Partial Order Structure Based Image Retrieval

Image retrieval plays an important role in the growing computer vision applications. The computation of the unrelated images in large scale image retrieval task seriously reduces the retrieval efficiency. In this paper, a new Partial Order Structure (POS) based image retrieval method is proposed. Partial order structure diagram is an effective visualization tool in Formal Concept Analysis (FCA) theory, including object partial order structure diagram and attribute partial order structure diagram. There are two contributions in this paper. First, we design an association rule according to the object partial order structure (OPOS) method to measure the correlation between the query image and the database, and then improve the database to be retrieved. Second, we perform a query expansion according to the attribute partial order structure (APOS) method to improve the generalization ability of the query information. Experimental results on two databases verify the effectiveness of the proposed algorithm.

[1]  Victor S. Lempitsky,et al.  Neural Codes for Image Retrieval , 2014, ECCV.

[2]  Yu Liu,et al.  DeepIndex for Accurate and Efficient Image Retrieval , 2015, ICMR.

[3]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Victor S. Lempitsky,et al.  Aggregating Local Deep Features for Image Retrieval , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[5]  Robinson Piramuthu,et al.  HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Josef Sivic,et al.  NetVLAD: CNN Architecture for Weakly Supervised Place Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Jun Jing,et al.  A VISUALIZATION METHOD FOR CHINESE MEDICINE KNOWLEDGE DISCOVERY BASED ON FORMAL CONCEPT ANALYSIS , 2013 .

[8]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[9]  Noel E. O'Connor,et al.  Bags of Local Convolutional Features for Scalable Instance Search , 2016, ICMR.

[10]  Xiaomin Wang,et al.  A CALCULATION OF FORMAL CONCEPT BY ATTRIBUTE TOPOLOGY , 2013 .

[11]  Michael Isard,et al.  Lost in quantization: Improving particular object retrieval in large scale image databases , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Takayuki Okatani,et al.  Understanding Convolutional Neural Networks in Terms of Category-Level Attributes , 2014, ACCV.

[13]  Atsuto Maki,et al.  A Baseline for Visual Instance Retrieval with Deep Convolutional Networks , 2014, ICLR 2015.

[14]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[15]  Weihong Deng,et al.  Very deep convolutional neural network based image classification using small training sample size , 2015, 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR).

[16]  Bernhard Ganter,et al.  Formal Concept Analysis , 2013 .

[17]  Cordelia Schmid,et al.  Aggregating local descriptors into a compact image representation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Larry S. Davis,et al.  Exploiting local features from deep networks for image retrieval , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[19]  Svetlana Lazebnik,et al.  Multi-scale Orderless Pooling of Deep Convolutional Activation Features , 2014, ECCV.

[20]  Ji Wan,et al.  Deep Learning for Content-Based Image Retrieval: A Comprehensive Study , 2014, ACM Multimedia.