Search

Search Results

• Diagnosisof Swine Diseases by Image Feature Extraction Methods and AutomaticClassification

  Do Thi Nham, Le Thi Nhung

  Date Received: 01-08-2015 / Date Accepted: 05-06-2016

   Abstract PDF (VIETNAMESE)

  In Viet Nam, the swine industry is ranked as leading position in animal husbandry. Due to disease problems, the swine industry often faces with a lot of difficulties and suffers great loss every year. Hence, the diagnosis of the diseases for treatment and prevention in time is extremely necessary. This paper proposes a model for diagnosis of swine diseases using image feature extraction methods and automatic classification. In this model, we also used some image feature extraction methods to evaluate the classification effectiveness of each method on test dataset. The experimental results of an image feature extraction method that we used with classification accuracy over 84% showed that our model can be employed effectively in practice.

• Leaf Image Classification Using Support Vector Machine

  Phan Thi Thu Hong, Doan Thi Thu Ha, Nguyen Thi Thuy

  Date Received: 21-08-2013 / Date Accepted: 29-10-2013

   Abstract PDF (VIETNAMESE)

  Computer vision is an inter-discipline research field, which has many real life applications. One of the important tasks is to identify and classify objects from their digital images. Computer vision has been applied successfully in many fields of agriculture such as agricultural automation, precision agriculture, classification of agricultural products and identification (trees, weeds, fruits etc). This paper presents the application of the computer vision technique to leaf image classification by using Support Vector Machine (SVM). The experimental results with classification accuracy of 98% showed the success of using SVM to classify leaf images. This also showed that the approach can be employed for other practical applications effectively.

• Nhận dạng hạt thóc giống sử dụng kĩ thuật xử lý ảnh và thị giác máy tính

  Phan Thi Thu Hong, Tran Thi Thanh Hai, Le Thi Lan, Vo Ta Hoang, Nguyen Thi Thuy

  Date Received: 22-07-2015 / Date Accepted: 03-09-2015

   Abstract PDF (VIETNAMESE)

  Bài báo này giới thiệu về một hệ thống tự động nhận dạng hạt thóc giống phục vụ cho quy trình sản xuất thóc giống ứng dụng kĩ thuật xử lý ảnh và thị giác máy tính. Hạt thóc của những giống lúa khác nhau khi nhìn bằng mắt thường là rất giống nhau về màu sắc, hình dáng và kết cấu bên ngoài. Điều đó làm cho việc phân biệt các loại thóc giống khác nhau với độ chính xác cao nhằm đánh giá độ thuần chủng của thóc là một thách thức lớn. Chúng tôi tập trung vào các kĩ thuật khác nhau để trích chọn đặc trưng hình ảnh của hạt thóc giống thông qua ảnh chụp các giống lúa một cách hiệu quả. Sau đó chúng tôi phân tích hiệu năng của các bộ phân loại dựa trên các đặc trưng được trích chọn ở trên để tìm ra một phương pháp phân lớp có độ chính xác cao nhất. Hình ảnh của sáu giống lúa khác nhau đã được thu nhận ở miền Bắc Việt Nam, trong đó mỗi giống có từ 1026-2229 hình ảnh hạt lúa. Những thực nghiệm của chúng tôi đã chỉ ra rằng hệ thống phân lớp đạt độ chính xác cao nhất 90.54% khi sử dụng phương pháp rừng ngẫu nhiên dựa trên bộ đặc trưng cơ bản. Kết quả này có thể sử dụng để phát triển một hệ thống thị giác máy tính hỗ trợ việc đánh giá tự động độ thuần chủng của hạt thóc giống.

