Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Democratic Diffusion Aggregation for Image Retrieval Abstract An image retrieval system is a computer system for browsing, searching and retrieving images from a large database of digital images. Most traditional and common methods of image retrieval utilize some method of adding metadata such as captioning', keywords, or descriptions to the images so that retrieval can be performed over the annotation words. Manual image annotation is timeconsuming, laborious and expensive; to address this, there has been a large amount of research done on automatic image annotation. Additionally, the increase in social web applications and the semantic web have inspired the development of several web-based image annotation tools. Content-based image retrieval is an important research topic in the multimedia filed. In large-scale image search using local features, image features are encoded and aggregated into a compact vector to avoid indexing each feature individually. In aggregation step, sum-aggregation is wildly used in many existing work and demonstrates promising performance. To address this problem, we propose a new aggregation method named democratic diffusion aggregation with weak spatial context embedded. The main idea of our aggregation method is to re-weight the embedded vectors before sum-aggregation by considering the relevance among local descriptors. Different from previous work, by conducting a diffusion process on the improved kernel matrix, besides, considering the relevance of local descriptors from different images, we also discuss an efficient query fusion strategy which uses the initial to pranked image vectors to enhance the retrieval performance. Consistently improves the retrieval quality. Architecture Diagram: SYSTEM ANALYSIS EXISTING SYSTEM It shows that our methods outperform most of existing encoding methods. Although the orientation covariant aggregation achieves similar mAP performance on Holidays dataset with ours, the orientation covariant aggregation leads to higher dimensionality of vector representation and sensitivity to the orientation of image. In fact, our efficient aggregation methods are compatible with orientation covariant aggregation and can be enhanced with it if necessary. Note, with the benefit from query fusion, our method outperforms all of previous the early encoding methods, such as VLAD and Fisher Vector show high computational efficiency but poor retrieval accuracy. Although the encoding (embedding+ aggregation) complexity of MOP-CNN is similar with VLAD, it suffers high computational complexity in feature extraction step. PROPOSED SYSTEM Recently, several encoding methods are proposed to aggregate local descriptors into a compact vector, such as Fisher vectors Vector of locally aggregated descriptors and T-embedding method. Recently, several encoding methods are proposed to aggregate local descriptors into a compact vector, such as Fisher vectors Vector of locally aggregated descriptors and T-embedding method. We calculate the weighting coefficients more efficiently without any iterative optimization. Besides, considering the relevance of local descriptors from different images, we also discuss an efficient query fusion strategy which uses the initial to pranked image vectors to enhance the retrieval performance. Modules Image Retrieval: Image representation is one of the key issues for the content based image retrieval. With the explosive growth of Web images, the compact image representation has attracted great attention recently. Image Cropping: Feature Extraction: In the feature extraction step, the image is represented with a set of local descriptors. In the embedding step, each local descriptor is mapped into a highdimensional vector. Aggregation: The aggregation step integrates all the embedded vectors of an image into a single vector which obtains a compact representation for image retrieval. The main idea of our aggregation method is to re-weight embedded vectors of an image before sum aggregation. The weighting coefficients are calculated efficiently from pair wise similarities between local descriptors of an image. MVC Framework I have created database in local db. I have generated entity framework. It will store and fetch the data from the database. Model The model data will be using for controller and views. Controller: I have created three controllers. These controller classes are user defined functions. 1. User Controller 2. File Controller. 3. Image Controller 4. Admin Controller In User Controller, In have created 3 Action methods, Register, Login, Search, Logout File Controller, Upload the file. Image Controller, Crop the image and store it to the database. Admin Controller: Save all the details and store all the images. View: The controller will return view to renders the response. We are using Strongly Typed HTML format. SYSTEM SPECIFICATION HARDWARE REQUIREMENTS: System : Pentium IV 2.4 GHz. Hard Disk : 40 GB. Floppy Drive : 1.44 Mb. Monitor : 14’ Colour Monitor. Mouse : Optical Mouse. Ram : 512 Mb. SOFTWARE REQUIREMENTS: Operating system : Windows 7 Ultimate. Coding Language : MVC 4 Razor Front-End : Visual Studio 2012 Professional. Data Base : SQL Server 2008. CONCLUSION In this paper, we target on compact image representation for large-scale contentbased image retrieval. Based on Embedding vectors, firstly, we propose a fast democratic aggregation method embedded with weak spatial context. Compared with the original democratic aggregation, our approach significantly improves the efficiency with over ten times speedup while achieving comparable or even better retrieval accuracy. At the re-ranking step, we discuss a simple yet effective retrieval strategy, query fusion, to boost the retrieval performance of the compact image representation. Experimental results demonstrate consistent improvement in accuracy with this strategy. Our query fusion is verified based on exhausted search which needs to keep all original vectors in memory. For large scale image search equipped with approximate nearest neighbor search algorithms, we will investigate the query fusion in the case that the original feature vectors are discarded to save memory.