Currently, the presence of wood is becoming increasingly scarce. In addition, recognition still using experts, who basing their judgments on characteristics that can be seen by eye directly such as color, texture and so on. However, experts are few have a disadvantage results obtained not sufficiently accurate time consuming. The purpose this research to develop Indonesian commercial woods clas...

State universities have a library as facility to support students’ education and science, which contains various books, journals, final assignments. An intelligent system for classifying documents is needed ease visitors in higher form of service students. The that are the generally result research. Various complaints related imbalance data texts categories based on irrelevant document titles w...

The recognition of symbols within document images is one the most relevant steps involved in Document Analysis field. While current state-of-the-art methods based on Deep Learning are capable adequately performing this task, they generally require a vast amount data that has to be manually labeled. In paper, we propose self-supervised learning-based method addresses task by training neural-base...