An yield estimation in citrus orchards via fruit detection and counting using image processing

Dorj, Ulzii-Orshikh,Lee, Malrey,Yun, Sang-seok Elsevier 2017 Computers and electronics in agriculture Vol.140 No.-

<P><B>Abstract</B></P> <P>The overall goal of this study is to develop an effective, simple, aptly computer vision algorithm to detect and count citrus on the tree using image processing techniques, to estimate the yield, and to compare the yield estimation results obtained through several methods. This new citrus recognition and counting algorithm was utilized the color features (or schemes) to present an estimate of the citrus yield, and the corresponding models are developed to provide an early estimation of the citrus yield. Citrus images were taken from Jeju, South Korea during daylight and the citrus recognition and counting algorithm were tested on 84 images which were collected from 21 trees. The citrus counting algorithm consisted of the following steps: convert RGB image to HSV, thresholding, orange color detection, noise removal, watershed segmentation, and counting. Distance transform and marker-controlled watershed algorithms were evaluated for automated watershed segmentation in citrus fruits to obtain good result. A correlation coefficient R<SUP>2</SUP> of 0.93 was obtained between the citrus counting algorithm and counting performed through human observation. The proposed algorithm showed great potential for early prediction of the yield of single citrus trees and the possibility of its uses for further fruit crops.</P> <P><B>Highlights</B></P> <P> <UL> <LI> The overall goal of this study is to develop an effective, simple, aptly computer vision algorithm to detect and count citrus on the tree using image processing techniques, to estimate the yield, and to compare the yield estimation results obtained through several methods. </LI> <LI> This new citrus recognition and counting algorithm was utilized the color features (or schemes) to present an estimate of the citrus yield, and the corresponding models are developed to provide an early estimation of the citrus yield. </LI> <LI> Citrus images were taken from Jeju, South Korea during daylight and the citrus recognition and counting algorithm were tested on 84 images, which were collected from 21 trees. </LI> <LI> The citrus counting algorithm consisted of the following steps: convert RGB image to HSV, thresholding, orange color detection, noise removal, watershed segmentation, and counting. </LI> <LI> Distance transform and marker-controlled watershed algorithms were evaluated for automated watershed segmentation in citrus fruits to obtain good result. </LI> <LI> A correlation coefficient R<SUP>2</SUP> of 0.93 was obtained between the citrus counting algorithm and counting performed through human observation. </LI> <LI> The proposed algorithm showed great potential for early prediction of the yield of single citrus trees and the possibility of its uses for further fruit crops. </LI> </UL> </P>

설색의 분포 및 설색과 임상병리검사 결과의 연관성에 대한 연구

임제민,남우진,윤용재,이상민,강유경,김원일,Yim, Je-Min,Nam, Woo-Jin,Yun, Yong-Jae,Lee, Sang-Min,Kang, You-Gyung,Kim, Won-Il 대한한방내과학회 2013 大韓韓方內科學會誌 Vol.34 No.1

Objectives : The aim of this study was to evaluate the distribution of tongue color and the correlation of the tongue colors with clinical laboratory parameters. Methods : Statistical analysis on the frequency of each tongue color and the results of the clinical laboratory parameters in each tongue color group. Results : Tongue colors that appeared most frequently were 702c, 695c, 493c, 694c, 701c, 500c, 7432c, 7431c, 7634c, 7419c in that order. Following them, 494c and 507c were rarer colors, and 501c, 673c, 687c, 693c, 696c, 703c, 7418c were equally rarest colors. Among each tongue color group, a significant difference was found in the result of complete blood cell count (CBC). The level of red blood cell (RBC) of 7432c group was significantly higher than that of the other groups except 694c group. The level of hemoglobin (Hb), hematocrit (Hct) of 7432c group were significantly higher than those of all the other groups. The level of RBC of 7431c group was lowest and significantly different from 694c, 7432c group. In results of the other tests were not significantly different. However the level of total cholesterol was higher in 695c, 694c, 500c group, and the level of triglyceride was higher in 500c, 7431c, 694c group. Those four colors have a low chroma and 7431c, 695c take blue violet color. Conclusions : The tongue color is distributed throughout following colors by order of frequency: 702c, 695c, 493c, 694c, 701c, 500c, 7432c, 7431c, 7634c, 7419c, 708c, 494c, 507c, 501c, 673c, 687c, 693c, 696c, 703c, 7418c. Some parameters of CBC has a significant correlation with some tongue colors. Other results including lipid profile, renal function test, and liver function test had no significant difference according to tongue color. However, the colors which have low chroma or take blue violet color tented to be higher in the levels of total cholesterol and triglyceride.