• Assessing Land Use and Land Cover Change: A Case of Tien Yen District, Quang Ninh Province from 2000 to 2010

  Nguyen Thi Thu Hien, Pham Vong Thanh, Nguyen Khac Thoi

  Date Received: 14-11-2013 / Date Accepted: 21-02-2013

   Abstract PDF (VIETNAMESE)

  The study was conducted to assess land useand land cover change in Tien Yen district in the 2000 -2010 period using SPOT images which were acquired in years 2000, 2005 and 2010. The object –oriented approach which was applied in this research includedtwomain steps: firstly, SPOT image was fragmented to vary objects by eCognition software, and, secondly,the segmentation images were classified by Maximum Likelihood approach using training dataset. The samples consisting of nineland usetypeswere collected by handheld GPSdevice. The overall accuracy of 3 image classifications in 2000, 2005, 2010 were 82.74%, 80,97% and 89.33%, respectively. Land useand land cover mapand land use/land cover change map were produced by ArcGIS (version 10.0) software to assess the land use change of the study area. Within 10 yearsperiod, the forest area and mangrove forest increased 3916.91ha and 1720.57ha, respectively. Meanwhile, the swidden and shrublanddecreased 4200.16ha. The increase of forest area in Tien Yen might be explained bybetter awarenessof local people about the benefits and the importance of forest as well as by thethe implementation of national and international projects which support Tien Yen in protecting and developing forest resource.

• Using Multi - Temporal MODIS Data for Mapping Paddy Rice Cultivation Area in Ninh Binh Province

  Le Van Dung, Le Phuong Thao

  Date Received: 22-07-2015 / Date Accepted: 03-09-2015

   Abstract PDF (VIETNAMESE)

  NinhBinh province is one of main paddy cultivation areas in theRed River Delta. Mapping paddy rice area by using remote sensing techniques is useful for policy makers to manage and plan for food security and socio - economic development in the province as well as in the region.Multi - temporal eight - day composite MODIS images (MOD09A1, MOD09Q1) and Landsat Thematic Mapper (TM) dataset were used for mapping paddy rice area. MODIS images were classified by using Maximum Likelihood Classification algorithm in testclassificationfollowed bysubpixel classification to increase the accuracy of classification result.Results of testclassification were over 74% (for the image taken on 02 June 2010) and 78% (forthe 14 September 2010 one) of land use classification in MODIS images. These results are acceptable for the moderate spatial resolution images. Result of Sub - pixel classification was over 86% (02 June 2010) and 90% (14 September 2010) of accuracy.

• Assessement of Land Management and Land Use of Economic Organizations Which Were Assigned or Leased Land by the Government in Me Linh District, Ha Noi City

  Do Thi Tam, Pham Minh Giap

  Date Received: 18-03-2015 / Date Accepted: 09-06-2015

   Abstract PDF (VIETNAMESE)

  The study aims to assess land management and land useof economicorganizationswhich were assigned or leased land by the governmentin Me Linh. Thus, propose solutionsto enhanceland use efficiency, at the same time to limit the cases of breaking the Land law. The research used intergrated analysis and comparisonmethods. The result shows thatthere were 217economicorganizationswhich wereassigned or leased land with a total area of ​​927.50 ha in Me Linh District. 25 organizations used the land for improper purposes with an area of 14.27 ha; 9organizations used land for leasing to another organization with an area of 13.20 ha; 5 organizations had land in dispute with an area of 13.10 ha; 16 organizations used land as a join capital in business with an area of 34.74 ha and 13 organizations with 84.55 ha of land which have not put in to use yet. To remedy thesesituations, it is necessary to promulgate appropriate policies and laws, economical solutions, scientific solutions and management solutions.

• Application of Unmanned Aerial Vehicle Technology (UAV) in Building Cleanrance Map

  Phan Van Khue, Tran Trong Phuong, Nguyen Duc Loc, Tran Thi Tinh

  Date Received: 07-10-2022 / Date Accepted: 27-01-2023

   Abstract PDF (VIETNAMESE)

  The large scale map, an indispensable and important document is the basis for making compensation, support and resettlement plans when implementing land acquisition. The objective of this study was to use unmanned aerial vehicle (UAV) technology to create maps for ground clearance. The research conducted field survey using DJI Phantom 4 Pro UAV and 20MP CMOS digital camera synchronized with the aircraft. Images were collaged and edited by Agisoft metashape. From orthomosaic images, digitization/interpretation was performed directly on the image, the map edited by MicroStation, and Gcadas used to calculate the area. Research results have established a map of 1/500 scale, fully ensuring the quality and detail of land use classification and monitoring of assets on land for ground clearance work in the area research. Research shows that clearance map by unmanned aerial vehicles (UAV) was an effective technology in terms of products, time, cost and technology development trends.