http://ir.haramaya.edu.et//hru/handle/123456789/215 Tue, 07 Apr 2026 13:20:57 GMT 2026-04-07T13:20:57Z http://ir.haramaya.edu.et//hru/handle/123456789/8075 DETERMINATION OF LEAF RUST (Puccinia Allii Rudolphi) SEVERITY AND ITS MANAGEMENT ON GARLIC (Allium Sativum L.) USING IMAGE PROCESSING TECHNIQUES Yohanis Boki; (PhD) Getachew Abebe; Prof. Mashilla Dejene Traditionally, fungicides are applied manually without objectively quantifying the severity of garlic rust disease. In this research, digital image processing techniques were employed to develop and test an algorithm that could measure the severity of leaf rust on garlic and manage the disease at various levels. Data on leaf rust were collected from seven groups of garlic plants, with samples taken from the top, middle, and lower leaves. Each group consisted of three pots, each containing two plants after thinning. The control group received no fungicide (Tilt or Propiconazole), while group 4 was treated with the recommended 60 mL of Tilt fungicide. Groups 1-3 received 10%, 5%, and 0% less than the recommended volume (6 mL, 3 mL, and 0 mL, respectively). Groups 5-7 received 5%, 10%, and 100% more than the recommended volume (3 mL, 6 mL, and 60 mL, respectively). The fungicide was sprayed on garlic leaves four times to observe the treatment progression and optimize the fungicide volume. A total of 504 garlic leaf images were captured across four rounds: before spraying fungicide, after the first spray, after the second spray, and after the third spray. The total leaf area and the diseased areas were extracted from these images. The relative error between experts' assessments and the imaging algorithm was found to be 4.2%. The algorithm developed for estimating disease severity using image processing technology demonstrated an accuracy of 95.80%. The results indicate the potential of this technology for measuring garlic rust severity and optimizing fungicide application. 73p. Sat, 01 Jun 2024 00:00:00 GMT http://ir.haramaya.edu.et//hru/handle/123456789/8075 2024-06-01T00:00:00Z http://ir.haramaya.edu.et//hru/handle/123456789/7981 APPLICATION OF HOUGH TRANSFORM ON COUNTERFEIT IDENTIFICATION OF ETHIOPIAN PAPER CURRENCY DENOMINATION ASHENAFI AYELE; Getachew Abebe (PhD) Counterfeiting is one of the critical problems affecting cash transactions. Counterfeit banknotes are becoming serious threats hampering the smooth transactions in Ethiopia. Hence, the availability of such counterfeit notes in the market needs the automation of money identification system. The importance of automatic methods for currency recognition has been increasing in the time being because of circulation of fake notes increased in today’s economy. This recognition system contains basic image processing techniques such as image acquisition, image preprocesses, feature extraction and identification using Hough Transform. Counterfeit currency identification was carried out on wide stripe and check for blind security features, which involved employing the appropriate image preprocessing algorithms to enhance the input image applying HT technique to extract security features and evaluating the performance of the Hough Transform algorithm applying on both genuine and counterfeit Ethiopian banknotes. Training, validation and testing was carried on 120 genuine and counterfeit currency notes. The results showed that using the proposed algorithm the identification rate for new, old and very old notes is 100%, 84% and 80% respectively. 77 Mon, 01 Apr 2024 00:00:00 GMT http://ir.haramaya.edu.et//hru/handle/123456789/7981 2024-04-01T00:00:00Z http://ir.haramaya.edu.et//hru/handle/123456789/6995 AUTOMATIC MAIZE VARIETIES IDENTIFICATION USING ARTIFICIAL NEURAL NETWORKIMAGE CLASSIFICATION TECHNIQUES Getachew Gobena; Getachew Abebe (PhD) Maize is an economically important crop, which is contributing the highest of all food, industrial product and animal feeding revenues in Ethiopia. It is also the major cash crop of our country and farmers of the maize producing regions. Therefore, maize has a unique quality that fetches premium prices in the world market. However, to exploit this good opportunity the distinct unique shape, color and size of maize need to be maintained and improved. The first step to improve the crop is to understand the exiting variability in the genotype/accession. Therefore, in this research work, a digital image processing technique was used to classify maize seed based on their Color, morphological, and textural features. Artificial neural network (ANN) was used to classify maize varieties that are grown under different agronomic management and to check the maize seeds, which are grown under the same agronomic management. Four classification set-ups were used, which are classification based on color features, morphology features, texture features and combination of color, texture and morphology features. For the analysis, 12 colors, 6- morphological and 12 textural features, totally 30 features were extracted from images of maize grains. Four experimental classification setups were applied. Setups 1, 2, 3 and 4 are classification designs by using color, morphology, texture and combination of morphology and color features, respectively. For all setups 160 images were used as inputs of the ANN. From this datasets, 70%(112) images were used for training the ANN while the remaining 30%(48) images were used for both testing and validation. The accuracy of classification using color, feature 99.4%, morphological feature was 87.5%, texture features was 100% and combination of morphological and color features was 87.5% for maize seeds. 68 Wed, 01 Nov 2023 00:00:00 GMT http://ir.haramaya.edu.et//hru/handle/123456789/6995 2023-11-01T00:00:00Z http://ir.haramaya.edu.et//hru/handle/123456789/6958 AUTOMATIC MAIZE VARIETIES IDENTIFICATION USING ARTIFICIAL NEURAL NETWORKIMAGE CLASSIFICATION TECHNIQUES Getachew Gobena Wabulcho; Getachew Abebe (PhD Maize is an economically important crop, which is contributing the highest of all food, industrial product and animal feeding revenues in Ethiopia. It is also the major cash crop of our country and farmers of the maize producing regions. Therefore, maize has a unique quality that fetches premium prices in the world market. However, to exploit this good opportunity the distinct unique shape, color and size of maize need to be maintained and improved. The first step to improve the crop is to understand the exiting variability in the genotype/accession. Therefore, in this research work, a digital image processing technique was used to classify maize seed based on their Color, morphological, and textural features. Artificial neural network (ANN) was used to classify maize varieties that are grown under different agronomic management and to check the maize seeds, which are grown under the same agronomic management. Four classification set-ups were used, which are classification based on color features, morphology features, texture features and combination of color, texture and morphology features. For the analysis, 12 colors, 6- morphological and 12 textural features, totally 30 features were extracted from images of maize grains. Four experimental classification setups were applied. Setups 1, 2, 3 and 4 are classification designs by using color, morphology, texture and combination of morphology and color features, respectively. For all setups 160 images were used as inputs of the ANN. From this datasets, 70%(112) images were used for training the ANN while the remaining 30%(48) images were used for both testing and validation. The accuracy of classification using color, feature 99.4%, morphological feature was 87.5%, texture features was 100% and combination of morphological and color features was 87.5% for maize seeds. 68 Wed, 01 Nov 2023 00:00:00 GMT http://ir.haramaya.edu.et//hru/handle/123456789/6958 2023-11-01T00:00:00Z