Development of a Novel Flow Cytometry-Based System for White Blood Cell Differential Counts: 10-color LeukoDiff

박동진,장지영,강지민,박훈희,조애린,김용구,한경자 대한진단검사의학회 2019 Annals of Laboratory Medicine Vol.39 No.2

Background: Flow cytometry (FCM) is commonly used to identify many cell populations. We developed a white blood cell (WBC) differential counting system for detecting abnormal cells using FCM incorporating 10 colors and 11 antibodies in a single tube, called “10-color LeukoDiff,” and evaluated its performance. Methods: Ninety-one EDTA-anti-coagulated peripheral blood samples from 76 patients were analyzed using 10-color LeukoDiff. We compared 10 color LeukoDiff results with the results of manual differential count (manual diff). WBCs were classified into 17 cell populations: neutrophils, total lymphocytes, T lymphocytes, B lymphocytes, CD5 and CD19 co-expressing lymphocytes, natural killer cells, total monocytes, 16+ monocytes, eosinophils, immature granulocytes, basophils, myeloblasts, B-blasts, T-blasts, myeloid antigen-positive B-blasts, CD19- plasma cells, and 19+ plasma cells. Results: The correlations between the 10-color LeukoDiff and manual diff results were strong (r>0.9) for mature neutrophils, lymphocytes, eosinophils, immature granulocytes, and blasts and moderate for monocytes and basophils (r=0.86 and 0.74, respectively). There was no discrepancy in blast detection between 10-color LeukoDiff and manual diff results. Furthermore, 10-color LeukoDiff could differentiate the lineage of the blasts and separately count chronic lymphocytic leukemic cells and multiple myeloma cells. Conclusions: The 10-color LeukoDiff provided an accurate and comprehensive WBC differential count. The most important ability of 10-color LeukoDiff is to detect blasts accurately. This system is clinically useful, especially for patients with hematologic diseases, such as acute leukemia, chronic lymphocytic leukemia, and multiple myeloma. Application of this system will improve the development of FCM gating strategy designs.

가스치환포장이 냉장돈육의 저장성에 미치는 영향

진상근,문점동 진주산업대학교 농업기술연구소 2000 農業技術硏究所報 Vol.13 No.-

The present experiment was undertaken to investigate the effects of the modified atmosphere packaging(MAP) with different gas composition, i.e. control(vaccum-packaging), T1(100% CO_2), T2(30% CO_2, 70% N_2), T3(30% CO_2, 50% N_2, 20% O_2) and T4(50% CO_2, 30% N_2, 20% O_2), on the changes of meat quality of porcine loin eye cuts after 6 wk of storage in the refrigerator(0±1℃). Summarized below are changes after the storage in phycochemical characteristics and the bacterial count. pH, WHC, TBARS, VBN, number of coliform bacteria and total plate count increased after the storage in all the treatments(Ts), whereas L, a and b values of the meat color decreased. Compared with control, pH was decreased in all the Ts; WHC was lowest in T2; purge loss was lowest in T2 and T3. L, a and b values of the meat color were not different between the control and Ts. TBARS, by contrast, was higher in all the Ts except T2; VBN and the number of coliform bacteria were greater in all the Ts; total plate counts were greater in all the Ts except T1 than in control. Taken together, T1 was the most effective MAP among those Ts that had been tested in improving the shortcoming of the vacuum-packaging. However, more studies are necessary to develop a MAP using O_2 gas that can maintain the meat color without causing any disadvantageous effect in fat oxidation.

