Yazar "Kavdir, I" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    Apple sorting using artificial neural networks and spectral imaging
    (Amer Soc Agricultural Engineers, 2002) Kavdir, I; Guyer, DE
    Empire and Golden Delicious apples were sorted based on their surface quality conditions using backpropagation neural networks. Pixel gray values and texture features obtained from the entire apple image were used as input to artificial neural network classifiers. Two classification applications were performed: a 2-class classification that included a defective (or stem/calyx) apple group and a good apple group, and a 5-class classification that included all the defective and good apple groups. Effective image resolution was evaluated to shorten the training and testing times in classification with neural networks. Resolution size of 60 x 80 pixels was identified to be efficient and used in all of the classification applications. Effective spectral bands for identification of specific surface characteristics were determined in the 2-class and 5-class classification applications. Artificial neural network classifiers successfully separated apples with defects from non-defective apples without confusing the stem/calyx with defects. Classification success in the 2-class classification ranged from 89.2% to 100%. In the. 5-class classification, classification success for Empire apples was between 93.8% and 100%, while classification success for Golden Delicious apples was between 89.7% and 94.9% based on the features used.
  • [ X ]
    Öğe
    Comparison of artificial neural networks and statistical classifiers in apple sorting using textural features
    (Academic Press Inc Elsevier Science, 2004) Kavdir, I; Guyer, DE
    Empire and Golden Delicious apples were classified based on their surface quality conditions using backpropagation neural networks (BPNN) and statistical classifiers such as decision tree (DT), K nearest neighbour (K-NN) and Bayesian with textural features (and histogram features only with the BPNN classifier) extracted using all the pixels in an entire apple image. Two classification applications were performed: two subsets that included a defective (or stem/calyx) apple group and a good apple group; and five subsets that included all the defective (leaf roller, bruise and puncture on Empire, and bruise bitter pit and russet on Golden Delicious) and good apple groups (good tissue and stem/calyx views). With two subsets, classification accuracy using textural features ranged between 72(.)2 and 100% for Empire apples while it ranged between 76(.)5 and 100% for Golden Delicious apples. Results obtained using histogram features were significantly lower than the other classification applications. With five subsets, slightly lower recognition accuracies were obtained; the BPNN using textural features performed 93(.)8% success rate in recognising Empire apples. However, for Golden Delicious apples, all the classifiers produced similar accuracy rates ranging between 85(.)9 and 89(.)7%. Results obtained from the BPNN using histogram features were significantly lower than the classification applications using textural features. (C) 2004 Silsoe Research Institute. All rights reserved Published by Elsevier Ltd.
  • [ X ]
    Öğe
    Discrimination of sunflower, weed and soil by artificial neural networks
    (Elsevier Sci Ltd, 2004) Kavdir, I
    Selective application of herbicide to weeds at an early stage in crop growth is an important aspect of site-specific management of field crops, both economically and environmentally. This paper describes the application of a neural network classifier to differentiate between 2 and 3 weeks old sunflower plants and common cocklebur weeds of similar size, shape and colour. Colour images were obtained by a digital camera, in natural sunlight. A specific objective was to minimise the subsequent image processing operations needed to enhance the images and to extract the features needed by a back propagation neural network classifier. Neural network structures with different numbers of hidden layers and neurons in them were tested to find the optimal classifier. The maximum number of correctly recognised images in distinguishing weeds from sunflower plants was 71 (out of 86), while it was 82 and 74 in separating sunflower and weed images from bare soil images, respectively. (C) 2004 Elsevier B.V. All rights reserved.
  • [ X ]
    Öğe
    Technical and Economical Analysis of Some Fruits Hand Harvested in Canakkale, and Determination of Some Propeties of Fruits Related with Mechanical Harvest
    (Univ Namik Kemal, 2009) Kocabiyik, H.; Kavdir, I; Ozpinar, S.
    The aim of this study is to obtain work efficiency, energy of labor force, and some physico-mechanical properties such as skin failure, tensile force and the ratio of fruit mass to tensile force for harvesting of apple, peach, apricot, cherry and plum. Mechanical properties were analysed through the puncture test and tensile test. According to the measuring and results of evaluation, work efficiency ranged from 10.26 to 230.97 kg/h for all fruits. Energy of labor force was beetwen 11.58 and 260.22 MJ/ton for all fruits. The highest energy of labor force was determined for cherry harvest. The ratio of fruit mass to tensile force was higher than 1 for all fruits.