Development of a low-cost digital image processing system for oranges selection using hopfield networks

Characterising Colour Feature Descriptors for Ficus carica L. Ripeness Classification Based on Artificial Neural Network (ANN)

Excessive feature dimensions impact the effectiveness of machine learning, computationally expensive and the analysis of feature correlations in the engineering area. This paper uses the colour descriptor to get the most optimal feature to improve time consumption and efficiency. This study investigated Ficus carica L. (figs) with three classification stages. The ripening classification of fig was examined using colour features descriptor with two different colour models, RGB and HSV. In addition, the machine learning classification model based on Artificial Neural Network (ANN) that utilised the Feed-Forward Neural Network (FFNN) model to classify the ripeness of fig is considered in this characterisation. Five different numbers of binning were characterised for RGB and HSV. Both colour feature descriptors were compared in terms of accuracy, sensitivity, precision, and time consumption to identify the dimension of the optimal feature. Based on the result, reducing the size of images will improve the time consumption with comparable accuracy. Moreover, the reduction of features dimension cannot be too small or too big due to inequitable enough to differentiate the ripeness stages and lead to a false error state. The optimal features dimension in binning for RGB was 8 (R/G/B) bins with 96.7% accuracy. Meanwhile, 96.7% accuracy for HSV at 15, 5, and 5 (H, S, V) bins as optimal colour features.

Developed an Automated Design Sorting System According to Outer Edges of Object

The automated sorting systems are used in the industrial sectors to increase the rate of production. This research developed the sorting system by using a vision machine to detect the matching of capturing image with the storage base image. The system will be matching and sorting in real-time with 5 cm/s conveyor belt speed. The vision system is based on three stages to arrive at the sorting decision. The first stage is to covert the capturing image to a binary image, the second stage is applying edge detection of the product, and the third stage is matching this result with the base image. The system was successful to sort any product with complexity in shape and with high efficiency. The system sorting can be detected and sorted any product/machine element at any position or orientation. The system uses real-time analysis in order to provide the required results. The results arrived at the sorting gate at the end conveyer belt of the system if open that means the product matching. Three different products were selected in order to investigate the response and the accuracy of the results. It was found that the maximum of error to detect the product is not exceeding 2% for all cases.