Browsing by Author "Hailemichael, Daniel"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Development Of Automatic Maize Quality Assessment System Using Image Processing Techniques
    (Addis Ababa University, 2015-11) Hailemichael, Daniel; Assabie, Yaregal (PHD)
    Maize is a very important crop where its circulation in the market has to conform to the rules of quality inspection. Currently, maize sample quality inspection is performed manually by human experts through visual evaluation and the constituents will be classified into foreign matter, rotten and diseased, healthy, broken, discolored, shriveled and pest damaged kernels. However, visual evaluation requires significant amount of time, trained and experienced people. Besides, it is affected by bias and inconsistencies associated with human nature. Such approach will not be satisfactory for large scale inspection and grading unless fully automated. The goal of this research work is to develop a system capable of assessing the quality of maize sample constituents using digital image processing techniques and artificial neural network classifier based on the standard for maize set by the Ethiopian Standards Agency. A novel segmentation technique is proposed to segment and lay the foundation for feature extraction. A total of 24 features (14 color, 8 shape and 2 size) have been identified to model maize sample constituents. For classificat ion of maize samples, a feedforward artificial neural network classifier with backpropagat ion learning algorithm, 24 input and 7 output nodes, corresponding to the number of features and classes respectively has been designed. The network is trained and its performance is compared against other classifiers both empirically and based on supporting facts from the literature. For the purpose of training the classifier, a total of 534 kernels and foreign matters have been collected from Ethiopian Grain Trade Enterprise. The training data is randomly apportioned into training (70%) and testing (30%). The classifier achieved an overall classification accuracy of 97.8%. The success rates for detecting foreign, rotten and diseased, healthy, broken, discolored, shriveled and pest damaged kernels are 100%, 95.2%, 98.6%, 98.8%, 100%, 98.4%, and 94.8%, respectively. Keywords: Artificial neural network, Maize quality assessment, Reconstructed image, Merged image, Color image segmentation, Digital image processing, Color structure tensor
  • No Thumbnail Available
    Item
    Development Of Automatic Maize Quality Assessment System Using Image Processing Techniques
    (Addis Ababa University, 2015-11) Hailemichael, Daniel; Assabie, Yaregal (PHD)
    Maize is a very important crop where its circulation in the market has to conform to the rules of quality inspection. Currently, maize sample quality inspection is performed manually by human experts through visual evaluation and the constituents will be classified into foreign matter, rotten and diseased, healthy, broken, discolored, shriveled and pest damaged kernels. However, visual evaluation requires significant amount of time, trained and experienced people. Besides, it is affected by bias and inconsistencies associated with human nature. Such approach will not be satisfactory for large scale inspection and grading unless fully automated. The goal of this research work is to develop a system capable of assessing the quality of maize sample constituents using digital image processing techniques and artificial neural network classifier based on the standard for maize set by the Ethiopian Standards Agency. A novel segmentation technique is proposed to segment and lay the foundation for feature extraction. A total of 24 features (14 color, 8 shape and 2 size) have been identified to model maize sample constituents. For classificat ion of maize samples, a feedforward artificial neural network classifier with backpropagat ion learning algorithm, 24 input and 7 output nodes, corresponding to the number of features and classes respectively has been designed. The network is trained and its performance is compared against other classifiers both empirically and based on supporting facts from the literature. For the purpose of training the classifier, a total of 534 kernels and foreign matters have been collected from Ethiopian Grain Trade Enterprise. The training data is randomly apportioned into training (70%) and testing (30%). The classifier achieved an overall classification accuracy of 97.8%. The success rates for detecting foreign, rotten and diseased, healthy, broken, discolored, shriveled and pest damaged kernels are 100%, 95.2%, 98.6%, 98.8%, 100%, 98.4%, and 94.8%, respectively. Keywords: Artificial neural network, Maize quality assessment, Reconstructed image, Merged image, Color image segmentation, Digital image processing, Color structure tensor
  • No Thumbnail Available
    Item
    Evaluation and Development of Floriculture Supply Chain in Ethiopia, to Attenuate Environmental Impact and Logistics Cost
