Scene Semantics Recognition Based on Target Detection and Fuzzy Reasoning

Wei-Liang Liu ； Chang-Liang Liu ； Yong-Jun Lin

《Research Journal of Applied Sciences, Engineering and Technology》 7卷5期 (2014/02) Pp. 970-974

並列摘要

In order to get better image semantics recognition, a recognition system based on object detection and fuzzy reasoning is presented in this study. The system contains four parts: image preprocessing, feature extraction, target recognition and fuzzy reasoning machine. Compared with other methods, the outputs of target detectors are fuzzed, the fuzzy relationships between targets are extracted and fuzzy inference is performed using fuzzy automata. The experiment indicates that this method could overcome the problems of false positive and false negative of pattern classifiers and perform relatively more accurate image semantics recognition than other existing methods.

並列關鍵字

Feature extraction ； fuzzy reasoning machine ； image preprocessing ； semantics recognition ； target detection