Invariant moment and learning vector quantization (LVQ NN) for images classification

Abstract

Image classification need two main components, i.e., features and classifier. The feature commonly used for classification of images with different scale is invariant moment; its value is invariant against the spatial transformation dealing with translation, scale and rotation. The classifier that is widely used for classification is LVQ NN. It is shallow network containing only two layers, the initial value of its weight is more fixed so that its output is more stable and its algorithm is relatively simple thus both training and testing process are run fast. Based on these facts, therefore, this research proposed a combination method of invariant moment and LVQ NN (IM-LVQ). The ability of the proposed method would be compared with two other methods. Firstly, the combination method of invariant moment and Euclidean distance (IM-ED). Secondly, the combination of invariant moment and principal component analysis (IM-PCA). The performance of the three methods was evaluated quantitatively with several metrics, viz.: Confusion Matrix, Accuracy, Precision, True Positive Rate, False Positive Rate, ROC graph and training time. The evaluation of the metrics was based upon the changing (reduction) of the scale/size of training image. The results showed that IM-LVQ method outperformed the other two methods in aforementioned metrics.