생물학적 영상 분석을 위한 자동 모바일 셀 계수 시스템

서재준 ( Jaejoon Seo ),전준철 ( Junchul Chun ),이진성 ( Jin-sung Lee ) 한국인터넷정보학회 2015 인터넷정보학회논문지 Vol.16 No.1

본 논문에서는 모바일 환경에서 미세세포 영상으로부터 셀을 자동 검출하고 계수하는 자동화 방법을 제시하였다. 셀 카운팅은 생물학 또는 병리학적 영상분석에 있어서 매우 중요한 과정이다. 과거에는 셀 카운팅은 수동적인 방법으로 진행되어 매우 지루하고 많은 시간을 필요로 하는 작업이었다. 이에 더하여 수동 계수 방법은 정확한 카운팅 결과를 도출하는데 어려움이 있었다. 따라서, 정확하고 일관된 셀 검출과 카운팅 결과를 생물학적인 영상으로부터 획득하기 위해서는 자동화방법이 필요하다. 제안된 다단계 셀계수방법은 배양된 세포영상으로부터 셀을 자동으로 분할하고 분할된 셀의 위상학적 분석을 통하여 셀을 라벨링 한다. 셀 카운팅의 정확도를 높이기 위하여 워터쉐드 알고리듬에 의하여 서로 덩어리로 뭉쳐진 셀을 서로 분리하고 모폴로지 연산을 통하여 영상으로부터 획득한 개별 셀의 형태를 개선한다. 제안된 시스템은 모바일 환경에서 사용될 수 있도록 개발되었다. 따라서 셀 영상은 모바일 폰의 카메라로 획득하며 미세세포의 통계학적인 분석 데이터는 유비쿼터스 환경의 모바일 장치에 의해 전송 된다. 실험을 통하여 수동으로 계수한 셀의 숫자와 제안된 방법에 의해 자동 카운팅 된 셀의 수를 비교한 결과 제안된 방법이 매우 효과적이고 정확한 결과를 제시한다는 사실을 입증하였다. This paper presents an automatic method to detect and count the cells from microorganism images based on mobile environments. Cell counting is an important process in the field of biological and pathological image analysis. In the past, cell counting is done manually, which is known as tedious and time consuming process. Moreover, the manual cell counting can lead inconsistent and imprecise results. Therefore, it is necessary to make an automatic method to detect and count cells from biological images to obtain accurate and consistent results. The proposed multi-step cell counting method automatically segments the cells from the image of cultivated microorganism and labels the cells by utilizing topological analysis of the segmented cells. To improve the accuracy of the cell counting, we adopt watershed algorithm in separating agglomerated cells from each other and morphological operation in enhancing the individual cell object from the image. The system is developed by considering the availability in mobile environments. Therefore, the cell images can be obtained by a mobile phone and the processed statistical data of microorganism can be delivered by mobile devices in ubiquitous smart space. From the experiments, by comparing the results between manual and the proposed automatic cell counting we can prove the efficiency of the developed system.

