A Fast Content-Based Image Retrieval Method Using Deep Visual Features
This work addresses scalability issues in image retrieval systems for domains like document and medical analysis, though it is incremental as it builds on existing deep visual features and indexing techniques.
The paper tackled the problem of fast and scalable content-based image retrieval for big data applications by proposing a method that pre-indexes L2 norm and cosine similarity in Elasticsearch, achieving effective and efficient results on the ImageNet dataset with a VGG-16 model.
Fast and scalable Content-Based Image Retrieval using visual features is required for document analysis, Medical image analysis, etc. in the present age. Convolutional Neural Network (CNN) activations as features achieved their outstanding performance in this area. Deep Convolutional representations using the softmax function in the output layer are also ones among visual features. However, almost all the image retrieval systems hold their index of visual features on main memory in order to high responsiveness, limiting their applicability for big data applications. In this paper, we propose a fast calculation method of cosine similarity with L2 norm indexed in advance on Elasticsearch. We evaluate our approach with ImageNet Dataset and VGG-16 pre-trained model. The evaluation results show the effectiveness and efficiency of our proposed method.