 정보를 취 득하는 과정과 이들로부터 등급을 판정하는 과정으로 구성된다. 피혁의 품질은 조밀도와 결함의 종류 및 분포도와 같은 피혁의 특성에 의해 결정된다. 본 논문에서는 디지털 카메라에 의해 획득된 흑백 영상으로부터 피혁의 조밀도 및 결함을 추출하여 피혁의 등급을 판정하는 알고리즘을 제안한다. 조밀도는 퓨리에 스펙트럼이 존재하는 영역의 넓이 및 가로, 세로 비율로서 계산된다. 그리고 결함은 전처리 과정을 거친 영상으로부터 검색 윈도우를 사용하여 윈도우에 해당하는 픽셀들의 히스토그램 분포의 특징에 의해서 검출된다. 피혁 전체에 대한 특성들은 피혁의 등급을 판정하는 지표로 사용되며 다른 분야에서의 인간의 시각 검사를 대체 할 수 있으리라 판단된다.

A leather quality inspection by naked eyes has known as unreliable because of its biological characteristics like accumulated fatigue caused from an optical illusion and biological phenomenon. Therefore it is necessary to automate the leather quality inspection by computer vision technique. In this paper, we present automatic leather qua1ity classification system get information from leather surface. Leather is usually graded by its information such as texture density, types and distribution of defects. The presented algorithm explain how we analyze leather information like texture density and defects from the gray-level images obtained by digital camera. The density data is computed by its ratio of distribution area, width, and height of Fourier spectrum magnitude. And the defect information of leather surface can be obtained by histogram distribution of pixels which is Windowed from preprocessed images. The information for entire leather could be a standard for grading leather quality. The proposed leather inspection system using machine vision can also be applied to another field to substitute human eye inspection.

들깻잎은 식생활의 변화로 인한 육류소비의 증가와 더불어 수요량이 급격히 증가하고 있다. 들깻잎은 특유의 향취로 인해 육류나 생선회, 영양탕 등의 음식점에서 상추와 함께 대량소비가 되고 있는 실정이다. 들깻잎의 수확은 반촉성 재배시 40-50일 뒤부터 수확하게 되며 봄가을에는 10일, 여름에는 5-7일 간격으로 수확한다. 들깻잎의 수확기간은 만생종은 150일, 조생종은 110일 정도이다. 1회 수확 시 보통 주당 1-2장(1마디)의 잎을 수확하며 숙련된 노동자의 경우 7,000-1l,000장 정도의 잎을 수확할 수 있다. (중략)

Objectives : Grading facial paralysis plays a crucial role in establishing treatment plans and determining prognosis. Both domestic and international efforts have actively focused on the development of objective automated grading systems. The purpose of this study is to investigate trends in Automated Facial Palsy Grading Systems through literature search. Methods : Using PubMed, OASIS, and other databases, related research papers published from 2000 to 2024 were analyzed. The studies were analyzed by dividing into Automated Grading Image Processing (2D, 3D, Video), Landmark Assignment and Standard Grading System for comparison. Results : A total of 13 studies were selected in this study. The first article was published in 2013. Studies were rapidly increased since 2019. The mostly used input data was photo. The other data were 3D photo and video. Studies using 68 landmark assignment system were the most prevalent, followed by OpenCV, Manual attachment, and other Machine Learning algorithms. There were 6 studies compared with House-Brackmann grading system, 4 studies compared with Sunny brook facial grading system, 3 studies compared with Nottingham scale and also studies involving Yanagihara grading system, eFACE, electroneurography (ENoG). Conclusions : The automated Grading systems were developed using various technologies, including image processing, automatic landmark assignment, OpenCV, machine learning, and applications. This automated grading systems demonstrated accuracy comparable to or exceeding that of conventional subjective evaluation methods. Moreover, it significantly reduced the time required for facial paralysis assessment, highlighting its potential as a viable alternative to subjective evaluation.