    (Addis Ababa University, 2013-01) Hailemichael, Daniel; Gebresenbet, Girma (Professor)
    Ethiopia is now Africa‟s second largest flower exporter after Kenya, with its export earnings growing by 500% over the past year. In 2008, there were 81 flower farms employing around 50,000 workers (over 70% women). Ethiopia‟s flower exports reached 100 million USD and the industry is one of the top four sources of foreign exchange for the country. In less than a decade of experience, Ethiopia ranks second in Africa for flower exports, and fifth in Extra-EU exporters to the EU market. Annual average growth in number of firms and exports in 2003 to 2008 is around 380% and 638% respectively. Ethiopian growers can produce a very high quality product, which has a big demand on the market in the advantage of higher altitude of the country but at this moment it is still quiet important to bring this product correctly and on time into that market. This can be achieved by designing a good logistic system. That is why the main objective of this research is being describing the supply chain of floriculture in Ethiopia, determine main bottlenecks and develop efficient methodology in line with coordination possibilities and route optimization to reduce logistic cost and environmental impact. The majority of the farms are located in about 50 km radius of the capital city, Addis Ababa. These cluster areas will create an opportunity for collaboration among producers. From analysis results there is a probability of collaboration between farms found in these three clusters in transporting their products inland and they can save the inland transport cost significantly. Supply chain of floriculture in Ethiopia consists of different activities categorized as farm operations, inland transport, and cargo activities. In the farm activities the operation starts from cutting. Cutting is done by leaving two leaves at bottom of the rose tree. After cutting, the stem is collected in water bucket and taken to pre-cooling room and kept for 8-10hrs at temperature of 4-6 oc. After pre-cooling the sorting and packaging process begins. The packed flowers kept in cold room for 1 and ½ days at temperature of 2oc. Finally the bundles of flowers are placed in carton ( 23 bundles/carton) and placed back to the cold room. The next activity is inland transport operation and the last activity is the cargo transport to the Dutch auction market or other whole sellers. Most farms in Ethiopia use ground water for irrigation purpose this will create continues depletion of ground water. The use of chemicals will also create contamination of ground water and streams near to the farm locations are also getting contaminated by the chemicals used even if the effect is not significant the proper use of chemicals and safe disposal of west should be made by trained professionals for chemical protection. The chemical sprayers wear mask during chemical spraying but most of the workers are not trained for this special purpose. This will put the health of the workers in danger.
  • No Thumbnail Available
    Item
    Psychosocial Impacts of Autism on Families and their Perceptions on the Supports Provided at Joy Center NIA Foundation for Autistic Children In Addis Ababa
    (Addis Ababa University, 2014-09) Hailemichael, Daniel
    The purpose of this study was to assess the psychosocial impacts of autism and the support systems to families of children with autism and their perception of the supports provided. To do this, a narrative research design was used for the study and qualitative approach was employed. Data were gathered from Joy Center Nia Foundation for Autistic children in Addis Ababa, Ethiopia. First, the researcher availed himself to employ observervation session. Then, using interviews, focus group discussion and observation; three teachers, including one head of teachers, five parents have participated in the study to obtain the necessary data. Findings of the study revealed that these parents were getting the support they needed even though there were a number of support systems yet to be accomplished. Experience and educational level of families appeared to have significant relationship with the provision of the support system and its application. Besides, psychological problems such as depression, exculsion, anxiety, fear, etc had also been their major problems. Caregivers are also found to get subsistence amount of money which can otherwise affect the support system. Following the findings and conclusions drawn, it is recommended that the government and other pertinent bodies should work in collaboration with the management of the center in areas where families can benefit a lot and ameliorate their current problems. It is also recommended that the center should do its very best to make the center a conducive research place for all who come to carry out their studies