No abstract

No abstract

No abstract

No abstract

No abstract

No abstract

Fruit size, dimensions and its geometrical attributes are important physical properties of agricultural produce. More specifically, the estimation of mean fruit size is needed in meeting quality standards, increasing market value, monitoring fruit growth, predicting yields and assessing optimal levels of fertilization and irrigation, as well as the design and development of sizing mechanisms. In this study, tangerine volume was measured using image processing technique. The actual volume of tangerine was obtained by water displacement method. In image processing method, we used two CCD cameras that were situated at right angle to each other in order to give us two perpendicular images of tangerines. By removing the background and dividing the image into a number of distinct sectors, we were able to calculate the surface area and volume of each sector. The volume of fruit was then obtained by adding up the volume of all sectors. Fifty tangerines in three replications were examined to determine the accuracy of the algorithm. The volume obtained from image processing was compared to the actual volume determined by the water displacement method using the t-test. The obtained result was not significantly different from the actual volume (P > 0.05). In conclusion, image processing technique provides a simple and efficient methodology for estimating tangerine volume.

Vibration analysis is an accepted method in condition monitoring of machines, since it can provide useful and reliable information about machine working condition. This paper surveys a new scheme for fault diagnosis of main journal-bearings of internal combustion (IC) engine based on power spectral density (PSD) technique and two classifiers, namely, K-nearest neighbor (KNN) and artificial neural network (ANN). Vibration signals for three different conditions of journal-bearing; normal, with oil starvation condition and extreme wear fault were acquired from an IC engine. PSD was applied to process the vibration signals. Thirty features were extracted from the PSD values of signals as a feature source for fault diagnosis. KNN and ANN were trained by training data set and then used as diagnostic classifiers. Variable K value and hidden neuron count (N) were used in the range of 1 to 20, with a step size of 1 for KNN and ANN to gain the best classification results. The roles of PSD, KNN and ANN techniques were studied. From the results, it is shown that the performance of ANN is better than KNN. The experimental results dèmonstrate that the proposed diagnostic method can reliably separate different fault conditions in main journal-bearings of IC engine.