Real-Time Image Recognition with the Parallel Directed Enumeration Method

Lecture Notes in Computer Science. 2013. Vol. 7963. P. 123–132.

Савченко А. В.

The parallel computing algorithms are explored to improve the efficiency of image recognition with large database. The novel parallel version of the directed enumeration method (DEM) is proposed. The experimental study results in face recognition problem with FERET and Essex datasets are presented. We compare the performance of our parallel DEM with the original DEM and parallel implementations of the nearest neighbor rule and conventional Best Bin First (BBF) k-d tree. It is shown that the proposed method is characterized by increased computing efficiency (2-10 times in comparison with exhaustive search and the BBF) and lower error rate than the original DEM.

Ключевые слова: автоматическое распознавание изображений, метод направленного перебора, Image recognition, directed enumeration method, face recognition, probabilistic neural network with homogeneity testing, распознавание лиц, вероятностная нейронная сеть с проверкой однородности

ПУБЛИКАЦИЯ ПОДГОТОВЛЕНА ПО РЕЗУЛЬТАТАМ ПРОЕКТА: Статистическая классификация выборки дискретных объектов на основе вероятностной нейронной сети с проверкой однородности (2013)