Inverted indexing of images for face search and recognition

There are many different possible applications for face recognition, but this problem has not been solved properly. Therefore face recognition is still very important task. As an example of its application, face recognition could be useful for security systems to provide safety. For these systems it is necessary to identify the person among many others. In this case this work presents new approach in data indexing, which provides fast retrieval in big image collections. Data indexing in this research has five stages. First, we detect and extract the area containing face, second we align face, and then we detect areas containing eyes and eyebrows, nose, mouth. On the next stage we find key points of each area using histograms of oriented gradients (HOG) descriptors and finally index these descriptors with help of quantization procedure. The experimental analysis of this method is also performed. This paper shows that performing method has results at the level of state-of-the-art face recognition methods, but it also gives results fast that is important for the systems that provide safety.