가열 처리에 따른 커틀릿의 식품안전성 확보 조건 - 내부 중심온도, 색도 및 위생지표미생물을 중심으로 -

김종규,김중순,Kim, Jong-Gyu,Kim, Joong-Soon 한국환경보건학회 2015 한국환경보건학회지 Vol.41 No.2

Objectives: This study was performed to investigate the effect of cooking time on the internal temperature and color of cutlets and the reduction of indicator organisms in cutlets by cooking. Methods: Three kinds of commercially packed frozen cutlets (pork, chicken and fish cutlets), were purchased from local markets. The cutlets were cooked in a frying pan at $180^{\circ}C$ for four minutes. Internal temperature was measured with a food thermometer. Color was measured using a Hunter spectrocolorimeter. Aerobic colony counts, coliforms, and Escherichia coli were determined according to the Food Code of Korea. Results: The internal cooked temperature of every cutlet reached over $74^{\circ}C$, the temperature considered safe, after three minutes, while external temperature reached this level in two minutes (p < 0.001). The instrumental color value as lightness (L) in the cooked cutlets significantly changed (p < 0.001) after one minute. The level of aerobic colony counts of fresh cutlets was under the specification and was reduced to one tenth its level in the cooked cutlets. Coliforms and E. coli were not detected in all samples. The internal temperature of the cutlets was significantly affected by cooking time and weight (p < 0.001). The interaction effect of time and weight was also significant (p < 0.001), and time was the more influential factor. Conclusion: The results of this study indicate that the sampled cutlets should be cooked for a minimum of three minutes or more in order to ensure food safety. The results also indicate that if consumers cease cooking based on external temperature or color, there will be a risk of inadequate cooking.

식초의 농도가 초밥의 미생물적 안전성 및 품질에 미치는 영향

이상빈,김성훈,송호수 한국식품위생안전성학회 2016 한국식품위생안전성학회지 Vol.31 No.5

This study was carried out to investigate the effect of vinegar on pH, total bacterial count, texture and color of rice with vinegar before and after storage at 4oC and 25oC. This results obtained were summarized as follows : The pH value and total bacterial counts were not significant changed under different storage conditions with sushi vinegar, but control without sushi vinegar was increased the number of bacteria from storage 1 days. and When rice with vinegar was stored at low temperature(4oC), the tendency of textural changes such as hardness, springiness, cohesiveness, chewiness, brittleness and adhesiveness was almost the same as those of 25oC. However, the rate of change was much higher in rice with vinegar when stored at 4oC than at 25oC. and The Hunter’s color parameters such as L, a, and b, of rice with vinegar were not changed much during storage at both 25oC. However, L value was slightly increased during storage, but a value was increased negatively without changing b value of rice with vinegar during storage at 4oC.

식초의 농도가 초밥의 식품안전성 및 품질에 미치는 영향

이상빈,김성훈,송호수 한국식품위생안전성학회 2016 한국식품위생안전성학회지 Vol.31 No.5

식초 농도를 달리하여 제조한 배합 초를 이용하여 만든초밥은 상온 25℃와 냉장온도인 4℃ 모두에서 초밥 제조직후에 측정한 결과값과 저장기간에 따른 pH의 변화는 유의적인 차이가 없는 것으로 나타났으며, 일반세균의 경우배합초를 첨가하지 않은 대조군은 저장 1일부터 세균수가 증가하였으나 식초를 첨가한 초밥의 경우에는 2배 산도및 3배 산도 식초를 사용한 초밥은 저장 5일째 가지 일반세균의 유의적인 변화가 없는 것으로 나타났다. 또한, 초밥 제조 시 식초의 농도 증가에 따라 초밥의 견고성, 탄력성, 응집성, 씹힘성, 부착성 및 깨짐성은 유의적으로 (p < 0.05) 감소하는 경향을 보였고, 상온 25℃에서 48시간저장기간 동안 견고성, 탄력성, 씹힘성, 깨짐성은 증가하였고, 부착성은 감소하였고, 저온 4℃에서 48시간 저장기간 동안 견고성은 상온 25℃에서 저장하는 것에 비해 견고성이 높은 것으로 나타났다. 저장온도 및 기간에 따른 색도의 변화를 측정한 결과대조구에 비해 식초를 첨가한 초밥의 명도(L)와 황색도(b)는 유의적으로(p < 0.05) 감소하였으나 초밥의 적색도(a)는 유의적인(p < 0.05) 차이가 없었다. 초밥은 4℃에서 48시간저장하는 동안 명도(L)는 유의적으로(p < 0.05) 증가하였으며, 적색도(a)는 저장하는 동안 초밥의 종류에 관계없이 (-)값이 증가하였다. 그리고 황색도(b)는 저장기간 동안 유의적인(p < 0.05) 변화는 없었다. This study was carried out to investigate the effect of vinegar on pH, total bacterial count, texture and color of rice with vinegar before and after storage at 4℃ and 25℃. This results obtained were summarized as follows : The pH value and total bacterial counts were not significant changed under different storage conditions with sushi vinegar, but control without sushi vinegar was increased the number of bacteria from storage 1 days. and When rice with vinegar was stored at low temperature (4℃), the tendency of textural changes such as hardness, springiness, cohesiveness, chewiness, brittleness and adhesiveness was almost the same as those of 25℃. However, the rate of change was much higher in rice with vinegar when stored at 4℃ than at 25℃. and The Hunter’s color parameters such as L, a, and b, of rice with vinegar were not changed much during storage at both 25℃. However, L value was slightly increased during storage, but a value was increased negatively without changing b value of rice with vinegar during storage at 4℃.

