Determination of weight percentage moldy corn kernels from bulk samples using flatbed scanner
2007
Bulaong, M.C. | Madamba, P.S.
A computer vision system for determination of weight percentage moldy kernels (WPMK) of corn (Zea mays L.) from bulk samples was developed. The system consists of a flatbed scanner and a desktop computer equipped with an image processing and artificial neural network (ANN) softwares. Images of bulk samples of corn with various levels of moldy kernels were taken using a flatbed scanner under a blue background with backlighting to eliminate shadows. Color and texture features were extracted from corn images and used as inputs for training, validation and testing of models based on canonical discriminant analysis (CDA) and ANN. The ANN performed consistently better than CDA in classifying corn grains into different WPMK levels. The ANN model based on color features extracted from red, green, and blue (RGB) histogram and texture features extracted from hue, saturation and brightness (HSB) color space obtained the highest correlation coefficient (r square) of 0.90 to 0.99 between predicted and actual WPMK. The study proved that a flatbed scanner can be used as a low-cost alternative to digital camera for estimating WPMK from images of bulk corn samples.
显示更多 [+] 显示较少 [-]