견직물의 스치는 소리로부터 변환된 색채의 물리량과 감성

김춘정 ( Chun Jeong Kim ),최계연 ( Kye Youn Choi ),김수아 ( Su Ah Kim ),조길수 ( Gil Soo Cho ) 한국감성과학회 2002 감성과학 Vol.5 No.1

식육처리기구 및 신선돈육의 위생적 처리방법에 관한 연구

문점동,진상근,박태선 진주산업대학교 농업기술연구소 1998 農業技術硏究所報 Vol.11 No.-

식육처리시 사용되는 실내의 공기, 도마, 칼, 장갑, 육절기 등의 위생적인 살균방법 및 지육, 정육을 가공용수(온수, 냉수), 알콜(70%), 유기산(acetic acid, citric acid, lactic acid, formic acid, chloride)을 처리하여 식육의 초기오염도를 조사한 결과는 다음과 같다. 70% 알콜 및 온수를 이용하여 식육처리기구의 오염원을 제거하기 위한 효과는 두 방법 모두 처리구가 대조구에 비하여 우수한 것으로 나타났으며, 온수와 70% 알콜의 처리방법은 온수가 뛰어났다(P<0.05). 지육의 처리는 온수처리를 통하여 오염원을 최소화할 수 있었다. 정육의 처리는 70% 알콜 처리로 총생균, 대장균의 증식을 억제할수 있었다. 유기산 처리를 통한 돈육의 오염원 최소화는 전체 처리구 모두 대조구에 비하여 우수한 경향을 나타내었으며, 이중 젖산균이 가장 우수한 것으로 나타났다. 유기산 처리시 육색은 차이를 나타내지 않았으며, 유기산 처리 후 관능검사에서는 생육, 가열육의 경우 모두가 차이를 발견할 수 없었다. 이상 본실험에서 온수, 알콜을 통한 소독과 유기산을 통한 정육의 처리는 오염최소화를 시킬 수 있는 방안으로 나타났다. This study was determine the effects of sanitary treatments that air conditioning, kitchen board, knife, glove, slicer, carcass and pork meat were treated water(hot and cold), alcohol(70%), organic acid(acetic acid ; AA, citric acid : CA, lactic acid : LA, formic acid ; FA) and chloride(200ppm). This study results obtained were summarized as follows ; Treatments of water and 70% alcohol were superior to control in the effect of removing contamination of carcass equipments. Hot water treatment was better than the other treatment(P<0.05). Carcass treatment gives the lowest contamination for Hot water. Pork meat was repressed all total plate count and E. coli by 70% alcohol. Pork meat treatment treated organic acid for the lowest contamination was better than control. Lactic acid was remarkable superior. Change o meat color by organic acid treatment did not take. Sensory evaluation by treatment of organic acid did not show difference in both of raw and cooked meat. Treatment of pork meat by disinfection of hot water, alcohol and organic acid was the way for the least contamination.